diff --git a/json_data/2023/main/3d-from-a-single-image-and-shape-from-x.json b/json_data/2023/main/3d-from-a-single-image-and-shape-from-x.json new file mode 100644 index 0000000..52059a2 --- /dev/null +++ b/json_data/2023/main/3d-from-a-single-image-and-shape-from-x.json @@ -0,0 +1,1838 @@ +[ + { + "title": "Aggregating Feature Point Cloud for Depth Completion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Aggregating_Feature_Point_Cloud_for_Depth_Completion_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Coordinate Transformer: Achieving Single-Stage Multi-Person Mesh Recovery from Videos", + "base_url": null, + "title_page": null, + "github": "Li-Hao-yuan/CoordFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Coordinate_Transformer_Achieving_Single-stage_Multi-person_Mesh_Recovery_from_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10334", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yasarla_MAMo_Leveraging_Memory_and_Attention_for_Monocular_Video_Depth_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14336", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments", + "base_url": null, + "title_page": null, + "github": "Syniez/SlaBins", + "web_page": null, + "github_page": "https://syniez.github.io/SlaBins/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yasarla_MAMo_Leveraging_Memory_and_Attention_for_Monocular_Video_Depth_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Creative Birds: Self-Supervised Single-View 3D Style Transfer", + "base_url": null, + "title_page": null, + "github": "wrk226/creative_birds", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Creative_Birds_Self-Supervised_Single-View_3D_Style_Transfer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14127", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Dynamic PlenOctree for Adaptive Sampling Refinement in Explicit NeRF", + "base_url": null, + "title_page": null, + "github": "hbai98/DOT", + "web_page": null, + "github_page": "https://vlislab22.github.io/DOT/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bai_Dynamic_PlenOctree_for_Adaptive_Sampling_Refinement_in_Explicit_NeRF_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15333", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "i9MnoFhH8Ec", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "CORE: Co-Planarity Regularized Monocular Geometry Estimation with Weak Supervision", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_CORE_Co-planarity_Regularized_Monocular_Geometry_Estimation_with_Weak_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Relightify: Relightable 3D Faces from a Single Image via Diffusion Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://foivospar.github.io/Relightify/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Papantoniou_Relightify_Relightable_3D_Faces_from_a_Single_Image_via_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.06077", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "N5pSN4Pc0JM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "GLA-GCN: Global-Local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video", + "base_url": null, + "title_page": null, + "github": "bruceyo/GLA-GCN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_GLA-GCN_Global-local_Adaptive_Graph_Convolutional_Network_for_3D_Human_Pose_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.05853", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Calibrating Panoramic Depth Estimation for Practical Localization and Mapping", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Calibrating_Panoramic_Depth_Estimation_for_Practical_Localization_and_Mapping_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14005", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "KXz8IwrtJWg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "SimNP: Learning Self-Similarity Priors between Neural Points", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wewer_SimNP_Learning_Self-Similarity_Priors_Between_Neural_Points_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03809", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "AGG-Net: Attention Guided Gated-Convolutional Network for Depth Image Completion", + "base_url": null, + "title_page": null, + "github": "htx0601/AGG-Net", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_AGG-Net_Attention_Guided_Gated-Convolutional_Network_for_Depth_Image_Completion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01624", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data", + "base_url": null, + "title_page": null, + "github": "szymanowiczs/viewset-diffusion", + "web_page": null, + "github_page": "https://szymanowiczs.github.io/viewset-diffusion", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Szymanowicz_Viewset_Diffusion_0-Image-Conditioned_3D_Generative_Models_from_2D_Data_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.07881", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion", + "base_url": null, + "title_page": null, + "github": "donghaotian123/CVSformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_CVSformer_Cross-View_Synthesis_Transformer_for_Semantic_Scene_Completion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07938", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds", + "base_url": null, + "title_page": null, + "github": "ZhangCYG/U-RED", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Di_U-RED_Unsupervised_3D_Shape_Retrieval_and_Deformation_for_Partial_Point_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06383", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Single Depth-Image 3D Reflection Symmetry and Shape Prediction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Single_Depth-image_3D_Reflection_Symmetry_and_Shape_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Self-Supervised Monocular Depth Estimation: Let's Talk About the Weather", + "base_url": null, + "title_page": null, + "github": "kieran514/robustdepth", + "web_page": null, + "github_page": "https://kieran514.github.io/Robust-Depth-Project/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Saunders_Self-supervised_Monocular_Depth_Estimation_Lets_Talk_About_The_Weather_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08357", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "zGXzpJAWjcQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Mesh2Tex: Generating Mesh Textures from Image Queries", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://alexeybokhovkin.github.io/mesh2tex/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bokhovkin_Mesh2Tex_Generating_Mesh_Textures_from_Image_Queries_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.05868", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "tY6pPHN5v9Q", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Sketch and Text Guided Diffusion Model for Colored Point Cloud Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Sketch_and_Text_Guided_Diffusion_Model_for_Colored_Point_Cloud_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.02874", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation", + "base_url": null, + "title_page": null, + "github": "shawLyu/Occ-SDF-Hybrid", + "web_page": null, + "github_page": "https://shawlyu.github.io/Occ-SDF-Hybrid/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lyu_Learning_a_Room_with_the_Occ-SDF_Hybrid_Signed_Distance_Function_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09152", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Robust Geometry-Preserving Depth Estimation using Differentiable Rendering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Robust_Geometry-Preserving_Depth_Estimation_Using_Differentiable_Rendering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.09724", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://jianglongye.com/featurenerf/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_FeatureNeRF_Learning_Generalizable_NeRFs_by_Distilling_Foundation_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12786", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "One-Shot Implicit Animatable Avatars with Model-based Priors", + "base_url": null, + "title_page": null, + "github": "huangyangyi/ELICIT", + "web_page": null, + "github_page": "https://huangyangyi.github.io/ELICIT/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_One-shot_Implicit_Animatable_Avatars_with_Model-based_Priors_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.02469", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis", + "base_url": null, + "title_page": null, + "github": "XinyaChen21/Veri3d", + "web_page": null, + "github_page": "https://xdimlab.github.io/VeRi3d/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_VeRi3D_Generative_Vertex-based_Radiance_Fields_for_3D_Controllable_Human_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04800", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Diffuse3D: Wide-Angle 3D Photography via Bilateral Diffusion", + "base_url": null, + "title_page": null, + "github": "yutaojiang1/Diffuse3D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Diffuse3D_Wide-Angle_3D_Photography_via_Bilateral_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://csyhquan.github.io/manuscript/23-iccv-Diffuse3D%20Wide-Angle%203D%20Photography%20via%20Bilateral%20Diffusion.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "5mL6AMEvPSQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dang_AutoSynth_Learning_to_Generate_3D_Training_Data_for_Object_Point_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11170", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction", + "base_url": null, + "title_page": null, + "github": "zhangy76/KNOWN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Body_Knowledge_and_Uncertainty_Modeling_for_Monocular_3D_Human_Body_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.00799", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Accurate 3D Face Reconstruction with Facial Component Tokens", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Accurate_3D_Face_Reconstruction_with_Facial_Component_Tokens_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Metric3D: Towards Zero-Shot Metric 3D Prediction from a Single Image", + "base_url": null, + "title_page": null, + "github": "YvanYin/Metric3D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yin_Metric3D_Towards_Zero-shot_Metric_3D_Prediction_from_A_Single_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10984", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "I3PkukQ3_F8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Reconstructing Interacting Hands with Interaction Prior from Monocular Images", + "base_url": null, + "title_page": null, + "github": "binghui-z/InterPrior_pytorch", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zuo_Reconstructing_Interacting_Hands_with_Interaction_Prior_from_Monocular_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14082", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "SparseNeRF: Distilling Depth Ranking for Few-Shot Novel View Synthesis", + "base_url": null, + "title_page": null, + "github": "Wanggcong/SparseNeRF", + "web_page": null, + "github_page": "https://sparsenerf.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_SparseNeRF_Distilling_Depth_Ranking_for_Few-shot_Novel_View_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16196", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "V0yCTakA964", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Beyond the Limitation of Monocular 3D Detector via Knowledge Distillation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Beyond_the_Limitation_of_Monocular_3D_Detector_via_Knowledge_Distillation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://project-hiface.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chai_HiFace_High-Fidelity_3D_Face_Reconstruction_by_Learning_Static_and_Dynamic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11225", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape", + "base_url": null, + "title_page": null, + "github": "XuJiacong/Animal3D", + "web_page": null, + "github_page": "https://xujiacong.github.io/Animal3D/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Animal3D_A_Comprehensive_Dataset_of_3D_Animal_Pose_and_Shape_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11737", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery", + "base_url": null, + "title_page": null, + "github": "xljh0520/JOTR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_JOTR_3D_Joint_Contrastive_Learning_with_Transformers_for_Occluded_Human_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16377", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "D-IF: Uncertainty-Aware Human Digitization via Implicit Distribution Field", + "base_url": null, + "title_page": null, + "github": "psyai-net/D-IF_release", + "web_page": null, + "github_page": "https://yxt7979.github.io/idf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_D-IF_Uncertainty-aware_Human_Digitization_via_Implicit_Distribution_Field_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08857", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "3D Distillation: Improving Self-Supervised Monocular Depth Estimation on Reflective Surfaces", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_3D_Distillation_Improving_Self-Supervised_Monocular_Depth_Estimation_on_Reflective_Surfaces_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "DeformToon3D: Deformable Neural Radiance Fields for 3D Toonification", + "base_url": null, + "title_page": null, + "github": "junzhezhang/DeformToon3D", + "web_page": "https://www.mmlab-ntu.com/project/deformtoon3d/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_DeformToon3D_Deformable_Neural_Radiance_Fields_for_3D_Toonification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04410", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "MonoDETR: Depth-Guided Transformer for Monocular 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "ZrrSkywalker/MonoDETR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_MonoDETR_Depth-guided_Transformer_for_Monocular_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2203.13310", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "ReLeaPS: Reinforcement Learning-based Illumination Planning for Generalized Photometric Stereo", + "base_url": null, + "title_page": null, + "github": "jhchan0805/ReLeaPS", + "web_page": null, + "github_page": "https://jhchan0805.github.io/ReLeaPS/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chan_ReLeaPS__Reinforcement_Learning-based_Illumination_Planning_for_Generalized_Photometric_Stereo_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "5D4NBlf-L3w", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Convex Decomposition of Indoor Scenes", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Vavilala_Convex_Decomposition_of_Indoor_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.04246", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes", + "base_url": null, + "title_page": null, + "github": "zubair-irshad/NeO-360", + "web_page": null, + "github_page": "https://zubair-irshad.github.io/projects/neo360.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Irshad_NeO_360_Neural_Fields_for_Sparse_View_Synthesis_of_Outdoor_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12967", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "avmylyL_V8c", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields", + "base_url": null, + "title_page": null, + "github": "freemty/urbanGIRAFFE", + "web_page": null, + "github_page": "https://lv3d.github.io/urbanGIRAFFE/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_UrbanGIRAFFE_Representing_Urban_Scenes_as_Compositional_Generative_Neural_Feature_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14167", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Efficient Converted Spiking Neural Network for 3D and 2D Classification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lan_Efficient_Converted_Spiking_Neural_Network_for_3D_and_2D_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Distribution-Aligned Diffusion for Human Mesh Recovery", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://gongjia0208.github.io/HMDiff/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Foo_Distribution-Aligned_Diffusion_for_Human_Mesh_Recovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13369", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Towards Zero-Shot Scale-Aware Monocular Depth Estimation", + "base_url": null, + "title_page": null, + "github": "tri-ml/vidar", + "web_page": "https://sites.google.com/view/tri-zerodepth", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guizilini_Towards_Zero-Shot_Scale-Aware_Monocular_Depth_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.17253", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Learning Depth Estimation for Transparent and Mirror Surfaces", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://cvlab-unibo.github.io/Depth4ToM/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Costanzino_Learning_Depth_Estimation_for_Transparent_and_Mirror_Surfaces_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15052", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction", + "base_url": null, + "title_page": null, + "github": "mlpc-ucsd/Uni-3D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Uni-3D_A_Universal_Model_for_Panoptic_3D_Scene_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "3D VR Sketch Guided 3D Shape Prototyping and Exploration", + "base_url": null, + "title_page": null, + "github": "Rowl1ng/3Dsketch2shape", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_3D_VR_Sketch_Guided_3D_Shape_Prototyping_and_Exploration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.10830", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Transparent Shape from a Single View Polarization Image", + "base_url": null, + "title_page": null, + "github": "shaomq2187/TransSfP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shao_Transparent_Shape_from_a_Single_View_Polarization_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2204.06331", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-Aligned Reconstruction Priors", + "base_url": null, + "title_page": null, + "github": "X-zhangyang/Get3DHuman", + "web_page": null, + "github_page": "https://x-zhangyang.github.io/2023_Get3DHuman/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiong_Get3DHuman_Lifting_StyleGAN-Human_into_a_3D_Generative_Model_Using_Pixel-Aligned_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.01162", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Zero-1-to-3: Zero-Shot One Image to 3D Object", + "base_url": null, + "title_page": null, + "github": "cvlab-columbia/zero123", + "web_page": "https://zero123.cs.columbia.edu/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/cvlab/zero123-live", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Zero-1-to-3_Zero-shot_One_Image_to_3D_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11328", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "EzcclEHqUBI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "FrozenRecon: Pose-Free 3D Scene Reconstruction with Frozen Depth Models", + "base_url": null, + "title_page": null, + "github": "aim-uofa/FrozenRecon", + "web_page": null, + "github_page": "https://aim-uofa.github.io/FrozenRecon/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_FrozenRecon_Pose-free_3D_Scene_Reconstruction_with_Frozen_Depth_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05733", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstruction", + "base_url": null, + "title_page": null, + "github": "robotic-vision-lab/Learning-Implicitly-From-Spatial-Transformers-Network", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Arshad_LIST_Learning_Implicitly_from_Spatial_Transformers_for_Single-View_3D_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12194", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "gUn5i6FgWWE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets", + "base_url": null, + "title_page": null, + "github": "ttchengab/3DMiner", + "web_page": null, + "github_page": "https://ttchengab.github.io/3dminerOfficial/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_3DMiner_Discovering_Shapes_from_Large-Scale_Unannotated_Image_Datasets_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.19188", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Nonrigid Object Contact Estimation with Regional Unwrapping Transformer", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_Nonrigid_Object_Contact_Estimation_With_Regional_Unwrapping_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14074", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "SHERF: Generalizable Human NeRF from a Single Image", + "base_url": null, + "title_page": null, + "github": "skhu101/SHERF", + "web_page": null, + "github_page": "https://skhu101.github.io/SHERF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_SHERF_Generalizable_Human_NeRF_from_a_Single_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12791", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "xyiv-cW6VcI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Full-Body Articulated Human-Object Interaction", + "base_url": null, + "title_page": null, + "github": "jnnan/chairs", + "web_page": null, + "github_page": "https://jnnan.github.io/project/chairs/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Full-Body_Articulated_Human-Object_Interaction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.10621", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View", + "base_url": null, + "title_page": null, + "github": "SJingjia/PlaneRecTR", + "web_page": null, + "github_page": "https://sjingjia.github.io/PlaneRecTR/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_PlaneRecTR_Unified_Query_Learning_for_3D_Plane_Recovery_from_a_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13756", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "YBB7totHGJg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields", + "base_url": null, + "title_page": null, + "github": "astra-vision/SceneRF", + "web_page": null, + "github_page": "https://astra-vision.github.io/SceneRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_SceneRF_Self-Supervised_Monocular_3D_Scene_Reconstruction_with_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.02501", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation", + "base_url": null, + "title_page": null, + "github": "edz-o/3DNBF", + "web_page": null, + "github_page": "https://3dnbf.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_3D-Aware_Neural_Body_Fitting_for_Occlusion_Robust_3D_Human_Pose_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10123", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "LO80Am0Sb0Y", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Two-in-One Depth: Bridging the Gap between Monocular and Binocular Self-Supervised Depth Estimation", + "base_url": null, + "title_page": null, + "github": "ZM-Zhou/TiO-Depth_pytorch", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Two-in-One_Depth_Bridging_the_Gap_Between_Monocular_and_Binocular_Self-Supervised_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.00933", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "LRRU: Long-Short Range Recurrent Updating Networks for Depth Completion", + "base_url": null, + "title_page": null, + "github": "YufeiWang777/LRRU", + "web_page": null, + "github_page": "https://npucvr.github.io/LRRU/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_LRRU_Long-short_Range_Recurrent_Updating_Networks_for_Depth_Completion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.08956", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "KBU0asJ8J2Y", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "OccFormer: Dual-Path Transformer for Vision-based 3D Semantic Occupancy Prediction", + "base_url": null, + "title_page": null, + "github": "zhangyp15/OccFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_OccFormer_Dual-path_Transformer_for_Vision-based_3D_Semantic_Occupancy_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.05316", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "CHORD: Category-Level Hand-Held Object Reconstruction via Shape Deformation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://kailinli.github.io/CHORD/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_CHORD_Category-level_Hand-held_Object_Reconstruction_via_Shape_Deformation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10574", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space", + "base_url": null, + "title_page": null, + "github": "Jiawei-Yao0812/NDCScene", + "web_page": null, + "github_page": "https://jiawei-yao0812.github.io/NDC-Scene/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yao_NDC-Scene_Boost_Monocular_3D_Semantic_Scene_Completion_in_Normalized_Device_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14616", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "hEpxgMSijUc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "Neural Video Depth Stabilizer", + "base_url": null, + "title_page": null, + "github": "RaymondWang987/NVDS", + "web_page": null, + "github_page": "https://raymondwang987.github.io/NVDS/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Neural_Video_Depth_Stabilizer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08695", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "SNV9F-60xrE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + }, + { + "title": "DiLiGenT-Pi: Photometric Stereo for Planar Surfaces with Rich Details - Benchmark Dataset and Beyond", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://photometricstereo.github.io/diligentpi.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_DiLiGenT-Pi_Photometric_Stereo_for_Planar_Surfaces_with_Rich_Details_-_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://photometricstereo.github.io/imgs/diligentpi/paper.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from a Single Image and Shape-from-X" + } +] \ No newline at end of file diff --git a/json_data/2023/main/3d-from-multi-view-and-sensors.json b/json_data/2023/main/3d-from-multi-view-and-sensors.json new file mode 100644 index 0000000..d447ffe --- /dev/null +++ b/json_data/2023/main/3d-from-multi-view-and-sensors.json @@ -0,0 +1,4673 @@ +[ + { + "title": "Multi-Modal Neural Radiance Field for Monocular Dense SLAM with a Light-Weight ToF Sensor", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://zju3dv.github.io/tof_slam/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Multi-Modal_Neural_Radiance_Field_for_Monocular_Dense_SLAM_with_a_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14383", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "7aJvVG7OLLQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://cy94.github.io/scannetpp/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yeshwanth_ScanNet_A_High-Fidelity_Dataset_of_3D_Indoor_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11417", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "E6P9e2r6M8I", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Translating_Images_to_Road_Network_A_Non-Autoregressive_Sequence-to-Sequence_Approach_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Doppelgangers: Learning to Disambiguate Images of Similar Structures", + "base_url": null, + "title_page": null, + "github": "RuojinCai/Doppelgangers", + "web_page": null, + "github_page": "https://doppelgangers-3d.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_Doppelgangers_Learning_to_Disambiguate_Images_of_Similar_Structures_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02420", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries", + "base_url": null, + "title_page": null, + "github": "Wayne-Mai/EgoLoc", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mai_EgoLoc_Revisiting_3D_Object_Localization_from_Egocentric_Videos_with_Visual_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.06969", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ClothPose: A Real-world Benchmark for Visual Analysis of Garment Pose via an Indirect Recording Solution", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_ClothPose_A_Real-world_Benchmark_for_Visual_Analysis_of_Garment_Pose_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigidity", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_EMR-MSF_Self-Supervised_Recurrent_Monocular_Scene_Flow_Exploiting_Ego-Motion_Rigidity_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting", + "base_url": null, + "title_page": null, + "github": "nexuslrf/ENVIDR", + "web_page": null, + "github_page": "https://nexuslrf.github.io/ENVIDR/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_ENVIDR_Implicit_Differentiable_Renderer_with_Neural_Environment_Lighting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13022", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": "https://drive.google.com/file/d/18kU-IWVxboCG8SCGgrBA5JHC0JIgPCS8/view?t=17s", + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Learning a more Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection", + "base_url": null, + "title_page": null, + "github": "junshengzhou/LevelSetUDF", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Learning_a_More_Continuous_Zero_Level_Set_in_Unsigned_Distance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11441", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts", + "base_url": null, + "title_page": null, + "github": "VITA-Group/GNT-MOVE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cong_Enhancing_NeRF_akin_to_Enhancing_LLMs_Generalizable_NeRF_Transformer_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11793", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "MatrixCity: A Large-Scale City Dataset for City-Scale Neural Rendering and Beyond", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://city-super.github.io/matrixcity/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_MatrixCity_A_Large-scale_City_Dataset_for_City-scale_Neural_Rendering_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://city-super.github.io/matrixcity/img/matrixcity_camera_ready.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras", + "base_url": null, + "title_page": null, + "github": "SysCV/r3d3", + "web_page": "https://www.vis.xyz/pub/r3d3/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Schmied_R3D3_Dense_3D_Reconstruction_of_Dynamic_Scenes_from_Multiple_Cameras_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14713", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "lkU0lDq9HHw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://climatenerf.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_ClimateNeRF_Extreme_Weather_Synthesis_in_Neural_Radiance_Field_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.13226", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Rendering Humans from Object-Occluded Monocular Videos", + "base_url": null, + "title_page": null, + "github": "tiangexiang/OccNeRF", + "web_page": "https://cs.stanford.edu/~xtiange/projects/occnerf/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiang_Rendering_Humans_from_Object-Occluded_Monocular_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04622", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "-LHyNdWGqTM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "AssetField: Assets Mining and Reconfiguration in Ground Feature Plane Representation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://city-super.github.io/assetfield/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiangli_AssetField_Assets_Mining_and_Reconfiguration_in_Ground_Feature_Plane_Representation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13953", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images", + "base_url": null, + "title_page": null, + "github": "megvii-research/PETR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_PETRv2_A_Unified_Framework_for_3D_Perception_from_Multi-Camera_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.01256", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "MIMO-NeRF: Fast Neural Rendering with Multi-Input Multi-Output Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kaneko_MIMO-NeRF_Fast_Neural_Rendering_with_Multi-input_Multi-output_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Adaptive Positional Encoding for Bundle-Adjusting Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_Adaptive_Positional_Encoding_for_Bundle-Adjusting_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-View Reconstruction", + "base_url": null, + "title_page": null, + "github": "19reborn/NeuS2", + "web_page": "https://vcai.mpi-inf.mpg.de/projects/NeuS2/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_NeuS2_Fast_Learning_of_Neural_Implicit_Surfaces_for_Multi-view_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.05231", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition", + "base_url": null, + "title_page": null, + "github": "wqtwjt1996/SUM-L", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Learning_from_Semantic_Alignment_between_Unpaired_Multiviews_for_Egocentric_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11489", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jing_Uncertainty_Guided_Adaptive_Warping_for_Robust_and_Efficient_Stereo_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14071", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Compatibility of Fundamental Matrices for Complete Viewing Graphs", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bratelund_Compatibility_of_Fundamental_Matrices_for_Complete_Viewing_Graphs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10658", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ProtoTransfer: Cross-Modal Prototype Transfer for Point Cloud Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_ProtoTransfer_Cross-Modal_Prototype_Transfer_for_Point_Cloud_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-View 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "mengtan00/SA-BEV", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_SA-BEV_Generating_Semantic-Aware_Birds-Eye-View_Feature_for_Multi-view_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11477", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_GraphAlign_Enhancing_Accurate_Feature_Alignment_by_Graph_matching_for_Multi-Modal_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Tangent Sampson Error: Fast Approximate Two-View Reprojection Error for Central Camera Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Terekhov_Tangent_Sampson_Error_Fast_Approximate_Two-view_Reprojection_Error_for_Central_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "valeoai/WaffleIron", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Puy_Using_a_Waffle_Iron_for_Automotive_Point_Cloud_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.10100", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Fast Globally Optimal Surface Normal Estimation from an Affine Correspondence", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hajder_Fast_Globally_Optimal_Surface_Normal_Estimation_from_an_Affine_Correspondence_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis", + "base_url": null, + "title_page": null, + "github": "syntec-research/Preface", + "web_page": null, + "github_page": "https://syntec-research.github.io/Preface/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Buhler_Preface_A_Data-driven_Volumetric_Prior_for_Few-shot_Ultra_High-resolution_Face_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "oSprm3QTeLc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Canonical Factors for Hybrid Neural Fields", + "base_url": null, + "title_page": null, + "github": "brentyi/tilted", + "web_page": null, + "github_page": "https://brentyi.github.io/tilted/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yi_Canonical_Factors_for_Hybrid_Neural_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.15461", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Center-based Decoupled Point-Cloud Registration for 6D Object Pose Estimation", + "base_url": null, + "title_page": null, + "github": "Jiang-HB/CenterReg", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Center-Based_Decoupled_Point-cloud_Registration_for_6D_Object_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Deep Geometry-Aware Camera Self-Calibration from Video", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hagemann_Deep_Geometry-Aware_Camera_Self-Calibration_from_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "V-FUSE: Volumetric Depth Map Fusion with Long-Range Constraints", + "base_url": null, + "title_page": null, + "github": "nburgdorfer/V-FUSE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Burgdorfer_V-FUSE_Volumetric_Depth_Map_Fusion_with_Long-Range_Constraints_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08715", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Consistent Depth Prediction for Transparent Object Reconstruction from RGB-D Camera", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_Consistent_Depth_Prediction_for_Transparent_Object_Reconstruction_from_RGB-D_Camera_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "FaceCLIPNeRF: Text-Driven 3D Face Manipulation using Deformable Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://faceclipnerf.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hwang_FaceCLIPNeRF_Text-driven_3D_Face_Manipulation_using_Deformable_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11418", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "HollowNeRF: Pruning Hashgrid-based NeRFs with Trainable Collision Mitigation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_HollowNeRF_Pruning_Hashgrid-Based_NeRFs_with_Trainable_Collision_Mitigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10122", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ICE-NeRF: Interactive Color Editing of NeRFs via Decomposition-Aware Weight Optimization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_ICE-NeRF_Interactive_Color_Editing_of_NeRFs_via_Decomposition-Aware_Weight_Optimization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "FULLER: Unified Multi-Modality Multi-Task 3D Perception via Multi-Level Gradient Calibration", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_FULLER_Unified_Multi-modality_Multi-task_3D_Perception_via_Multi-level_Gradient_Calibration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16617", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Neural Fields for Structured Lighting", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shandilya_Neural_Fields_for_Structured_Lighting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "CO-Net: Learning Multiple Point Cloud Tasks at Once with a Cohesive Network", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_CO-Net_Learning_Multiple_Point_Cloud_Tasks_at_Once_with_A_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Pose-Free Neural Radiance Fields via Implicit Pose Regularization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Pose-Free_Neural_Radiance_Fields_via_Implicit_Pose_Regularization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.15049", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering", + "base_url": null, + "title_page": null, + "github": "pansanity666/TransHuman", + "web_page": null, + "github_page": "https://pansanity666.github.io/TransHuman/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pan_TransHuman_A_Transformer-based_Human_Representation_for_Generalizable_Neural_Human_Rendering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12291", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfaces", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://hao-yu-wu.github.io/s-volsdf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_S-VolSDF_Sparse_Multi-View_Stereo_Regularization_of_Neural_Implicit_Surfaces_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17712", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "3_4PeVHWliY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "DPS-Net: Deep Polarimetric Stereo Depth Estimation", + "base_url": null, + "title_page": null, + "github": "Ethereal-Tian/DPS_Net", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tian_DPS-Net_Deep_Polarimetric_Stereo_Depth_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "drilistbox/3DPPE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shu_3DPPE_3D_Point_Positional_Encoding_for_Transformer-based_Multi-Camera_3D_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.14710", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Deformable Neural Radiance Fields using RGB and Event Cameras", + "base_url": null, + "title_page": null, + "github": "qimaqi/DE-NeRF", + "web_page": null, + "github_page": "https://qimaqi.github.io/DE-NeRF.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Deformable_Neural_Radiance_Fields_using_RGB_and_Event_Cameras_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08416", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "K-hINgoSPKU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimation", + "base_url": null, + "title_page": null, + "github": "apple/ml-neilfpp", + "web_page": null, + "github_page": "https://yoyo000.github.io/NeILF_pp/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_NeILF_Inter-Reflectable_Light_Fields_for_Geometry_and_Material_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17147", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Hierarchical Prior Mining for Non-Local Multi-View Stereo", + "base_url": null, + "title_page": null, + "github": "CLinvx/HPM-MVS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ren_Hierarchical_Prior_Mining_for_Non-local_Multi-View_Stereo_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09758", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "exiawsh/StreamPETR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Exploring_Object-Centric_Temporal_Modeling_for_Efficient_Multi-View_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11926", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Re-ReND: Real-Time Rendering of NeRFs Across Devices", + "base_url": null, + "title_page": null, + "github": "sararoma95/Re-ReND", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rojas_Re-ReND_Real-Time_Rendering_of_NeRFs_across_Devices_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08717", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Learning Shape Primitives via Implicit Convexity Regularization", + "base_url": null, + "title_page": null, + "github": "seanywang0408/ICR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Learning_Shape_Primitives_via_Implicit_Convexity_Regularization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Geometry-Guided Feature Learning and Fusion for Indoor Scene Reconstruction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yin_Geometry-guided_Feature_Learning_and_Fusion_for_Indoor_Scene_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment", + "base_url": null, + "title_page": null, + "github": "zhangzw12319/lcps", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_LiDAR-Camera_Panoptic_Segmentation_via_Geometry-Consistent_and_Semantic-Aware_Alignment_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.01686", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ding_PivotNet_Vectorized_Pivot_Learning_for_End-to-end_HD_Map_Construction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16477", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs", + "base_url": null, + "title_page": null, + "github": "qianmingduowan/Sat2Density", + "web_page": null, + "github_page": "https://sat2density.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qian_Sat2Density_Faithful_Density_Learning_from_Satellite-Ground_Image_Pairs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14672", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "mf00PRXUpTU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Mask-Attention-Free Transformer for 3D Instance Segmentation", + "base_url": null, + "title_page": null, + "github": "dvlab-research/Mask-Attention-Free-Transformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lai_Mask-Attention-Free_Transformer_for_3D_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01692", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Scene-Aware Feature Matching", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Scene-Aware_Feature_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09949", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-Balanced Pseudo-Labeling", + "base_url": null, + "title_page": null, + "github": "zhuoxiao-chen/ReDB-DA-3Ddet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Revisiting_Domain-Adaptive_3D_Object_Detection_by_Reliable_Diverse_and_Class-balanced_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07944", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction", + "base_url": null, + "title_page": null, + "github": "youmi-zym/GO-SLAM", + "web_page": null, + "github_page": "https://youmi-zym.github.io/projects/GO-SLAM/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_GO-SLAM_Global_Optimization_for_Consistent_3D_Instant_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02436", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "MbGn94Y4l8Y", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "BANSAC: A dynamic BAyesian Network for adaptive SAmple Consensus", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://pmiraldo.github.io/projects/bansac/bansac.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Piedade_BANSAC_A_Dynamic_BAyesian_Network_for_Adaptive_SAmple_Consensus_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08690", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Theoretical and Numerical Analysis of 3D Reconstruction using Point and Line Incidences", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rydell_Theoretical_and_Numerical_Analysis_of_3D_Reconstruction_Using_Point_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13593", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "RealGraph: A Multiview Dataset for 4D Real-World Context Graph Generation", + "base_url": null, + "title_page": null, + "github": "THU-luvision/RealGraph", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_RealGraph_A_Multiview_Dataset_for_4D_Real-world_Context_Graph_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://rqhuang88.github.io/html/RealGraph.html", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "CL-MVSNet: Unsupervised Multi-View Stereo with Dual-Level Contrastive Learning", + "base_url": null, + "title_page": null, + "github": "KaiqiangXiong/CL-MVSNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiong_CL-MVSNet_Unsupervised_Multi-View_Stereo_with_Dual-Level_Contrastive_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://jianbojiao.com/pdfs/iccv23_clmvs.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Temporal Enhanced Training of Multi-View 3D Object Detector via Historical Object Prediction", + "base_url": null, + "title_page": null, + "github": "Sense-X/HoP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zong_Temporal_Enhanced_Training_of_Multi-view_3D_Object_Detector_via_Historical_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.00967", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Object as Query: Lifting any 2D Object Detector to 3D Detection", + "base_url": null, + "title_page": null, + "github": "tusen-ai/MV2D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Object_as_Query_Lifting_Any_2D_Object_Detector_to_3D_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.02364", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nie_PARTNER_Level_up_the_Polar_Representation_for_LiDAR_3D_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03982", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Not Every Side is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Not_Every_Side_Is_Equal_Localization_Uncertainty_Estimation_for_Semi-Supervised_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "LiveHand: Real-Time and Photorealistic Neural Hand Rendering", + "base_url": null, + "title_page": null, + "github": "amundra15/livehand", + "web_page": "https://vcai.mpi-inf.mpg.de/projects/LiveHand/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mundra_LiveHand_Real-time_and_Photorealistic_Neural_Hand_Rendering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.07672", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "DG-Recon: Depth-Guided Neural 3D Scene Reconstruction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ju_DG-Recon_Depth-Guided_Neural_3D_Scene_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos", + "base_url": null, + "title_page": null, + "github": "MCG-NJU/SparseBEV", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_SparseBEV_High-Performance_Sparse_3D_Object_Detection_from_Multi-Camera_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09244", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Strivec: Sparse Tri-Vector Radiance Fields", + "base_url": null, + "title_page": null, + "github": "Zerg-Overmind/Strivec", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_Strivec_Sparse_Tri-Vector_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13226", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "zQ5Uli553CY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "LDP-Feat: Image Features with Local Differential Privacy", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pittaluga_LDP-Feat_Image_Features_with_Local_Differential_Privacy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11223", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "yichen928/SparseFusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_SparseFusion_Fusing_Multi-Modal_Sparse_Representations_for_Multi-Sensor_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.14340", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Strata-NeRF: Neural Radiance Fields for Stratified Scenes", + "base_url": null, + "title_page": null, + "github": "ankitatiisc/Strata-NeRF", + "web_page": null, + "github_page": "https://ankitatiisc.github.io/Strata-NeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dhiman_Strata-NeRF__Neural_Radiance_Fields_for_Stratified_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10337", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "EzHlqoinwAg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_CRN_Camera_Radar_Net_for_Accurate_Robust_Efficient_3D_Perception_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.00670", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "hMWe2yjzwQ0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "LightGlue: Local Feature Matching at Light Speed", + "base_url": null, + "title_page": null, + "github": "cvg/LightGlue", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lindenberger_LightGlue_Local_Feature_Matching_at_Light_Speed_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.13643", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_ExBluRF_Efficient_Radiance_Fields_for_Extreme_Motion_Blurred_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08957", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Generalized Differentiable RANSAC", + "base_url": null, + "title_page": null, + "github": "weitong8591/differentiable_ransac", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Generalized_Differentiable_RANSAC_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.13185", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-Shaped Depth Cells", + "base_url": null, + "title_page": null, + "github": "DIVE128/DMVSNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_Constraining_Depth_Map_Geometry_for_Multi-View_Stereo_A_Dual-Depth_Approach_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09160", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis", + "base_url": null, + "title_page": null, + "github": "andrewsonga/Total-Recon", + "web_page": null, + "github_page": "https://andrewsonga.github.io/totalrecon/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_Total-Recon_Deformable_Scene_Reconstruction_for_Embodied_View_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.12317", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "IpXw41cDYPU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": "windingwind/seal-3d", + "web_page": null, + "github_page": "https://windingwind.github.io/seal-3d/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Seal-3D_Interactive_Pixel-Level_Editing_for_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15131", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "rm5aJl-9tmE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "PointMBF: A Multi-Scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration", + "base_url": null, + "title_page": null, + "github": "phdymz/PointMBF", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yuan_PointMBF_A_Multi-scale_Bidirectional_Fusion_Network_for_Unsupervised_RGB-D_Point_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04782", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "PARF: Primitive-Aware Radiance Fusion for Indoor Scene Novel View Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://oceanying.github.io/PARF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ying_PARF_Primitive-Aware_Radiance_Fusion_for_Indoor_Scene_Novel_View_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.17190", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Rethinking Point Cloud Registration as Masking and Reconstruction", + "base_url": null, + "title_page": null, + "github": "CGuangyan-BIT/MRA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Rethinking_Point_Cloud_Registration_as_Masking_and_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Ada3D: Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "A-suozhang/ada3d", + "web_page": null, + "github_page": "https://a-suozhang.xyz/ada3d.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Ada3D__Exploiting_the_Spatial_Redundancy_with_Adaptive_Inference_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08209", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "N_llpMqMJbk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement", + "base_url": null, + "title_page": null, + "github": "ashawkey/nerf2mesh", + "web_page": "https://me.kiui.moe/nerf2mesh/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_Delicate_Textured_Mesh_Recovery_from_NeRF_via_Adaptive_Surface_Refinement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.02091", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "CVRecon: Rethinking 3D Geometric Feature Learning for Neural Reconstruction", + "base_url": null, + "title_page": null, + "github": "fengziyue/CVRecon", + "web_page": "https://cvrecon.ziyue.cool/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_CVRecon_Rethinking_3D_Geometric_Feature_Learning_For_Neural_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.14633", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "AVbbx4TBFf8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction", + "base_url": null, + "title_page": null, + "github": "kyleleey/RICO", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_RICO_Regularizing_the_Unobservable_for_Indoor_Compositional_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08605", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_Multiscale_Representation_for_Real-Time_Anti-Aliasing_Neural_Rendering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.10075", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ELFNet: Evidential Local-Global Fusion for Stereo Matching", + "base_url": null, + "title_page": null, + "github": "jimmy19991222/ELFNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lou_ELFNet_Evidential_Local-global_Fusion_for_Stereo_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.00728", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "GaPro: Box-Supervised 3D Point Cloud Instance Segmentation using Gaussian Processes as Pseudo Labelers", + "base_url": null, + "title_page": null, + "github": "VinAIResearch/GaPro", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ngo_GaPro_Box-Supervised_3D_Point_Cloud_Instance_Segmentation_Using_Gaussian_Processes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13251", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Multi-Body Depth and Camera Pose Estimation from Multiple Views", + "base_url": null, + "title_page": null, + "github": "andreadalcin/MultiBodySfM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dal_Cin_Multi-body_Depth_and_Camera_Pose_Estimation_from_Multiple_Views_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Reference-Guided Controllable Inpainting of Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://ashmrz.github.io/reference-guided-3d/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mirzaei_Reference-guided_Controllable_Inpainting_of_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.09677", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "y7Tv3iN6OgY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "AllenXiangX/Retro-FPN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiang_Retro-FPN_Retrospective_Feature_Pyramid_Network_for_Point_Cloud_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09314", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-View 3D Understanding", + "base_url": null, + "title_page": null, + "github": "Sense-X/GeoMIM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_GeoMIM_Towards_Better_3D_Knowledge_Transfer_via_Masked_Image_Modeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11325", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception", + "base_url": null, + "title_page": null, + "github": "JeffWang987/OpenOccupancy", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_OpenOccupancy_A_Large_Scale_Benchmark_for_Surrounding_Semantic_Occupancy_Perception_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.03991", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Surface Normal Clustering for Implicit Representation of Manhattan Scenes", + "base_url": null, + "title_page": null, + "github": "nikola3794/normal-clustering-nerf", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Popovic_Surface_Normal_Clustering_for_Implicit_Representation_of_Manhattan_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.01331", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Spacetime Surface Regularization for Neural Dynamic Scene Reconstruction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Choe_Spacetime_Surface_Regularization_for_Neural_Dynamic_Scene_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "LDL: Line Distance Functions for Panoramic Localization", + "base_url": null, + "title_page": null, + "github": "82magnolia/panoramic-localization", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_LDL_Line_Distance_Functions_for_Panoramic_Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13989", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "cQ5l4rauNY0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Learning Neural Implicit Surfaces with Object-Aware Radiance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Learning_Neural_Implicit_Surfaces_with_Object-Aware_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "MonoNeRF: Learning a Generalizable Dynamic Radiance Field from Monocular Videos", + "base_url": null, + "title_page": null, + "github": "tianfr/MonoNeRF", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tian_MonoNeRF_Learning_a_Generalizable_Dynamic_Radiance_Field_from_Monocular_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.13056", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "A6O4Q3PZZ18", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Neural Radiance Field with LiDAR Maps", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chang_Neural_Radiance_Field_with_LiDAR_maps_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings", + "base_url": null, + "title_page": null, + "github": "xubaixinxbx/3dheads", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Deformable_Model-Driven_Neural_Rendering_for_High-Fidelity_3D_Reconstruction_of_Human_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13855", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "DeLiRa: Self-Supervised Depth, Light, and Radiance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://sites.google.com/view/tri-delira", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guizilini_DeLiRa_Self-Supervised_Depth_Light_and_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02797", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ATT3D: Amortized Text-to-3D Object Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://research.nvidia.com/labs/toronto-ai/ATT3D/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lorraine_ATT3D_Amortized_Text-to-3D_Object_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.07349", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "IWnap49eIwc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ScatterNeRF: Seeing through Fog with Physically-based Inverse Neural Rendering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://light.princeton.edu/publication/scatternerf/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ramazzina_ScatterNeRF_Seeing_Through_Fog_with_Physically-Based_Inverse_Neural_Rendering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.02103", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "CroCo v2: Improved Cross-View Completion Pre-Training for Stereo Matching and Optical Flow", + "base_url": null, + "title_page": null, + "github": "naver/croco", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Weinzaepfel_CroCo_v2_Improved_Cross-view_Completion_Pre-training_for_Stereo_Matching_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.10408", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Guiding Local Feature Matching with Surface Curvature", + "base_url": null, + "title_page": null, + "github": "AaltoVision/surface-curvature-estimator", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Guiding_Local_Feature_Matching_with_Surface_Curvature_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation", + "base_url": null, + "title_page": null, + "github": "Arlo0o/NaviNeRF", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_NaviNeRF_NeRF-based_3D_Representation_Disentanglement_by_Latent_Semantic_Navigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.11342", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Efficient LiDAR Point Cloud Oversegmentation Network", + "base_url": null, + "title_page": null, + "github": "fpthink/SuperLiDAR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hui_Efficient_LiDAR_Point_Cloud_Oversegmentation_Network_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Iterative Superquadric Recomposition of 3D Objects from Multiple Views", + "base_url": null, + "title_page": null, + "github": "ExplainableML/ISCO", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Alaniz_Iterative_Superquadric_Recomposition_of_3D_Objects_from_Multiple_Views_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02102", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "S3IM: Stochastic Structural SIMilarity and its Unreasonable Effectiveness for Neural Fields", + "base_url": null, + "title_page": null, + "github": "Madaoer/S3IM-Neural-Fields", + "web_page": null, + "github_page": "https://madaoer.github.io/s3im_nerf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_S3IM_Stochastic_Structural_SIMilarity_and_Its_Unreasonable_Effectiveness_for_Neural_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07032", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Neural-PBIR Reconstruction of Shape, Material, and Illumination", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://neural-pbir.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Neural-PBIR_Reconstruction_of_Shape_Material_and_Illumination_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.13445", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Predict to Detect: Prediction-Guided 3D Object Detection using Sequential Images", + "base_url": null, + "title_page": null, + "github": "sanmin0312/P2D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Predict_to_Detect_Prediction-guided_3D_Object_Detection_using_Sequential_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.08528", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ObjectFusion: Multi-Modal 3D Object Detection with Object-Centric Fusion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_ObjectFusion_Multi-modal_3D_Object_Detection_with_Object-Centric_Fusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Domain Generalization of 3D Semantic Segmentation in Autonomous Driving", + "base_url": null, + "title_page": null, + "github": "JulesSanchez/3DLabelProp", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sanchez_Domain_Generalization_of_3D_Semantic_Segmentation_in_Autonomous_Driving_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.04245", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "When Epipolar Constraint Meets Non-Local Operators in Multi-View Stereo", + "base_url": null, + "title_page": null, + "github": "TQTQliu/ET-MVSNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_When_Epipolar_Constraint_Meets_Non-Local_Operators_in_Multi-View_Stereo_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.17218", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Hierarchical Point-based Active Learning for Semi-Supervised Point Cloud Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "SmiletoE/HPAL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Hierarchical_Point-based_Active_Learning_for_Semi-supervised_Point_Cloud_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11166", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_UniT3D_A_Unified_Transformer_for_3D_Dense_Captioning_and_Visual_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.00836", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs", + "base_url": null, + "title_page": null, + "github": "ethanweber/nerfbusters", + "web_page": null, + "github_page": "https://ethanweber.me/nerfbusters/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Warburg_Nerfbusters_Removing_Ghostly_Artifacts_from_Casually_Captured_NeRFs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.10532", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Clutter Detection and Removal in 3D Scenes with View-Consistent Inpainting", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://weify627.github.io/clutter/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Clutter_Detection_and_Removal_in_3D_Scenes_with_View-Consistent_Inpainting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.03763", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "2rZtQTFFc-o", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "PG-RCNN: Semantic Surface Point Generation for 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "quotation2520/PG-RCNN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Koo_PG-RCNN_Semantic_Surface_Point_Generation_for_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12637", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Distributed Bundle Adjustment with Block-based Sparse Matrix Compression for Super Large Scale Datasets", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Distributed_Bundle_Adjustment_with_Block-Based_Sparse_Matrix_Compression_for_Super_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08383", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Adaptive Reordering Sampler with Neurally Guided MAGSAC", + "base_url": null, + "title_page": null, + "github": "weitong8591/ars_magsac", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Adaptive_Reordering_Sampler_with_Neurally_Guided_MAGSAC_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2111.14093", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Privacy Preserving Localization via Coordinate Permutations", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pan_Privacy_Preserving_Localization_via_Coordinate_Permutations_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "nkJ3ylpWSdQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://mxuai.github.io/WaveNeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_WaveNeRF_Wavelet-based_Generalizable_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04826", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "TransIFF: An Instance-Level Feature Fusion Framework for Vehicle-Infrastructure Cooperative 3D Detection with Transformers", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_TransIFF_An_Instance-Level_Feature_Fusion_Framework_for_Vehicle-Infrastructure_Cooperative_3D_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Density-Invariant Features for Distant Point Cloud Registration", + "base_url": null, + "title_page": null, + "github": "liuQuan98/GCL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Density-invariant_Features_for_Distant_Point_Cloud_Registration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09788", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D Reconstruction", + "base_url": null, + "title_page": null, + "github": "GaryZhu1996/UMIFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_UMIFormer_Mining_the_Correlations_between_Similar_Tokens_for_Multi-View_3D_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.13987", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Neural LiDAR Fields for Novel View Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://research.nvidia.com/labs/toronto-ai/nfl/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Neural_LiDAR_Fields_for_Novel_View_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.01643", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://w-ted.github.io/publications/udc-nerf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Learning_Unified_Decompositional_and_Compositional_NeRF_for_Editable_Novel_View_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.02840", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Long-Range Grouping Transformer for Multi-View 3D Reconstruction", + "base_url": null, + "title_page": null, + "github": "LiyingCV/Long-Range-Grouping-Transformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Long-Range_Grouping_Transformer_for_Multi-View_3D_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08724", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Cross Modal Transformer: Towards Fast and Robust 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "junjie18/CMT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_Cross_Modal_Transformer_Towards_Fast_and_Robust_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.01283", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "Luoyadan/KECOR-active-3Ddet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_KECOR_Kernel_Coding_Rate_Maximization_for_Active_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07942", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "C2F2NeUS: Cascade Cost Frustum Fusion for High Fidelity and Generalizable Neural Surface Reconstruction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_C2F2NeUS_Cascade_Cost_Frustum_Fusion_for_High_Fidelity_and_Generalizable_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.10003", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "End-to-End 3D Tracking with Decoupled Queries", + "base_url": null, + "title_page": null, + "github": "NVlabs/DQTrack", + "web_page": "https://sites.google.com/view/dqtrack", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_End-to-end_3D_Tracking_with_Decoupled_Queries_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "PHDKu3-iKfo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://zezhoucheng.github.io/lu-nerf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_LU-NeRF_Scene_and_Pose_Estimation_by_Synchronizing_Local_Unposed_NeRFs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.05410", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Clouds", + "base_url": null, + "title_page": null, + "github": "chenchao15/GridPull", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_GridPull_Towards_Scalability_in_Learning_Implicit_Representations_from_3D_Point_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13175", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motion", + "base_url": null, + "title_page": null, + "github": "wengflow/robust-e-nerf", + "web_page": null, + "github_page": "https://wengflow.github.io/robust-e-nerf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Low_Robust_e-NeRF_NeRF_from_Sparse__Noisy_Events_under_Non-Uniform_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08596", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Parameterized Cost Volume for Stereo Matching", + "base_url": null, + "title_page": null, + "github": "jiaxiZeng/Parameterized-Cost-Volume-for-Stereo-Matching", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zeng_Parameterized_Cost_Volume_for_Stereo_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Coordinate Quantized Neural Implicit Representations for Multi-View Reconstruction", + "base_url": null, + "title_page": null, + "github": "MachinePerceptionLab/CQ-NIR", + "web_page": null, + "github_page": "https://machineperceptionlab.github.io/CQ-NIR-page/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Coordinate_Quantized_Neural_Implicit_Representations_for_Multi-view_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11025", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "n0X8cv-bDCo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "ymingxie/parq", + "web_page": null, + "github_page": "https://ymingxie.github.io/parq/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_Pixel-Aligned_Recurrent_Queries_for_Multi-View_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.01401", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "rIHsyEXjTN4", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Optimizing the Placement of Roadside LiDARs for Autonomous Driving", + "base_url": null, + "title_page": null, + "github": "PJLab-ADG/PCSim", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Optimizing_the_Placement_of_Roadside_LiDARs_for_Autonomous_Driving_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.07247", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "ActorsNeRF: Animatable Few-Shot Human Rendering with Generalizable NeRFs", + "base_url": null, + "title_page": null, + "github": "JitengMu/ActorsNeRF", + "web_page": null, + "github_page": "https://jitengmu.github.io/ActorsNeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mu_ActorsNeRF_Animatable_Few-shot_Human_Rendering_with_Generalizable_NeRFs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.14401", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "CH9f31jRNRA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "NeRFrac: Neural Radiance Fields through Refractive Surface", + "base_url": null, + "title_page": null, + "github": "Yifever20002/NeRFrac", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhan_NeRFrac_Neural_Radiance_Fields_through_Refractive_Surface_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "CPCM: Contextual Point Cloud Modeling for Weakly-Supervised Point Cloud Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_CPCM_Contextual_Point_Cloud_Modeling_for_Weakly-supervised_Point_Cloud_Semantic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10316", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "FineRecon: Depth-Aware Feed-Forward Network for Detailed 3D Reconstruction", + "base_url": null, + "title_page": null, + "github": "apple/ml-finerecon", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Stier_FineRecon_Depth-aware_Feed-forward_Network_for_Detailed_3D_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01480", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Point-SLAM: Dense Neural Point Cloud-based SLAM", + "base_url": null, + "title_page": null, + "github": "eriksandstroem/Point-SLAM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sandstrom_Point-SLAM_Dense_Neural_Point_Cloud-based_SLAM_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.04278", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "QFjtL8XTxlU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "You Never Get a Second Chance to Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "nerminsamet/seedal", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Samet_You_Never_Get_a_Second_Chance_To_Make_a_Good_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.11762", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Tetra-NeRF: Representing Neural Radiance Fields using Tetrahedra", + "base_url": null, + "title_page": null, + "github": "jkulhanek/tetra-nerf", + "web_page": "https://jkulhanek.com/tetra-nerf/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kulhanek_Tetra-NeRF_Representing_Neural_Radiance_Fields_Using_Tetrahedra_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.09987", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Active Stereo without Pattern Projector", + "base_url": null, + "title_page": null, + "github": "bartn8/vppstereo", + "web_page": null, + "github_page": "https://vppstereo.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bartolomei_Active_Stereo_Without_Pattern_Projector_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.12315", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video", + "base_url": null, + "title_page": null, + "github": "TencentARC/HOSNeRF", + "web_page": null, + "github_page": "https://showlab.github.io/HOSNeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_HOSNeRF_Dynamic_Human-Object-Scene_Neural_Radiance_Fields_from_a_Single_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.12281", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "wS5k5nNkPi4", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs", + "base_url": null, + "title_page": null, + "github": "manycore-research/PlankAssembly", + "web_page": null, + "github_page": "https://manycore-research.github.io/PlankAssembly/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_PlankAssembly_Robust_3D_Reconstruction_from_Three_Orthographic_Views_with_Learnt_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05744", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Efficient View Synthesis with Neural Radiance Distribution Field", + "base_url": null, + "title_page": null, + "github": "yushuang-wu/NeRDF", + "web_page": null, + "github_page": "https://yushuang-wu.github.io/NeRDF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Efficient_View_Synthesis_with_Neural_Radiance_Distribution_Field_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11130", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Query Refinement Transformer for 3D Instance Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Query_Refinement_Transformer_for_3D_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses", + "base_url": null, + "title_page": null, + "github": "V2AI/EFG", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_TrajectoryFormer_3D_Object_Tracking_Transformer_with_Predictive_Trajectory_Hypotheses_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.05888", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "NerfAcc: Efficient Sampling Accelerates NeRFs", + "base_url": null, + "title_page": null, + "github": "KAIR-BAIR/nerfacc", + "web_page": "https://www.nerfacc.com/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_NerfAcc_Efficient_Sampling_Accelerates_NeRFs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.04966", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "NeTO: Neural Reconstruction of Transparent Objects with Self-Occlusion Aware Refraction-Tracing", + "base_url": null, + "title_page": null, + "github": "xxlong0/NeTO", + "web_page": "https://www.xxlong.site/NeTO/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_NeTONeural_Reconstruction_of_Transparent_Objects_with_Self-Occlusion_Aware_Refraction-Tracing_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11219", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Text2Tex: Text-Driven Texture Synthesis via Diffusion Models", + "base_url": null, + "title_page": null, + "github": "daveredrum/Text2Tex", + "web_page": null, + "github_page": "https://daveredrum.github.io/Text2Tex/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Text2Tex_Text-driven_Texture_Synthesis_via_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11396", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "2ve8tJ9LlcA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Learning Long-Range Information with Dual-Scale Transformers for Indoor Scene Completion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Learning_Long-Range_Information_with_Dual-Scale_Transformers_for_Indoor_Scene_Completion_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "NeRF-MS: Neural Radiance Fields with Multi-Sequence", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://nerf-ms.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_NeRF-MS_Neural_Radiance_Fields_with_Multi-Sequence_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Zip-NeRF: Anti-Aliased Grid-based Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://jonbarron.info/zipnerf/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Barron_Zip-NeRF_Anti-Aliased_Grid-Based_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06706", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "xrrhynRzC8k", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Mixed Neural Voxels for Fast Multi-View Video Synthesis", + "base_url": null, + "title_page": null, + "github": "fengres/mixvoxels", + "web_page": null, + "github_page": "https://fengres.github.io/mixvoxels/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Mixed_Neural_Voxels_for_Fast_Multi-view_Video_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.00190", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips", + "base_url": null, + "title_page": null, + "github": "JudyYe/diffhoi", + "web_page": null, + "github_page": "https://judyye.github.io/diffhoi-www/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_Diffusion-Guided_Reconstruction_of_Everyday_Hand-Object_Interaction_Clips_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05663", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "LERF: Language Embedded Radiance Fields", + "base_url": null, + "title_page": null, + "github": "kerrj/lerf", + "web_page": "https://www.lerf.io/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kerr_LERF_Language_Embedded_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09553", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "7Z2XqH40L08", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions", + "base_url": null, + "title_page": null, + "github": "ayaanzhaque/instruct-nerf2nerf", + "web_page": null, + "github_page": "https://instruct-nerf2nerf.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Haque_Instruct-NeRF2NeRF_Editing_3D_Scenes_with_Instructions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12789", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "D6KWAYU3rCA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "P1AC: Revisiting Absolute Pose from a Single Affine Correspondence", + "base_url": null, + "title_page": null, + "github": "jonathanventura/P1AC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ventura_P1AC_Revisiting_Absolute_Pose_From_a_Single_Affine_Correspondence_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2011.08790", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Neural Haircut: Prior-Guided Strand-based Hair Reconstruction", + "base_url": null, + "title_page": null, + "github": "SamsungLabs/NeuralHaircut", + "web_page": null, + "github_page": "https://samsunglabs.github.io/NeuralHaircut/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sklyarova_Neural_Haircut_Prior-Guided_Strand-Based_Hair_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.05872", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "-gg4GhWKuQs", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": "wbhu/Tri-MipRF", + "web_page": null, + "github_page": "https://wbhu.github.io/projects/Tri-MipRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_Tri-MipRF_Tri-Mip_Representation_for_Efficient_Anti-Aliasing_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11335", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "eBgoul4F148", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "LiDAR-UDA: Self-Ensembling through Time for Unsupervised LiDAR Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "JHLee0513/LiDARUDA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shaban_LiDAR-UDA_Self-ensembling_Through_Time_for_Unsupervised_LiDAR_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.13523", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Tracking Everything Everywhere All at Once", + "base_url": null, + "title_page": null, + "github": "qianqianwang68/omnimotion", + "web_page": null, + "github_page": "https://omnimotion.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Tracking_Everything_Everywhere_All_at_Once_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.05422", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "KHoAG3gA024", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Ego-Humans: An Ego-Centric 3D Multi-Human Benchmark", + "base_url": null, + "title_page": null, + "github": "rawalkhirodkar/egohumans", + "web_page": null, + "github_page": "https://rawalkhirodkar.github.io/egohumans/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Khirodkar_Ego-Humans_An_Ego-Centric_3D_Multi-Human_Benchmark_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.16487", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "TsLxINpWXR8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + }, + { + "title": "Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "tusen-ai/SST", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_Once_Detected_Never_Lost_Surpassing_Human_Performance_in_Offline_LiDAR_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.12315", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D from Multi-View and Sensors" + } +] \ No newline at end of file diff --git a/json_data/2023/main/3d-shape-modeling-and-processing.json b/json_data/2023/main/3d-shape-modeling-and-processing.json new file mode 100644 index 0000000..4fc072f --- /dev/null +++ b/json_data/2023/main/3d-shape-modeling-and-processing.json @@ -0,0 +1,1244 @@ +[ + { + "title": "2D3D-MATR: 2D-3D Matching Transformer for Detection-Free Registration between Images and Point Clouds", + "base_url": null, + "title_page": null, + "github": "minhaolee/2D3DMATR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_2D3D-MATR_2D-3D_Matching_Transformer_for_Detection-Free_Registration_Between_Images_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05667", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Learning Versatile 3D Shape Generation with Improved Auto-Regressive Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_Learning_Versatile_3D_Shape_Generation_with_Improved_Auto-regressive_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14700", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "CaPhy: Capturing Physical Properties for Animatable Human Avatars", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Su_CaPhy_Capturing_Physical_Properties_for_Animatable_Human_Avatars_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05925", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Instance-Aware Dynamic Prompt Tuning for Pre-Trained Point Cloud Models", + "base_url": null, + "title_page": null, + "github": "zyh16143998882/ICCV23-IDPT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zha_Instance-aware_Dynamic_Prompt_Tuning_for_Pre-trained_Point_Cloud_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.07221", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Structure-Aware Surface Reconstruction via Primitive Assembly", + "base_url": null, + "title_page": null, + "github": "xiaowuga/PrimFit", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Structure-Aware_Surface_Reconstruction_via_Primitive_Assembly_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "BaRe-ESA: A Riemannian Framework for Unregistered Human Body Shapes", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hartman_BaRe-ESA_A_Riemannian_Framework_for_Unregistered_Human_Body_Shapes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.13185", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "5bLGru_OOJQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_Speech4Mesh_Speech-Assisted_Monocular_3D_Facial_Reconstruction_for_Speech-Driven_3D_Facial_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Learning Point Cloud Completion without Complete Point Clouds: A Pose-Aware Approach", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Learning_Point_Cloud_Completion_without_Complete_Point_Clouds_A_Pose-Aware_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-Guided Distance Representation", + "base_url": null, + "title_page": null, + "github": "rsy6318/GeoUDF", + "web_page": null, + "github_page": "https://rsy6318.github.io/GeoUDF.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ren_GeoUDF_Surface_Reconstruction_from_3D_Point_Clouds_via_Geometry-guided_Distance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.16762", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "SurfsUP: Learning Fluid Simulation for Novel Surfaces", + "base_url": null, + "title_page": null, + "github": "cvlab-columbia/surfsup", + "web_page": "https://surfsup.cs.columbia.edu/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mani_SurfsUP_Learning_Fluid_Simulation_for_Novel_Surfaces_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06197", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_DeFormer_Integrating_Transformers_with_Deformable_Models_for_3D_Shape_Abstraction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.12594", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_Neural_Deformable_Models_for_3D_Bi-Ventricular_Heart_Shape_Reconstruction_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07693", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "DiffFacto: Controllable Part-based 3D Point Cloud Generation with Cross Diffusion", + "base_url": null, + "title_page": null, + "github": "diffFacto/diffFacto", + "web_page": null, + "github_page": "https://difffacto.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nakayama_DiffFacto_Controllable_Part-Based_3D_Point_Cloud_Generation_with_Cross_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.01921", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "gwlqiJP5izI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Self-Supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects", + "base_url": null, + "title_page": null, + "github": "iscas3dv/deformshape", + "web_page": null, + "github_page": "https://iscas3dv.github.io/deformshape/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Self-supervised_Learning_of_Implicit_Shape_Representation_with_Dense_Correspondence_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12590", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Neural Implicit Surface Evolution", + "base_url": null, + "title_page": null, + "github": "dsilvavinicius/nise", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Novello_Neural_Implicit_Surface_Evolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2201.09636", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "8NqwLkhaRBU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "PointDC: Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-Modal Distillation and Super-Voxel Clustering", + "base_url": null, + "title_page": null, + "github": "SCUT-BIP-Lab/PointDC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_PointDC_Unsupervised_Semantic_Segmentation_of_3D_Point_Clouds_via_Cross-Modal_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion", + "base_url": null, + "title_page": null, + "github": "Rgtemze/HyperDiffusion", + "web_page": "https://ziyaerkoc.com/hyperdiffusion/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Erkoc_HyperDiffusion_Generating_Implicit_Neural_Fields_with_Weight-Space_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17015", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "wjFpsKdo-II", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly", + "base_url": null, + "title_page": null, + "github": "crtie/Leveraging-SE-3-Equivariance-for-Learning-3D-Geometric-Shape-Assembly", + "web_page": null, + "github_page": "https://crtie.github.io/SE-3-part-assembly/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Leveraging_SE3_Equivariance_for_Learning_3D_Geometric_Shape_Assembly_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.06810", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "pEtIAal-xgQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shuai_DPF-Net_Combining_Explicit_Shape_Priors_in_Deformable_Primitive_Field_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13225", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Sample-Adaptive Augmentation for Point Cloud Recognition Against Real-World Corruptions", + "base_url": null, + "title_page": null, + "github": "Roywangj/AdaptPoint", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Sample-adaptive_Augmentation_for_Point_Cloud_Recognition_Against_Real-world_Corruptions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.10431", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "3DHacker: Spectrum-based Decision Boundary Generation for Hard-Label 3D Point Cloud Attack", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tao_3DHacker_Spectrum-based_Decision_Boundary_Generation_for_Hard-label_3D_Point_Cloud_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07546", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds", + "base_url": null, + "title_page": null, + "github": "CuiRuikai/Partial2Complete", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cui_P2C_Self-Supervised_Point_Cloud_Completion_from_Single_Partial_Clouds_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14726", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Towards Multi-Layered 3D Garments Animation", + "base_url": null, + "title_page": null, + "github": "ftbabi/LayersNet_ICCV2023", + "web_page": "https://www.mmlab-ntu.com/project/layersnet/index.html", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shao_Towards_Multi-Layered_3D_Garments_Animation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.10418", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control", + "base_url": null, + "title_page": null, + "github": "songrise/avatarcraft", + "web_page": null, + "github_page": "https://avatar-craft.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_AvatarCraft_Transforming_Text_into_Neural_Human_Avatars_with_Parameterized_Shape_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17606", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "GXPjdN-UF04", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://seokhunchoi.github.io/Blending-NeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_Blending-NeRF_Text-Driven_Localized_Editing_in_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11974", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "vmz9HUlTR7E", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration", + "base_url": null, + "title_page": null, + "github": "Chen-Suyi/SIRA_Pytorch", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_SIRA-PCR_Sim-to-Real_Adaptation_for_3D_Point_Cloud_Registration_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "TJfONIn5p_k", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capability", + "base_url": null, + "title_page": null, + "github": "TrepangCat/3D_Semantic_Subspace_Traverser", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_3D_Semantic_Subspace_Traverser_Empowering_3D_Generative_Model_with_Shape_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14051", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "DMNet: Delaunay Meshing Network for 3D Shape Representation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_DMNet_Delaunay_Meshing_Network_for_3D_Shape_Representation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Attention Discriminant Sampling for Point Clouds", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hong_Attention_Discriminant_Sampling_for_Point_Clouds_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation", + "base_url": null, + "title_page": null, + "github": "KAIST-Geometric-AI-Group/SALAD", + "web_page": null, + "github_page": "https://salad3d.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/KAIST-Geometric-AI-Lab/salad-demo", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Koo_SALAD_Part-Level_Latent_Diffusion_for_3D_Shape_Generation_and_Manipulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12236", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "MAPConNet: Self-Supervised 3D Pose Transfer with Mesh and Point Contrastive Learning", + "base_url": null, + "title_page": null, + "github": "justin941208/MAPConNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_MAPConNet_Self-supervised_3D_Pose_Transfer_with_Mesh_and_Point_Contrastive_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.13819", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition", + "base_url": null, + "title_page": null, + "github": "yxymessi/InvJoint", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yi_Invariant_Training_2D-3D_Joint_Hard_Samples_for_Few-Shot_Point_Cloud_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09694", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "EPiC: Ensemble of Partial Point Clouds for Robust Classification", + "base_url": null, + "title_page": null, + "github": "yossilevii100/EPiC", + "web_page": null, + "github_page": null, + "colab": "https://colab.research.google.com/gist/yossilevii100/ce4cae6c26e7c3d3358c4fb7dda3bec4/untitled5.ipynb", + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Levi_EPiC_Ensemble_of_Partial_Point_Clouds_for_Robust_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11419", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Leveraging Intrinsic Properties for Non-Rigid Garment Alignment", + "base_url": null, + "title_page": null, + "github": "jsnln/IntrinsicGarmAlign", + "web_page": null, + "github_page": "https://jsnln.github.io/iccv2023_intrinsic/index.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Leveraging_Intrinsic_Properties_for_Non-Rigid_Garment_Alignment_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09519", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Spatially and Spectrally Consistent Deep Functional Maps", + "base_url": null, + "title_page": null, + "github": "rqhuang88/Spatially-and-Spectrally-Consistent-Deep-Functional-Maps", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Spatially_and_Spectrally_Consistent_Deep_Functional_Maps_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08871", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "SVDFormer: Complementing Point Cloud via Self-View Augmentation and Self-Structure Dual-Generator", + "base_url": null, + "title_page": null, + "github": "czvvd/SVDFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_SVDFormer_Complementing_Point_Cloud_via_Self-view_Augmentation_and_Self-structure_Dual-generator_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08492", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Batch-based Model Registration for Fast 3D Sherd Reconstruction", + "base_url": null, + "title_page": null, + "github": "jiepengwang/FIRES", + "web_page": null, + "github_page": "https://jiepengwang.github.io/FIRES/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Batch-based_Model_Registration_for_Fast_3D_Sherd_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.06897", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning", + "base_url": null, + "title_page": null, + "github": "SimingYan/IAE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_Implicit_Autoencoder_for_Point-Cloud_Self-Supervised_Representation_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2201.00785", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "E3Sym: Leveraging E(3) Invariance for Unsupervised 3D Planar Reflective Symmetry Detection", + "base_url": null, + "title_page": null, + "github": "renwuli/e3sym", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_E3Sym_Leveraging_E3_Invariance_for_Unsupervised_3D_Planar_Reflective_Symmetry_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Semantify: Simplifying the Control of 3D Morphable Models using CLIP", + "base_url": null, + "title_page": null, + "github": "Omergral/Semantify", + "web_page": null, + "github_page": "https://omergral.github.io/Semantify/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gralnik_Semantify_Simplifying_the_Control_of_3D_Morphable_Models_Using_CLIP_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07415", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "umiDWAPUcL8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "VoroMesh: Learning Watertight Surface Meshes with Voronoi Diagrams", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Maruani_VoroMesh_Learning_Watertight_Surface_Meshes_with_Voronoi_Diagrams_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14616", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "DG3D: Generating High Quality 3D Textured Shapes by Learning to Discriminate Multi-Modal Diffusion-Renderings", + "base_url": null, + "title_page": null, + "github": "seakforzq/DG3D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zuo_DG3D_Generating_High_Quality_3D_Textured_Shapes_by_Learning_to_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers", + "base_url": null, + "title_page": null, + "github": "samb-t/x2ct-vqvae", + "web_page": null, + "github_page": "https://abrilcf.github.io/publications/CodeDiff3D/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Corona-Figueroa_Unaligned_2D_to_3D_Translation_with_Conditional_Vector-Quantized_Code_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14152", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "TZ4nK9qH8h0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Hyperbolic Chamfer Distance for Point Cloud Completion", + "base_url": null, + "title_page": null, + "github": "ark1234/ICCV2023-HyperCD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Hyperbolic_Chamfer_Distance_for_Point_Cloud_Completion_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "SKED: Sketch-Guided Text-based 3D Editing", + "base_url": null, + "title_page": null, + "github": "aryanmikaeili/SKED", + "web_page": null, + "github_page": "https://sked-paper.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mikaeili_SKED_Sketch-guided_Text-based_3D_Editing_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10735", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + }, + { + "title": "Adaptive Spiral Layers for Efficient 3D Representation Learning on Meshes", + "base_url": null, + "title_page": null, + "github": "Fb2221/DFC", + "web_page": null, + "github_page": "https://fb2221.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Babiloni_Adaptive_Spiral_Layers_for_Efficient_3D_Representation_Learning_on_Meshes_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "3D Shape Modeling and Processing" + } +] \ No newline at end of file diff --git a/json_data/2023/main/action-and-event-understanding.json b/json_data/2023/main/action-and-event-understanding.json new file mode 100644 index 0000000..bf57b76 --- /dev/null +++ b/json_data/2023/main/action-and-event-understanding.json @@ -0,0 +1,812 @@ +[ + { + "title": "Weakly-Supervised Action Segmentation and Unseen Error Detection in Anomalous Instructional Videos", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ghoddoosian_Weakly-Supervised_Action_Segmentation_and_Unseen_Error_Detection_in_Anomalous_Instructional_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Diffusion Action Segmentation", + "base_url": null, + "title_page": null, + "github": "Finspire13/DiffAct", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Diffusion_Action_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17959", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Audio-Visual Glance Network for Efficient Video Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nugroho_Audio-Visual_Glance_Network_for_Efficient_Video_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09322", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization", + "base_url": null, + "title_page": null, + "github": "kunnxia/NPL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xia_Learning_from_Noisy_Pseudo_Labels_for_Semi-Supervised_Temporal_Action_Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Video Action Recognition with Attentive Semantic Units", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Video_Action_Recognition_with_Attentive_Semantic_Units_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09756", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Masked Motion Predictors are Strong 3D Action Representation Learners", + "base_url": null, + "title_page": null, + "github": "maoyunyao/MAMP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mao_Masked_Motion_Predictors_are_Strong_3D_Action_Representation_Learners_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07092", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Boosting Positive Segments for Weakly-Supervised Audio-Visual Video Parsing", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rachavarapu_Boosting_Positive_Segments_for_Weakly-Supervised_Audio-Visual_Video_Parsing_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Weakly-Supervised Action Localization by Hierarchically-Structured Latent Attention Modeling", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Weakly-Supervised_Action_Localization_by_Hierarchically-Structured_Latent_Attention_Modeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09946", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Few-Shot Common Action Localization via Cross-Attentional Fusion of Context and Temporal Dynamics", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Few-Shot_Common_Action_Localization_via_Cross-Attentional_Fusion_of_Context_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Interaction-Aware Joint Attention Estimation using People Attributes", + "base_url": null, + "title_page": null, + "github": "chihina/PJAE", + "web_page": "https://www.toyota-ti.ac.jp/Lab/Denshi/iim/ukita/selection/ICCV2023-PJAE.html", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nakatani_Interaction-aware_Joint_Attention_Estimation_Using_People_Attributes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05382", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "FineDance: A Fine-Grained Choreography Dataset for 3D Full Body Dance Generation", + "base_url": null, + "title_page": null, + "github": "li-ronghui/FineDance", + "web_page": null, + "github_page": "https://li-ronghui.github.io/finedance", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_FineDance_A_Fine-grained_Choreography_Dataset_for_3D_Full_Body_Dance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.03741", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "SOAR: Scene-Debiasing Open-Set Action Recognition", + "base_url": null, + "title_page": null, + "github": "yhZhai/SOAR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhai_SOAR_Scene-debiasing_Open-set_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01265", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Leveraging Spatio-Temporal Dependency for Skeleton-based Action Recognition", + "base_url": null, + "title_page": null, + "github": "Jho-Yonsei/STC-Net", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Leveraging_Spatio-Temporal_Dependency_for_Skeleton-Based_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.04761", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Cross-Modal Learning with 3D Deformable Attention for Action Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Cross-Modal_Learning_with_3D_Deformable_Attention_for_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.05638", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Generative Action Description Prompts for Skeleton-based Action Recognition", + "base_url": null, + "title_page": null, + "github": "MartinXM/GAP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiang_Generative_Action_Description_Prompts_for_Skeleton-based_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.05318", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Self-Feedback DETR for Temporal Action Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Self-Feedback_DETR_for_Temporal_Action_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10570", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Skip-Plan_Procedure_Planning_in_Instructional_Videos_via_Condensed_Action_Space_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "The Unreasonable Effectiveness of Large Language-Vision Models for Source-Free Video Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "giaczara/dallv", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zara_The_Unreasonable_Effectiveness_of_Large_Language-Vision_Models_for_Source-Free_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09139", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection", + "base_url": null, + "title_page": null, + "github": "aleflabo/MoCoDAD", + "web_page": "https://www.pinlab.org/mocodad", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Flaborea_Multimodal_Motion_Conditioned_Diffusion_Model_for_Skeleton-based_Video_Anomaly_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07205", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "IuDzVez--9U", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Video Anomaly Detection via Sequentially Learning Multiple Pretext Tasks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_Video_Anomaly_Detection_via_Sequentially_Learning_Multiple_Pretext_Tasks_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "MiniROAD: Minimal RNN Framework for Online Action Detection", + "base_url": null, + "title_page": null, + "github": "jbistanbul/MiniROAD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/An_MiniROAD_Minimal_RNN_Framework_for_Online_Action_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "How much Temporal Long-Term Context is Needed for Action Segmentation?", + "base_url": null, + "title_page": null, + "github": "LTContext/LTContext", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bahrami_How_Much_Temporal_Long-Term_Context_is_Needed_for_Action_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11358", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion", + "base_url": null, + "title_page": null, + "github": "sauradip/DiffusionTAD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nag_DiffTAD_Temporal_Action_Detection_with_Proposal_Denoising_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14863", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos", + "base_url": null, + "title_page": null, + "github": "anshulbshah/STEPs", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shah_STEPs_Self-Supervised_Key_Step_Extraction_and_Localization_from_Unlabeled_Procedural_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.00794", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Efficient Video Action Detection with Token Dropout and Context Refinement", + "base_url": null, + "title_page": null, + "github": "MCG-NJU/EVAD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Efficient_Video_Action_Detection_with_Token_Dropout_and_Context_Refinement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.08451", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_FSAR_Federated_Skeleton-based_Action_Recognition_with_Adaptive_Topology_Structure_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.11046", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Exploring Predicate Visual Context in Detecting of Human-Object Interactions", + "base_url": null, + "title_page": null, + "github": "fredzzhang/pvic", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Exploring_Predicate_Visual_Context_in_Detecting_of_Human-Object_Interactions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06202", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "E2E-LOAD: End-to-End Long-Form Online Action Detection", + "base_url": null, + "title_page": null, + "github": "sqiangcao99/E2E-LOAD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_E2E-LOAD_End-to-End_Long-form_Online_Action_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.07703", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Revisiting Foreground and Background Separation in Weakly-Supervised Temporal Action Localization: A Clustering-based Approach", + "base_url": null, + "title_page": null, + "github": "Qinying-Liu/CASE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Revisiting_Foreground_and_Background_Separation_in_Weakly-supervised_Temporal_Action_Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + }, + { + "title": "Hierarchically Decomposed Graph Convolutional Networks for Skeleton-based Action Recognition", + "base_url": null, + "title_page": null, + "github": "Jho-Yonsei/HD-GCN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Hierarchically_Decomposed_Graph_Convolutional_Networks_for_Skeleton-Based_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.10741", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Action and Event Understanding" + } +] \ No newline at end of file diff --git a/json_data/2023/main/adversarial-attack-and-defense.json b/json_data/2023/main/adversarial-attack-and-defense.json new file mode 100644 index 0000000..1f9f4c9 --- /dev/null +++ b/json_data/2023/main/adversarial-attack-and-defense.json @@ -0,0 +1,1433 @@ +[ + { + "title": "Robust Mixture-of-Expert Training for Convolutional Neural Networks", + "base_url": null, + "title_page": null, + "github": "OPTML-Group/Robust-MoE-CNN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Robust_Mixture-of-Expert_Training_for_Convolutional_Neural_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10110", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Set-Level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-Training Models", + "base_url": null, + "title_page": null, + "github": "Zoky-2020/SGA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Set-level_Guidance_Attack_Boosting_Adversarial_Transferability_of_Vision-Language_Pre-training_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14061", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning", + "base_url": null, + "title_page": null, + "github": "nishadsinghi/CleanCLIP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bansal_CleanCLIP_Mitigating_Data_Poisoning_Attacks_in_Multimodal_Contrastive_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.03323", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "CGBA: Curvature-Aware Geometric Black-Box Attack", + "base_url": null, + "title_page": null, + "github": "Farhamdur/CGBA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Reza_CGBA_Curvature-aware_Geometric_Black-box_Attack_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03163", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Robust Evaluation of Diffusion-based Adversarial Purification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Robust_Evaluation_of_Diffusion-Based_Adversarial_Purification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09051", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Advancing Example Exploitation can Alleviate Critical Challenges in Adversarial Training", + "base_url": null, + "title_page": null, + "github": "geyao1995/advancing-example-exploitation-in-adversarial-training", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ge_Advancing_Example_Exploitation_Can_Alleviate_Critical_Challenges_in_Adversarial_Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "The Victim and the Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data", + "base_url": null, + "title_page": null, + "github": "Zixuan-Zhu/VaB", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_The_Victim_and_The_Beneficiary_Exploiting_a_Poisoned_Model_to_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models", + "base_url": null, + "title_page": null, + "github": "SRI-CSL/TIJO", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sur_TIJO_Trigger_Inversion_with_Joint_Optimization_for_Defending_Multimodal_Backdoored_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03906", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "SAGA: Spectral Adversarial Geometric Attack on 3D Meshes", + "base_url": null, + "title_page": null, + "github": "StolikTomer/SAGA", + "web_page": null, + "github_page": "https://stoliktomer.github.io/SAGA/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Stolik_SAGA_Spectral_Adversarial_Geometric_Attack_on_3D_Meshes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.13775", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples", + "base_url": null, + "title_page": null, + "github": "qiufan319/benchmark_pc_attack", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ji_Benchmarking_and_Analyzing_Robust_Point_Cloud_Recognition_Bag_of_Tricks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16361", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://islab-ai.github.io/active-iccv2023/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Suryanto_ACTIVE_Towards_Highly_Transferable_3D_Physical_Camouflage_for_Universal_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07009", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "m6m90kX0O3w", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Frequency-Aware GAN for Adversarial Manipulation Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Frequency-aware_GAN_for_Adversarial_Manipulation_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations using Image Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Breaking_Temporal_Consistency_Generating_Video_Universal_Adversarial_Perturbations_Using_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_Tracing_the_Origin_of_Adversarial_Attack_for_Forensic_Investigation_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.01218", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Downstream-Agnostic Adversarial Examples", + "base_url": null, + "title_page": null, + "github": "CGCL-codes/AdvEncoder", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Downstream-agnostic_Adversarial_Examples_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12280", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Hiding Visual Information via Obfuscating Adversarial Perturbations", + "base_url": null, + "title_page": null, + "github": "suzhigangssz/AVIH", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Su_Hiding_Visual_Information_via_Obfuscating_Adversarial_Perturbations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2209.15304", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "An Embarrassingly Simple Backdoor Attack on Self-Supervised Learning", + "base_url": null, + "title_page": null, + "github": "meet-cjli/CTRL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_An_Embarrassingly_Simple_Backdoor_Attack_on_Self-supervised_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.07346", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Efficient Decision-based Black-Box Patch Attacks on Video Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Efficient_Decision-based_Black-box_Patch_Attacks_on_Video_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11917", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Suzuki_Adversarial_Finetuning_with_Latent_Representation_Constraint_to_Mitigate_Accuracy-Robustness_Tradeoff_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16454", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Towards Building more Robust Models with Frequency Bias", + "base_url": null, + "title_page": null, + "github": "retsuh-bqw/ICCV23-Towards-Building-More-Robust-Models-with-Frequency-Bias", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bu_Towards_Building_More_Robust_Models_with_Frequency_Bias_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09763", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://sites.google.com/view/cav-sec/sysadv", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Does_Physical_Adversarial_Example_Really_Matter_to_Autonomous_Driving_Towards_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11894", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning", + "base_url": null, + "title_page": null, + "github": "microsoft/robustlearn", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Improving_Generalization_of_Adversarial_Training_via_Robust_Critical_Fine-Tuning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.02533", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation", + "base_url": null, + "title_page": null, + "github": "liuxuannan/Stochastic-Gradient-Aggregation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Enhancing_Generalization_of_Universal_Adversarial_Perturbation_through_Gradient_Aggregation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06015", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Unified Adversarial Patch for Cross-Modal Attacks in the Physical World", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Unified_Adversarial_Patch_for_Cross-Modal_Attacks_in_the_Physical_World_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07859", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World", + "base_url": null, + "title_page": null, + "github": "winterwindwang/RFLA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_RFLA_A_Stealthy_Reflected_Light_Adversarial_Attack_in_the_Physical_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07653", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Enhancing Fine-Tuning based Backdoor Defense with Sharpness-Aware Minimization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Enhancing_Fine-Tuning_Based_Backdoor_Defense_with_Sharpness-Aware_Minimization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.11823", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Conditional 360-Degree Image Synthesis for Immersive Indoor Scene Decoration", + "base_url": null, + "title_page": null, + "github": "kcshum/neural_360_decoration", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shum_Conditional_360-degree_Image_Synthesis_for_Immersive_Indoor_Scene_Decoration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09621", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability", + "base_url": null, + "title_page": null, + "github": "CHENBIN99/AdaEA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_An_Adaptive_Model_Ensemble_Adversarial_Attack_for_Boosting_Adversarial_Transferability_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.02897", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning", + "base_url": null, + "title_page": null, + "github": "ByungKwanLee/Double-Debiased-Adversary", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Mitigating_Adversarial_Vulnerability_through_Causal_Parameter_Estimation_by_Adversarial_Double_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07250", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "LEA2: A Lightweight Ensemble Adversarial Attack via Non-Overlapping Vulnerable Frequency Regions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qian_LEA2_A_Lightweight_Ensemble_Adversarial_Attack_via_Non-overlapping_Vulnerable_Frequency_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective", + "base_url": null, + "title_page": null, + "github": "clustering-effect/SAT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jin_Explaining_Adversarial_Robustness_of_Neural_Networks_from_Clustering_Effect_Perspective_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "VertexSerum: Poisoning Graph Neural Networks for Link Inference", + "base_url": null, + "title_page": null, + "github": "RollinDing/VertexSerum", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ding_VertexSerum_Poisoning_Graph_Neural_Networks_for_Link_Inference_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.01469", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "How to Choose Your Best Allies for a Transferable Attack?", + "base_url": null, + "title_page": null, + "github": "t-maho/transferability_measure_fit", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Maho_How_to_Choose_your_Best_Allies_for_a_Transferable_Attack_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02312", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation", + "base_url": null, + "title_page": null, + "github": "dyoony/SRST_AWR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Enhancing_Adversarial_Robustness_in_Low-Label_Regime_via_Adaptively_Weighted_Regularization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04061", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models", + "base_url": null, + "title_page": null, + "github": "lafeat/advdiffuser", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_AdvDiffuser_Natural_Adversarial_Example_Synthesis_with_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives", + "base_url": null, + "title_page": null, + "github": "infZhou/FnF_Attack", + "web_page": null, + "github_page": "https://infzhou.github.io/FnFAttack/index.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_FF_Attack_Adversarial_Attack_against_Multiple_Object_Trackers_by_Inducing_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis", + "base_url": null, + "title_page": null, + "github": "LukasStruppek/Rickrolling-the-Artist", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Struppek_Rickrolling_the_Artist_Injecting_Backdoors_into_Text_Encoders_for_Text-to-Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.02408", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Hard No-Box Adversarial Attack on Skeleton-based Human Action Recognition with Skeleton-Motion-Informed Gradient", + "base_url": null, + "title_page": null, + "github": "luyg45/HardNoBoxAttack", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Hard_No-Box_Adversarial_Attack_on_Skeleton-Based_Human_Action_Recognition_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05681", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "hvniybZIiqA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Structure Invariant Transformation for Better Adversarial Transferability", + "base_url": null, + "title_page": null, + "github": "xiaosen-wang/SIT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Structure_Invariant_Transformation_for_better_Adversarial_Transferability_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Beating Backdoor Attack at its Own Game", + "base_url": null, + "title_page": null, + "github": "damianliumin/non-adversarial_backdoor", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Beating_Backdoor_Attack_at_Its_Own_Game_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15539", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Transferable Adversarial Attack for Both Vision Transformers and Convolutional Networks via Momentum Integrated Gradients", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Transferable_Adversarial_Attack_for_Both_Vision_Transformers_and_Convolutional_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "REAP: A Large-Scale Realistic Adversarial Patch Benchmark", + "base_url": null, + "title_page": null, + "github": "wagner-group/reap-benchmark", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hingun_REAP_A_Large-Scale_Realistic_Adversarial_Patch_Benchmark_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.05680", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Multi-Metrics Adaptively Identifies Backdoors in Federated Learning", + "base_url": null, + "title_page": null, + "github": "siquanhuang/Multi-metrics_against_backdoors_in_FL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Multi-Metrics_Adaptively_Identifies_Backdoors_in_Federated_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06601", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Backpropagation Path Search on Adversarial Transferability", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Backpropagation_Path_Search_On_Adversarial_Transferability_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07625", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Rapid Network Adaptation: Learning to Adapt Neural Networks using Test-Time Feedback", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://rapid-network-adaptation.epfl.ch/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yeo_Rapid_Network_Adaptation_Learning_to_Adapt_Neural_Networks_Using_Test-Time_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.15762", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "One-Bit Flip is All You Need: When Bit-Flip Attack Meets Model Training", + "base_url": null, + "title_page": null, + "github": "jianshuod/TBA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_One-bit_Flip_is_All_You_Need_When_Bit-flip_Attack_Meets_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07934", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_PolicyCleanse_Backdoor_Detection_and_Mitigation_for_Competitive_Reinforcement_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2202.03609", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Towards Viewpoint-Invariant Visual Recognition via Adversarial Training", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ruan_Towards_Viewpoint-Invariant_Visual_Recognition_via_Adversarial_Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10235", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Fast Adversarial Training with Smooth Convergence", + "base_url": null, + "title_page": null, + "github": "FAT-CS/ConvergeSmooth", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Fast_Adversarial_Training_with_Smooth_Convergence_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12857", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "The Perils of Learning from Unlabeled Data: Backdoor Attacks on Semi-Supervised Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shejwalkar_The_Perils_of_Learning_From_Unlabeled_Data_Backdoor_Attacks_on_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.00453", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Boosting Adversarial Transferability via Gradient Relevance Attack", + "base_url": null, + "title_page": null, + "github": "RYC-98/GRA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Boosting_Adversarial_Transferability_via_Gradient_Relevance_Attack_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "Towards Robust Model Watermark via Reducing Parametric Vulnerability", + "base_url": null, + "title_page": null, + "github": "GuanhaoGan/robust-model-watermarking", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gan_Towards_Robust_Model_Watermark_via_Reducing_Parametric_Vulnerability_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04777", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + }, + { + "title": "TRM-UAP: Enhancing the Transferability of Data-Free Universal Adversarial Perturbation via Truncated Ratio Maximization", + "base_url": null, + "title_page": null, + "github": "RandolphCarter0/TRMUAP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_TRM-UAP_Enhancing_the_Transferability_of_Data-Free_Universal_Adversarial_Perturbation_via_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Adversarial Attack and Defense" + } +] \ No newline at end of file diff --git a/json_data/2023/main/biometrics.json b/json_data/2023/main/biometrics.json new file mode 100644 index 0000000..24b05a8 --- /dev/null +++ b/json_data/2023/main/biometrics.json @@ -0,0 +1,245 @@ +[ + { + "title": "GPGait: Generalized Pose-based Gait Recognition", + "base_url": null, + "title_page": null, + "github": "BNU-IVC/FastPoseGait", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fu_GPGait_Generalized_Pose-based_Gait_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05234", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "NY_MzAxpm94", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Biometrics" + }, + { + "title": "RPG-Palm: Realistic Pseudo-Data Generation for Palmprint Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shen_RPG-Palm_Realistic_Pseudo-data_Generation_for_Palmprint_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14016", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Biometrics" + }, + { + "title": "Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification", + "base_url": null, + "title_page": null, + "github": "liufeng2915/3DInvarReID", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Learning_Clothing_and_Pose_Invariant_3D_Shape_Representation_for_Long-Term_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10658", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Biometrics" + }, + { + "title": "Physics-Augmented Autoencoder for 3D Skeleton-based Gait Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Physics-Augmented_Autoencoder_for_3D_Skeleton-Based_Gait_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Biometrics" + }, + { + "title": "Hierarchical Spatio-Temporal Representation Learning for Gait Recognition", + "base_url": null, + "title_page": null, + "github": "gudaochangsheng/HSTL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Hierarchical_Spatio-Temporal_Representation_Learning_for_Gait_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09856", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Biometrics" + }, + { + "title": "IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Model", + "base_url": null, + "title_page": null, + "github": "fdbtrs/idiff-face", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Boutros_IDiff-Face_Synthetic-based_Face_Recognition_through_Fizzy_Identity-Conditioned_Diffusion_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Biometrics" + }, + { + "title": "Template Inversion Attack against Face Recognition Systems using 3D Face Reconstruction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://www.idiap.ch/paper/gafar/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shahreza_Template_Inversion_Attack_against_Face_Recognition_Systems_using_3D_Face_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Biometrics" + }, + { + "title": "Privacy-Preserving Face Recognition using Random Frequency Components", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mi_Privacy-Preserving_Face_Recognition_Using_Random_Frequency_Components_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10461", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Biometrics" + }, + { + "title": "FLIP: Cross-Domain Face Anti-Spoofing with Language Guidance", + "base_url": null, + "title_page": null, + "github": "koushiksrivats/FLIP", + "web_page": null, + "github_page": "https://koushiksrivats.github.io/FLIP/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Srivatsan_FLIP_Cross-domain_Face_Anti-spoofing_with_Language_Guidance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16649", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Biometrics" + } +] \ No newline at end of file diff --git a/json_data/2023/main/computational-imaging.json b/json_data/2023/main/computational-imaging.json new file mode 100644 index 0000000..d9780c0 --- /dev/null +++ b/json_data/2023/main/computational-imaging.json @@ -0,0 +1,1001 @@ +[ + { + "title": "Tiled Multiplane Images for Practical 3D Photography", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Khan_Tiled_Multiplane_Images_for_Practical_3D_Photography_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14291", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Eulerian Single-Photon Vision", + "base_url": null, + "title_page": null, + "github": "shantanu-gupta/ESPV", + "web_page": "https://wisionlab.com/project/eulerian-single-photon-vision/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gupta_Eulerian_Single-Photon_Vision_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "ProPainter: Improving Propagation and Transformer for Video Inpainting", + "base_url": null, + "title_page": null, + "github": "sczhou/ProPainter", + "web_page": "https://shangchenzhou.com/projects/ProPainter/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_ProPainter_Improving_Propagation_and_Transformer_for_Video_Inpainting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03897", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "92EHfgCO5-Q", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Global Perception based Autoregressive Neural Processes", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tai_Global_Perception_Based_Autoregressive_Neural_Processes_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "DOLCE: A Model-based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_DOLCE_A_Model-Based_Probabilistic_Diffusion_Framework_for_Limited-Angle_CT_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.12340", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://glowgan.mpi-inf.mpg.de/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_GlowGAN_Unsupervised_Learning_of_HDR_Images_from_LDR_Images_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.12352", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Score-based Diffusion Models as Principled Priors for Inverse Imaging", + "base_url": null, + "title_page": null, + "github": "berthyf96/score_prior", + "web_page": "http://imaging.cms.caltech.edu/score_prior/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_Score-Based_Diffusion_Models_as_Principled_Priors_for_Inverse_Imaging_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.11751", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "FkPpQ_GDh4Y", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "NLOS-NeuS: Non-Line-of-Sight Neural Implicit Surface", + "base_url": null, + "title_page": null, + "github": "yfujimura/nlos-neus", + "web_page": null, + "github_page": "https://yfujimura.github.io/nlos-neus/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fujimura_NLOS-NeuS_Non-line-of-sight_Neural_Implicit_Surface_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12280", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "MEFLUT: Unsupervised 1D Lookup Tables for Multi-Exposure Image Fusion", + "base_url": null, + "title_page": null, + "github": "Hedlen/MEFLUT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_MEFLUT_Unsupervised_1D_Lookup_Tables_for_Multi-exposure_Image_Fusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11847", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Temporal-Coded Spiking Neural Networks with Dynamic Firing Threshold: Learning with Event-Driven Backpropagation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Temporal-Coded_Spiking_Neural_Networks_with_Dynamic_Firing_Threshold_Learning_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Enhancing Non-Line-of-Sight Imaging via Learnable Inverse Kernel and Attention Mechanisms", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Enhancing_Non-line-of-sight_Imaging_via_Learnable_Inverse_Kernel_and_Attention_Mechanisms_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Aperture Diffraction for Compact Snapshot Spectral Imaging", + "base_url": null, + "title_page": null, + "github": "Krito-ex/CSST", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lv_Aperture_Diffraction_for_Compact_Snapshot_Spectral_Imaging_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16372", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Content-Aware Local GAN for Photo-Realistic Super-Resolution", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_Content-Aware_Local_GAN_for_Photo-Realistic_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "RED-PSM: Regularization by Denoising of Partially Separable Models for Dynamic Imaging", + "base_url": null, + "title_page": null, + "github": "berkiskender/RED-PSM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Iskender_RED-PSM_Regularization_by_Denoising_of_Partially_Separable_Models_for_Dynamic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.03483", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Self-Supervised Burst Super-Resolution", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bhat_Self-Supervised_Burst_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Coherent Event Guided Low-Light Video Enhancement", + "base_url": null, + "title_page": null, + "github": "sherrycattt/EvLowLight", + "web_page": null, + "github_page": "https://sherrycattt.github.io/EvLowLight/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_Coherent_Event_Guided_Low-Light_Video_Enhancement_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "zLz0GTTXwZg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Panoramas from Photons", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://wisionlab.com/project/panoramas-from-photons/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jungerman_Panoramas_from_Photons_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03811", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Designing Phase Masks for Under-Display Cameras", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Designing_Phase_Masks_for_Under-Display_Cameras_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Xlzl3sQ9W0w", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Deep Optics for Video Snapshot Compressive Imaging", + "base_url": null, + "title_page": null, + "github": "pwangcs/DeepOpticsSCI", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Deep_Optics_for_Video_Snapshot_Compressive_Imaging_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "TiDy-PSFs: Computational Imaging with Time-Averaged Dynamic Point-Spread-Functions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shah_TiDy-PSFs_Computational_Imaging_with_Time-Averaged_Dynamic_Point-Spread-Functions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17583", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Generalized Lightness Adaptation with Channel Selective Normalization", + "base_url": null, + "title_page": null, + "github": "mdyao/CSNorm", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yao_Generalized_Lightness_Adaptation_with_Channel_Selective_Normalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13783", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction", + "base_url": null, + "title_page": null, + "github": "DelinQu/qrsc", + "web_page": null, + "github_page": "https://delinqu.github.io/QRSC/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qu_Towards_Nonlinear-Motion-Aware_and_Occlusion-Robust_Rolling_Shutter_Correction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.18125", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Or-yvKHUrZ0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "FCCNs: Fully Complex-Valued Convolutional Networks using Complex-Valued Color Model and Loss Function", + "base_url": null, + "title_page": null, + "github": "saurabhya/FCCNs", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yadav_FCCNs_Fully_Complex-valued_Convolutional_Networks_using_Complex-valued_Color_Model_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Event Camera Data Pre-Training", + "base_url": null, + "title_page": null, + "github": "Yan98/Event-Camera-Data-Pre-training", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Event_Camera_Data_Pre-training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.01928", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models", + "base_url": null, + "title_page": null, + "github": "hyn2028/tpdm", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Improving_3D_Imaging_with_Pre-Trained_Perpendicular_2D_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08440", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Multiscale Structure Guided Diffusion for Image Deblurring", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ren_Multiscale_Structure_Guided_Diffusion_for_Image_Deblurring_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.01789", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Generalizing Event-based Motion Deblurring in Real-World Scenarios", + "base_url": null, + "title_page": null, + "github": "XiangZ-0/GEM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Generalizing_Event-Based_Motion_Deblurring_in_Real-World_Scenarios_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05932", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": "https://photos.onedrive.com/share/DE821E161E64CE08!2223?cid=DE821E161E64CE08&resId=DE821E161E64CE08!2223&authkey=!ALrfDWQod8KYAkc&ithint=video&e=KGNdnb", + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "On the Robustness of Normalizing Flows for Inverse Problems in Imaging", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hong_On_the_Robustness_of_Normalizing_Flows_for_Inverse_Problems_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.04319", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Learned Compressive Representations for Single-Photon 3D Imaging", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gutierrez-Barragan_Learned_Compressive_Representations_for_Single-Photon_3D_Imaging_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "E71rYGHFEYQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Recovering a Molecule's 3D Dynamics from Liquid-Phase Electron Microscopy Movies", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_Recovering_a_Molecules_3D_Dynamics_from_Liquid-phase_Electron_Microscopy_Movies_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11927", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "7KllsPLHwDc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "NIR-Assisted Video Enhancement via Unpaired 24-Hour Data", + "base_url": null, + "title_page": null, + "github": "MyNiuuu/NVEU", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Niu_NIR-assisted_Video_Enhancement_via_Unpaired_24-hour_Data_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "SpinCam: High-Speed Imaging via a Rotating Point-Spread Function", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chan_SpinCam_High-Speed_Imaging_via_a_Rotating_Point-Spread_Function_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning", + "base_url": null, + "title_page": null, + "github": "KangLiao929/RecRecNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liao_RecRecNet_Rectangling_Rectified_Wide-Angle_Images_by_Thin-Plate_Spline_Model_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.01661", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Affective Image Filter: Reflecting Emotions from Text to Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Weng_Affective_Image_Filter_Reflecting_Emotions_from_Text_to_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Towards General Low-Light Raw Noise Synthesis and Modeling", + "base_url": null, + "title_page": null, + "github": "fengzhang427/LRD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Towards_General_Low-Light_Raw_Noise_Synthesis_and_Modeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16508", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "Unsupervised Video Deraining with an Event Camera", + "base_url": null, + "title_page": null, + "github": "booker-max/Unsupervised-Deraining-with-Event-Camera", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Unsupervised_Video_Deraining_with_An_Event_Camera_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + }, + { + "title": "LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_LoLep_Single-View_View_Synthesis_with_Locally-Learned_Planes_and_Self-Attention_Occlusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12217", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computational Imaging" + } +] \ No newline at end of file diff --git a/json_data/2023/main/computer-vision-theory.json b/json_data/2023/main/computer-vision-theory.json new file mode 100644 index 0000000..84ef1b8 --- /dev/null +++ b/json_data/2023/main/computer-vision-theory.json @@ -0,0 +1,245 @@ +[ + { + "title": "Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation", + "base_url": null, + "title_page": null, + "github": "myukzzz/EICR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Min_Environment-Invariant_Curriculum_Relation_Learning_for_Fine-Grained_Scene_Graph_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03282", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computer Vision Theory" + }, + { + "title": "DCPB: Deformable Convolution based on the Poincaré Ball for Top-View Fisheye Cameras", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_DCPB_Deformable_Convolution_Based_on_the_Poincare_Ball_for_Top-view_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computer Vision Theory" + }, + { + "title": "FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs", + "base_url": null, + "title_page": null, + "github": "yh-pengtu/FemtoDet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tu_FemtoDet_An_Object_Detection_Baseline_for_Energy_Versus_Performance_Tradeoffs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.06719", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computer Vision Theory" + }, + { + "title": "Curvature-Aware Training for Coordinate Networks", + "base_url": null, + "title_page": null, + "github": "sfchng/curvature-aware-INRs", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Saratchandran_Curvature-Aware_Training_for_Coordinate_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.08552", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computer Vision Theory" + }, + { + "title": "Yes, We CANN: Constrained Approximate Nearest Neighbors for Local Feature-based Visual Localization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Aiger_Yes_we_CANN_Constrained_Approximate_Nearest_Neighbors_for_Local_Feature-Based_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.09012", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computer Vision Theory" + }, + { + "title": "Unleashing the Potential of Spiking Neural Networks with Dynamic Confidence", + "base_url": null, + "title_page": null, + "github": "chenlicodebank/Dynamic-Confidence-in-Spiking-Neural-Networks", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Unleashing_the_Potential_of_Spiking_Neural_Networks_with_Dynamic_Confidence_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computer Vision Theory" + }, + { + "title": "Minimal Solutions to Uncalibrated Two-View Geometry with Known Epipoles", + "base_url": null, + "title_page": null, + "github": "g9nkn/uncalibF_epipoles", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nakano_Minimal_Solutions_to_Uncalibrated_Two-view_Geometry_with_Known_Epipoles_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computer Vision Theory" + }, + { + "title": "FBLNet: FeedBack Loop Network for Driver Attention Prediction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_FBLNet_FeedBack_Loop_Network_for_Driver_Attention_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.02096", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computer Vision Theory" + }, + { + "title": "Deep Feature Deblurring Diffusion for Detecting Out-of-Distribution Objects", + "base_url": null, + "title_page": null, + "github": "AmingWu/DFDD-OOD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Deep_Feature_Deblurring_Diffusion_for_Detecting_Out-of-Distribution_Objects_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Computer Vision Theory" + } +] \ No newline at end of file diff --git a/json_data/2023/main/datasets-and-evaluation.json b/json_data/2023/main/datasets-and-evaluation.json new file mode 100644 index 0000000..bcb7c55 --- /dev/null +++ b/json_data/2023/main/datasets-and-evaluation.json @@ -0,0 +1,1433 @@ +[ + { + "title": "A Step Towards Understanding why Classification Helps Regression", + "base_url": null, + "title_page": null, + "github": "SilviaLauraPintea/reg-cls", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pintea_A_step_towards_understanding_why_classification_helps_regression_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10603", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-Centric Rendering", + "base_url": null, + "title_page": null, + "github": "DNA-Rendering/DNA-Rendering", + "web_page": null, + "github_page": "https://dna-rendering.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_DNA-Rendering_A_Diverse_Neural_Actor_Repository_for_High-Fidelity_Human-Centric_Rendering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10173", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "xlhfvxvu7nc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Robo3D: Towards Robust and Reliable 3D Perception against Corruptions", + "base_url": null, + "title_page": null, + "github": "ldkong1205/Robo3D", + "web_page": "https://ldkong.com/Robo3D", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kong_Robo3D_Towards_Robust_and_Reliable_3D_Perception_against_Corruptions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17597", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "kM8n-jMg0qw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Efficient Discovery and Effective Evaluation of Visual Perceptual Similarity: A Benchmark and Beyond", + "base_url": null, + "title_page": null, + "github": "vsd-benchmark/vsd", + "web_page": null, + "github_page": "https://vsd-benchmark.github.io/vsd/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Barkan_Efficient_Discovery_and_Effective_Evaluation_of_Visual_Perceptual_Similarity_A_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14753", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determiners", + "base_url": null, + "title_page": null, + "github": "clarence-lee-sheng/DetermiNet", + "web_page": null, + "github_page": "https://clarence-lee-sheng.github.io/DetermiNet/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_DetermiNet_A_Large-Scale_Diagnostic_Dataset_for_Complex_Visually-Grounded_Referencing_using_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03483", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "rsTrUVL8yzM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Beyond Object Recognition: A New Benchmark Towards Object Concept Learning", + "base_url": null, + "title_page": null, + "github": "silicx/ObjectConceptLearning", + "web_page": "https://mvig-rhos.com/ocl", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Beyond_Object_Recognition_A_New_Benchmark_towards_Object_Concept_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.02710", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "NTyJmTzhfkE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models", + "base_url": null, + "title_page": null, + "github": "eslambakr/HRS_benchmark", + "web_page": null, + "github_page": "https://eslambakr.github.io/hrsbench.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bakr_HRS-Bench_Holistic_Reliable_and_Scalable_Benchmark_for_Text-to-Image_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.05390", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning", + "base_url": null, + "title_page": null, + "github": "dahlian00/SegRCDB", + "web_page": null, + "github_page": "https://dahlian00.github.io/SegRCDBPage/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shinoda_SegRCDB_Semantic_Segmentation_via_Formula-Driven_Supervised_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "5qj9_wQ_fQg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "LoTE-Animal: A Long Time-Span Dataset for Endangered Animal Behavior Understanding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://lote-animal.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_LoTE-Animal_A_Long_Time-span_Dataset_for_Endangered_Animal_Behavior_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Building3D: A Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Clouds", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Building3D_A_Urban-Scale_Dataset_and_Benchmarks_for_Learning_Roof_Structures_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11914", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Lecture Presentations Multimodal Dataset: Towards Understanding Multimodality in Educational Videos", + "base_url": null, + "title_page": null, + "github": "dondongwon/LPMDataset", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Lecture_Presentations_Multimodal_Dataset_Towards_Understanding_Multimodality_in_Educational_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.08080", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models", + "base_url": null, + "title_page": null, + "github": "kdst-team/Probablistic_precision_recall", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_Probabilistic_Precision_and_Recall_Towards_Reliable_Evaluation_of_Generative_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01590", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding", + "base_url": null, + "title_page": null, + "github": "facebookresearch/EgoObjects", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_EgoObjects_A_Large-Scale_Egocentric_Dataset_for_Fine-Grained_Object_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08816", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "CAME: Contrastive Automated Model Evaluation", + "base_url": null, + "title_page": null, + "github": "pengr/Contrastive_AutoEval", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Peng_CAME_Contrastive_Automated_Model_Evaluation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11111", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://www.projectaria.com/datasets/adt/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pan_Aria_Digital_Twin_A_New_Benchmark_Dataset_for_Egocentric_3D_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.06362", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "rrnJQ5NQEiQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives", + "base_url": null, + "title_page": null, + "github": "VQAssessment/DOVER", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Exploring_Video_Quality_Assessment_on_User_Generated_Contents_from_Aesthetic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.04894", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Going Beyond Nouns with Vision & Language Models using Synthetic Data", + "base_url": null, + "title_page": null, + "github": "uvavision/SyViC", + "web_page": null, + "github_page": "https://synthetic-vic.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cascante-Bonilla_Going_Beyond_Nouns_With_Vision__Language_Models_Using_Synthetic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17590", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "dITNWLs35cQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "H3WB: Human3.6M 3D WholeBody Dataset and Benchmark", + "base_url": null, + "title_page": null, + "github": "wholebody3d/wholebody3d", + "web_page": "http://vision.imar.ro/human3.6m/description.php", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_H3WB_Human3.6M_3D_WholeBody_Dataset_and_Benchmark_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.15692", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Zenseact Open Dataset: A Large-Scale and Diverse Multimodal Dataset for Autonomous Driving", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://zod.zenseact.com/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Alibeigi_Zenseact_Open_Dataset_A_Large-Scale_and_Diverse_Multimodal_Dataset_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.02008", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "CAD-Estate: Large-Scale CAD Model Annotation in RGB Videos", + "base_url": null, + "title_page": null, + "github": "google-research/cad-estate", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Maninis_CAD-Estate_Large-scale_CAD_Model_Annotation_in_RGB_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.09011", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Neglected Free Lunch - Learning Image Classifiers using Annotation Byproducts", + "base_url": null, + "title_page": null, + "github": "naver-ai/NeglectedFreeLunch", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_Neglected_Free_Lunch_-_Learning_Image_Classifiers_Using_Annotation_Byproducts_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17595", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "9HEj3Km2TWo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Chaotic World: A Large and Challenging Benchmark for Human Behavior Understanding in Chaotic Events", + "base_url": null, + "title_page": null, + "github": "sutdcv/Chaotic-World", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ong_Chaotic_World_A_Large_and_Challenging_Benchmark_for_Human_Behavior_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": "https://www.researchgate.net/publication/373692522_Chaotic_World_A_Large_and_Challenging_Benchmark_for_Human_Behavior_Understanding_in_Chaotic_Events", + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "MOSE: A New Dataset for Video Object Segmentation in Complex Scenes", + "base_url": null, + "title_page": null, + "github": "henghuiding/MOSE-api", + "web_page": null, + "github_page": "https://henghuiding.github.io/MOSE/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ding_MOSE_A_New_Dataset_for_Video_Object_Segmentation_in_Complex_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.01872", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet", + "base_url": null, + "title_page": null, + "github": "YanNeu/spurious_imagenet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Neuhaus_Spurious_Features_Everywhere_-_Large-Scale_Detection_of_Harmful_Spurious_Features_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.04871", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Chop & Learn: Recognizing and Generating Object-State Compositions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://chopnlearn.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Saini_Chop__Learn_Recognizing_and_Generating_Object-State_Compositions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14339", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Building Bridge Across the Time: Disruption and Restoration of Murals in the Wild", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shao_Building_Bridge_Across_the_Time_Disruption_and_Restoration_of_Murals_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "HoloAssist: An Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://holoassist.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_HoloAssist_an_Egocentric_Human_Interaction_Dataset_for_Interactive_AI_Assistants_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.17024", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://synbody.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_SynBody_Synthetic_Dataset_with_Layered_Human_Models_for_3D_Human_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17368", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?", + "base_url": null, + "title_page": null, + "github": "runjiali-rl/Oxford_HIC", + "web_page": "https://torrvision.com/tvghic/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_OxfordTVG-HIC_Can_Machine_Make_Humorous_Captions_from_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11636", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmark", + "base_url": null, + "title_page": null, + "github": "lojzezust/lars_evaluator", + "web_page": null, + "github_page": "https://lojzezust.github.io/lars-dataset/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zust_LaRS_A_Diverse_Panoptic_Maritime_Obstacle_Detection_Dataset_and_Benchmark_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09618", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "70TACDeZ6kI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Joint Metrics Matter: A Better Standard for Trajectory Forecasting", + "base_url": null, + "title_page": null, + "github": "ericaweng/joint-metrics-matter", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Weng_Joint_Metrics_Matter_A_Better_Standard_for_Trajectory_Forecasting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.06292", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "LPFF: A Portrait Dataset for Face Generators Across Large Poses", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_LPFF_A_Portrait_Dataset_for_Face_Generators_Across_Large_Poses_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14407", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Replay: Multi-Modal Multi-View Acted Videos for Casual Holography", + "base_url": null, + "title_page": null, + "github": "facebookresearch/replay_dataset", + "web_page": null, + "github_page": "https://replay-dataset.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shapovalov_Replay_Multi-modal_Multi-view_Acted_Videos_for_Casual_Holography_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12067", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Human-Centric Scene Understanding for 3D Large-Scale Scenarios", + "base_url": null, + "title_page": null, + "github": "4DVLab/HuCenLife", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Human-centric_Scene_Understanding_for_3D_Large-scale_Scenarios_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14392", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Pre-Training Vision Transformers with Very Limited Synthesized Images", + "base_url": null, + "title_page": null, + "github": "ryoo-nakamura/OFDB", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nakamura_Pre-training_Vision_Transformers_with_Very_Limited_Synthesized_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14710", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "BzgNBwZt1W4", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "FACET: Fairness in Computer Vision Evaluation Benchmark", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://facet.metademolab.com/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gustafson_FACET_Fairness_in_Computer_Vision_Evaluation_Benchmark_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.00035", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "EmoSet: A Large-Scale Visual Emotion Dataset with Rich Attributes", + "base_url": null, + "title_page": null, + "github": "JingyuanYY/EmoSet", + "web_page": "https://vcc.tech/EmoSet", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_EmoSet_A_Large-scale_Visual_Emotion_Dataset_with_Rich_Attributes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07961", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "RenderIH: A Large-Scale Synthetic Dataset for 3D Interacting Hand Pose Estimation", + "base_url": null, + "title_page": null, + "github": "adwardlee/RenderIH", + "web_page": null, + "github_page": "https://adwardlee.github.io/view_renderih/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_RenderIH_A_Large-Scale_Synthetic_Dataset_for_3D_Interacting_Hand_Pose_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.09301", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "eUVE61O-K0s", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering", + "base_url": null, + "title_page": null, + "github": "Yushi-Hu/tifa", + "web_page": null, + "github_page": "https://tifa-benchmark.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_TIFA_Accurate_and_Interpretable_Text-to-Image_Faithfulness_Evaluation_with_Question_Answering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11897", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Exploring the Sim2Real Gap using Digital Twins", + "base_url": null, + "title_page": null, + "github": "SruthiSudhakar/Exploring-the-Sim2Real-Gap-using-Digital-Twins-Dataset", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sudhakar_Exploring_the_Sim2Real_Gap_Using_Digital_Twins_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "ClothesNet: An Information-Rich 3D Garment Model Repository with Simulated Clothes Environment", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://sites.google.com/view/clothesnet", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_ClothesNet_An_Information-Rich_3D_Garment_Model_Repository_with_Simulated_Clothes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09987", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Video State-Changing Object Segmentation", + "base_url": null, + "title_page": null, + "github": "venom12138/VSCOS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Video_State-Changing_Object_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "xkmKjuVTzrk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "PlanarTrack: A Large-Scale Challenging Benchmark for Planar Object Tracking", + "base_url": null, + "title_page": null, + "github": "HengLan/PlanarTrack", + "web_page": null, + "github_page": "https://hengfan2010.github.io/projects/PlanarTrack/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_PlanarTrack_A_Large-scale_Challenging_Benchmark_for_Planar_Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.07625", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception", + "base_url": null, + "title_page": null, + "github": "ydk122024/AIDE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_AIDE_A_Vision-Driven_Multi-View_Multi-Modal_Multi-Tasking_Dataset_for_Assistive_Driving_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13933", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Harvard Glaucoma Detection and Progression: A Multimodal Multitask Dataset and Generalization-Reinforced Semi-Supervised Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://ophai.hms.harvard.edu/datasets/harvard-gdp1000", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_Harvard_Glaucoma_Detection_and_Progression_A_Multimodal_Multitask_Dataset_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13411", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "ARNOLD: A Benchmark for Language-Grounded Task Learning with Continuous States in Realistic 3D Scenes", + "base_url": null, + "title_page": null, + "github": "arnold-benchmark/arnold", + "web_page": null, + "github_page": "https://arnold-benchmark.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gong_ARNOLD_A_Benchmark_for_Language-Grounded_Task_Learning_with_Continuous_States_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.04321", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "w-Cp1PRDWzI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "FishNet: A Large-Scale Dataset and Benchmark for Fish Recognition, Detection, and Functional Trait Prediction", + "base_url": null, + "title_page": null, + "github": "faixan-khan/FishNet", + "web_page": null, + "github_page": "https://fishnet-2023.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Khan_FishNet_A_Large-scale_Dataset_and_Benchmark_for_Fish_Recognition_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Towards Content-based Pixel Retrieval in Revisited Oxford and Paris", + "base_url": null, + "title_page": null, + "github": "anguoyuan/Pixel_retrieval-Segmented_instance_retrieval", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/An_Towards_Content-based_Pixel_Retrieval_in_Revisited_Oxford_and_Paris_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05438", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "A Large-Scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition", + "base_url": null, + "title_page": null, + "github": "AndongDeng/BEAR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Deng_A_Large-scale_Study_of_Spatiotemporal_Representation_Learning_with_a_New_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13505", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "SQAD: Automatic Smartphone Camera Quality Assessment and Benchmarking", + "base_url": null, + "title_page": null, + "github": "aiff22/SQAD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_SQAD_Automatic_Smartphone_Camera_Quality_Assessment_and_Benchmarking_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Revisiting Scene Text Recognition: A Data Perspective", + "base_url": null, + "title_page": null, + "github": "Mountchicken/Union14M", + "web_page": null, + "github_page": "https://union14m.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Revisiting_Scene_Text_Recognition_A_Data_Perspective_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08723", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "Will Large-Scale Generative Models Corrupt Future Datasets?", + "base_url": null, + "title_page": null, + "github": "moskomule/dataset-contamination", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hataya_Will_Large-scale_Generative_Models_Corrupt_Future_Datasets_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.08095", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + }, + { + "title": "360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking", + "base_url": null, + "title_page": null, + "github": "HuajianUP/360VOT", + "web_page": "https://360vot.hkustvgd.com/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_360VOT_A_New_Benchmark_Dataset_for_Omnidirectional_Visual_Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14630", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "PKAVzyGBJMw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Datasets and Evaluation" + } +] \ No newline at end of file diff --git a/json_data/2023/main/deep-learning-architectures-and-techniques.json b/json_data/2023/main/deep-learning-architectures-and-techniques.json new file mode 100644 index 0000000..f894ecf --- /dev/null +++ b/json_data/2023/main/deep-learning-architectures-and-techniques.json @@ -0,0 +1,1217 @@ +[ + { + "title": "Efficient Controllable Multi-Task Architectures", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Aich_Efficient_Controllable_Multi-Task_Architectures_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11744", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "ParCNetV2: Oversized Kernel with Enhanced Attention", + "base_url": null, + "title_page": null, + "github": "XuRuihan/ParCNetV2", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_ParCNetV2_Oversized_Kernel_with_Enhanced_Attention_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.07157", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Unleashing the Power of Gradient Signal-to-Noise Ratio for Zero-Shot NAS", + "base_url": null, + "title_page": null, + "github": "Sunzh1996/Xi-GSNR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Unleashing_the_Power_of_Gradient_Signal-to-Noise_Ratio_for_Zero-Shot_NAS_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "MMST-ViT: Climate Change-Aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer", + "base_url": null, + "title_page": null, + "github": "fudong03/MMST-ViT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_MMST-ViT_Climate_Change-aware_Crop_Yield_Prediction_via_Multi-Modal_Spatial-Temporal_Vision_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://drive.google.com/file/d/1xc_8KkOxVUVsHUiz9Vgv1nqqOa2O_t-2/view", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization", + "base_url": null, + "title_page": null, + "github": "apple/ml-fastvit", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Vasu_FastViT_A_Fast_Hybrid_Vision_Transformer_Using_Structural_Reparameterization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14189", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "IIEU: Rethinking Neural Feature Activation from Decision-Making", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_IIEU_Rethinking_Neural_Feature_Activation_from_Decision-Making_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Scratching Visual Transformer's Back with Uniform Attention", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hyeon-Woo_Scratching_Visual_Transformers_Back_with_Uniform_Attention_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.08457", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference", + "base_url": null, + "title_page": null, + "github": "microsoft/Moonlit", + "web_page": null, + "github_page": "https://github.com/microsoft/Moonlit/tree/main/SpaceEvo", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_SpaceEvo_Hardware-Friendly_Search_Space_Design_for_Efficient_INT8_Inference_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08308", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "ElasticViT: Conflict-Aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices", + "base_url": null, + "title_page": null, + "github": "microsoft/Moonlit", + "web_page": null, + "github_page": "https://github.com/microsoft/Moonlit/tree/main/ElasticViT", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_ElasticViT_Conflict-aware_Supernet_Training_for_Deploying_Fast_Vision_Transformer_on_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09730", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Gramian Attention Heads are Strong yet Efficient Vision Learners", + "base_url": null, + "title_page": null, + "github": "Lab-LVM/imagenet-models", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ryu_Gramian_Attention_Heads_are_Strong_yet_Efficient_Vision_Learners_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.16483", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones", + "base_url": null, + "title_page": null, + "github": "LeapLabTHU/EfficientTrain", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_EfficientTrain_Exploring_Generalized_Curriculum_Learning_for_Training_Visual_Backbones_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.09703", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Ord2Seq: Regarding Ordinal Regression as Label Sequence Prediction", + "base_url": null, + "title_page": null, + "github": "wjh892521292/Ord2Seq", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Ord2Seq_Regarding_Ordinal_Regression_as_Label_Sequence_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09004", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bai_Unified_Data-Free_Compression_Pruning_and_Quantization_without_Fine-Tuning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07209", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "LaPE: Layer-Adaptive Position Embedding for Vision Transformers with Independent Layer Normalization", + "base_url": null, + "title_page": null, + "github": "Ingrid725/LaPE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_LaPE_Layer-adaptive_Position_Embedding_for_Vision_Transformers_with_Independent_Layer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.05262", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Exemplar-Free Continual Transformer with Convolutions", + "base_url": null, + "title_page": null, + "github": "CVIR/contracon", + "web_page": null, + "github_page": "https://cvir.github.io/projects/contracon", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Roy_Exemplar-Free_Continual_Transformer_with_Convolutions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11357", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Building Vision Transformers with Hierarchy Aware Feature Aggregation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Building_Vision_Transformers_with_Hierarchy_Aware_Feature_Aggregation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "ShiftNAS: Improving One-Shot NAS via Probability Shift", + "base_url": null, + "title_page": null, + "github": "bestfleer/ShiftNAS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_ShiftNAS_Improving_One-shot_NAS_via_Probability_Shift_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08300", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "DarSwin: Distortion Aware Radial Swin Transformer", + "base_url": null, + "title_page": null, + "github": "thalesgroup/darswin", + "web_page": null, + "github_page": "https://lvsn.github.io/darswin/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Athwale_DarSwin_Distortion_Aware_Radial_Swin_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.09691", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "jghHwwrvSyk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_ROME_Robustifying_Memory-Efficient_NAS_via_Topology_Disentanglement_and_Gradient_Accumulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2011.11233", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "FDViT: Improve the Hierarchical Architecture of Vision Transformer", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_FDViT_Improve_the_Hierarchical_Architecture_of_Vision_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "FLatten Transformer: Vision Transformer using Focused Linear Attention", + "base_url": null, + "title_page": null, + "github": "LeapLabTHU/FLatten-Transformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_FLatten_Transformer_Vision_Transformer_using_Focused_Linear_Attention_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.00442", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "MixPath: A Unified Approach for One-Shot Neural Architecture Search", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chu_MixPath_A_Unified_Approach_for_One-shot_Neural_Architecture_Search_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2001.05887", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "SSF: Accelerating Training of Spiking Neural Networks with Stabilized Spiking Flow", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_SSF_Accelerating_Training_of_Spiking_Neural_Networks_with_Stabilized_Spiking_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Dynamic Perceiver for Efficient Visual Recognition", + "base_url": null, + "title_page": null, + "github": "LeapLabTHU/Dynamic_Perceiver", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_Dynamic_Perceiver_for_Efficient_Visual_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.11248", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "SG-Former: Self-Guided Transformer with Evolving Token Reallocation", + "base_url": null, + "title_page": null, + "github": "OliverRensu/SG-Former", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ren_SG-Former_Self-guided_Transformer_with_Evolving_Token_Reallocation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12216", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Scale-Aware Modulation Meet Transformer", + "base_url": null, + "title_page": null, + "github": "AFeng-x/SMT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Scale-Aware_Modulation_Meet_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08579", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Learning to Upsample by Learning to Sample", + "base_url": null, + "title_page": null, + "github": "tiny-smart/dysample", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Learning_to_Upsample_by_Learning_to_Sample_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.15085", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "GET: Group Event Transformer for Event-based Vision", + "base_url": null, + "title_page": null, + "github": "Peterande/GET-Group-Event-Transformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Peng_GET_Group_Event_Transformer_for_Event-Based_Vision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.02642", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Adaptive Frequency Filters as Efficient Global Token Mixers", + "base_url": null, + "title_page": null, + "github": "microsoft/TokenMixers", + "web_page": null, + "github_page": "https://github.com/microsoft/TokenMixers/tree/main/Adaptive%20Frequency%20Filters", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Adaptive_Frequency_Filters_As_Efficient_Global_Token_Mixers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14008", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Fcaformer: Forward Cross Attention in Hybrid Vision Transformer", + "base_url": null, + "title_page": null, + "github": "hkzhang-git/FcaFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Fcaformer_Forward_Cross_Attention_in_Hybrid_Vision_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.07198", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation", + "base_url": null, + "title_page": null, + "github": "YaoleiQi/DSCNet", + "web_page": null, + "github_page": "https://yaoleiqi.github.io/pub_homepage/2023_ICCV/index.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qi_Dynamic_Snake_Convolution_Based_on_Topological_Geometric_Constraints_for_Tubular_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08388", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Sentence Attention Blocks for Answer Grounding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Khoshsirat_Sentence_Attention_Blocks_for_Answer_Grounding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11593", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "MST-Compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Vo_MST-compression_Compressing_and_Accelerating_Binary_Neural_Networks_with_Minimum_Spanning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13735", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yun_EGformer_Equirectangular_Geometry-biased_Transformer_for_360_Depth_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.07803", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "SPANet: Frequency-Balancing Token Mixer using Spectral Pooling Aggregation Modulation", + "base_url": null, + "title_page": null, + "github": "DoranLyong/SPANet-official", + "web_page": null, + "github_page": "https://doranlyong.github.io/projects/spanet/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yun_SPANet_Frequency-balancing_Token_Mixer_using_Spectral_Pooling_Aggregation_Modulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11568", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "wEVuA9-jv00", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "ModelGiF: Gradient Fields for Model Functional Distance", + "base_url": null, + "title_page": null, + "github": "zju-vipa/modelgif", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_ModelGiF_Gradient_Fields_for_Model_Functional_Distance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11013", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "ClusT3: Information Invariant Test-Time Training", + "base_url": null, + "title_page": null, + "github": "dosowiechi/ClusT3", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hakim_ClusT3_Information_Invariant_Test-Time_Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.12345", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Cumulative Spatial Knowledge Distillation for Vision Transformers", + "base_url": null, + "title_page": null, + "github": "Zzzzz1/CSKD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Cumulative_Spatial_Knowledge_Distillation_for_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08500", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Luminance-Aware Color Transform for Multiple Exposure Correction", + "base_url": null, + "title_page": null, + "github": "whdgusdl48/LACT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Baek_Luminance-aware_Color_Transform_for_Multiple_Exposure_Correction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks", + "base_url": null, + "title_page": null, + "github": "qymeng94/SLTT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Meng_Towards_Memory-_and_Time-Efficient_Backpropagation_for_Training_Spiking_Neural_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.14311", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Michalkiewicz_Domain_Generalization_Guided_by_Gradient_Signal_to_Noise_Ratio_of_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.07361", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "DOT: A Distillation-Oriented Trainer", + "base_url": null, + "title_page": null, + "github": "megvii-research/mdistiller", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08436", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Extensible and Efficient Proxy for Neural Architecture Search", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Extensible_and_Efficient_Proxy_for_Neural_Architecture_Search_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Learning to Transform for Generalizable Instance-Wise Invariance", + "base_url": null, + "title_page": null, + "github": "sutkarsh/flow_inv", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Singhal_Learning_to_Transform_for_Generalizable_Instance-wise_Invariance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16672", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + }, + { + "title": "Convolutional Networks with Oriented 1D Kernels", + "base_url": null, + "title_page": null, + "github": "princeton-vl/Oriented1D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kirchmeyer_Convolutional_Networks_with_Oriented_1D_Kernels_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.15812", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Deep Learning Architectures and Techniques" + } +] \ No newline at end of file diff --git a/json_data/2023/main/document-analysis-and-understanding.json b/json_data/2023/main/document-analysis-and-understanding.json new file mode 100644 index 0000000..eb70b56 --- /dev/null +++ b/json_data/2023/main/document-analysis-and-understanding.json @@ -0,0 +1,353 @@ +[ + { + "title": "A Benchmark for Chinese-English Scene Text Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "mjq11302010044/Real-CE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_A_Benchmark_for_Chinese-English_Scene_Text_Image_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03262", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "Vision Grid Transformer for Document Layout Analysis", + "base_url": null, + "title_page": null, + "github": "AlibabaResearch/AdvancedLiterateMachinery", + "web_page": null, + "github_page": "https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/VGT", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Da_Vision_Grid_Transformer_for_Document_Layout_Analysis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14978", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "Self-Supervised Character-to-Character Distillation for Text Recognition", + "base_url": null, + "title_page": null, + "github": "TongkunGuan/CCD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guan_Self-Supervised_Character-to-Character_Distillation_for_Text_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.00288", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction", + "base_url": null, + "title_page": null, + "github": "MAEHCM/ICL-D3IE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_ICL-D3IE_In-Context_Learning_with_Diverse_Demonstrations_Updating_for_Document_Information_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05063", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer", + "base_url": null, + "title_page": null, + "github": "mxin262/ESTextSpotter", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_ESTextSpotter_Towards_Better_Scene_Text_Spotting_with_Explicit_Synergy_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10147", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "Few Shot Font Generation via Transferring Similarity Guided Global Style and Quantization Local Style", + "base_url": null, + "title_page": null, + "github": "awei669/VQ-Font", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pan_Few_Shot_Font_Generation_Via_Transferring_Similarity_Guided_Global_Style_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.00827", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "Attention where it Matters: Rethinking Visual Document Understanding with Selective Region Concentration", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Attention_Where_It_Matters_Rethinking_Visual_Document_Understanding_with_Selective_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01131", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "Document Understanding Dataset and Evaluation (DUDE)", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Van_Landeghem_Document_Understanding_Dataset_and_Evaluation_DUDE_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.08455", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition", + "base_url": null, + "title_page": null, + "github": "AlibabaResearch/AdvancedLiterateMachinery", + "web_page": null, + "github_page": "https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/LISTER", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_LISTER_Neighbor_Decoding_for_Length-Insensitive_Scene_Text_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12774", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "MolGrapher: Graph-based Visual Recognition of Chemical Structures", + "base_url": null, + "title_page": null, + "github": "DS4SD/MolGrapher", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Morin_MolGrapher_Graph-based_Visual_Recognition_of_Chemical_Structures_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12234", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "SCOB: Universal Text Understanding via Character-Wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_SCOB_Universal_Text_Understanding_via_Character-wise_Supervised_Contrastive_Learning_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.12382", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "Foreground and Text-Lines Aware Document Image Rectification", + "base_url": null, + "title_page": null, + "github": "xiaomore/Document-Image-Dewarping", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Foreground_and_Text-lines_Aware_Document_Image_Rectification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + }, + { + "title": "DocTr: Document Transformer for Structured Information Extraction in Documents", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liao_DocTr_Document_Transformer_for_Structured_Information_Extraction_in_Documents_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07929", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Document Analysis and Understanding" + } +] \ No newline at end of file diff --git a/json_data/2023/main/efficient-and-scalable-vision.json b/json_data/2023/main/efficient-and-scalable-vision.json new file mode 100644 index 0000000..89595f1 --- /dev/null +++ b/json_data/2023/main/efficient-and-scalable-vision.json @@ -0,0 +1,1703 @@ +[ + { + "title": "AdaNIC: Towards Practical Neural Image Compression via Dynamic Transform Routing", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tao_AdaNIC_Towards_Practical_Neural_Image_Compression_via_Dynamic_Transform_Routing_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Rethinking Vision Transformers for MobileNet Size and Speed", + "base_url": null, + "title_page": null, + "github": "snap-research/EfficientFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Rethinking_Vision_Transformers_for_MobileNet_Size_and_Speed_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.08059", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds", + "base_url": null, + "title_page": null, + "github": "IRMVLab/DELFlow", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Peng_DELFlow_Dense_Efficient_Learning_of_Scene_Flow_for_Large-Scale_Point_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04383", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers", + "base_url": null, + "title_page": null, + "github": "WISION-Lab/eventful-transformer", + "web_page": "https://wisionlab.com/project/eventful-transformers/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dutson_Eventful_Transformers_Leveraging_Temporal_Redundancy_in_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13494", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Inherent Redundancy in Spiking Neural Networks", + "base_url": null, + "title_page": null, + "github": "BICLab/ASA-SNN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yao_Inherent_Redundancy_in_Spiking_Neural_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08227", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Achievement-based Training Progress Balancing for Multi-Task Learning", + "base_url": null, + "title_page": null, + "github": "samsung/Achievement-based-MTL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yun_Achievement-Based_Training_Progress_Balancing_for_Multi-Task_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Prune Spatio-Temporal Tokens by Semantic-Aware Temporal Accumulation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ding_Prune_Spatio-temporal_Tokens_by_Semantic-aware_Temporal_Accumulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04549", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Differentiable Transportation Pruning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Differentiable_Transportation_Pruning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08483", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "XiNet: Efficient Neural Networks for tinyML", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ancilotto_XiNet_Efficient_Neural_Networks_for_tinyML_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers", + "base_url": null, + "title_page": null, + "github": "enyac-group/evol-q", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Frumkin_Jumping_through_Local_Minima_Quantization_in_the_Loss_Landscape_of_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10814", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Colbert_A2Q_Accumulator-Aware_Quantization_with_Guaranteed_Overflow_Avoidance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13504v1", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Workie-Talkie: Accelerating Federated Learning by Overlapping Computing and Communications via Contrastive Regularization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Workie-Talkie_Accelerating_Federated_Learning_by_Overlapping_Computing_and_Communications_via_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://github.com/xinlinli170/noah-research/tree/master/S3-Training", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_DenseShift_Towards_Accurate_and_Efficient_Low-Bit_Power-of-Two_Quantization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.09708", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "L_C6dBkVttg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "PRANC: Pseudo RAndom Networks for Compacting Deep Models", + "base_url": null, + "title_page": null, + "github": "UCDvision/PRANC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nooralinejad_PRANC_Pseudo_RAndom_Networks_for_Compacting_Deep_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.08464", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement", + "base_url": null, + "title_page": null, + "github": "apple/ml-dr", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Faghri_Reinforce_Data_Multiply_Impact_Improved_Model_Accuracy_and_Robustness_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08983", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "A Fast Unified System for 3D Object Detection and Tracking", + "base_url": null, + "title_page": null, + "github": "theitzin/FUS3D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Heitzinger_A_Fast_Unified_System_for_3D_Object_Detection_and_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Estimator Meets Equilibrium Perspective: A Rectified Straight through Estimator for Binary Neural Networks Training", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Estimator_Meets_Equilibrium_Perspective_A_Rectified_Straight_Through_Estimator_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06689", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "I-ViT: Integer-Only Quantization for Efficient Vision Transformer Inference", + "base_url": null, + "title_page": null, + "github": "zkkli/I-ViT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_I-ViT_Integer-only_Quantization_for_Efficient_Vision_Transformer_Inference_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2207.01405", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "EMQ: Evolving Training-Free Proxies for Automated Mixed Precision Quantization", + "base_url": null, + "title_page": null, + "github": "lilujunai/EMQ-series", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_EMQ_Evolving_Training-free_Proxies_for_Automated_Mixed_Precision_Quantization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10554", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Local or Global: Selective Knowledge Assimilation for Federated Learning with Limited Labels", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cho_Local_or_Global_Selective_Knowledge_Assimilation_for_Federated_Learning_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08809", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "DataDAM: Efficient Dataset Distillation with Attention Matching", + "base_url": null, + "title_page": null, + "github": "DataDistillation/DataDAM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sajedi_DataDAM_Efficient_Dataset_Distillation_with_Attention_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.00093", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "SAFE: Machine Unlearning with Shard Graphs", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dukler_SAFE_Machine_Unlearning_With_Shard_Graphs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.13169", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "ResQ: Residual Quantization for Video Perception", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Abati_ResQ_Residual_Quantization_for_Video_Perception_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09511", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Efficient Computation Sharing for Multi-Task Visual Scene Understanding", + "base_url": null, + "title_page": null, + "github": "sarashoouri/EfficientMTL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shoouri_Efficient_Computation_Sharing_for_Multi-Task_Visual_Scene_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09663", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Essential Matrix Estimation using Convex Relaxations in Orthogonal Space", + "base_url": null, + "title_page": null, + "github": "armandok/QME", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Karimian_Essential_Matrix_Estimation_using_Convex_Relaxations_in_Orthogonal_Space_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "TripLe: Revisiting Pretrained Model Reuse and Progressive Learning for Efficient Vision Transformer Scaling and Searching", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fu_TripLe_Revisiting_Pretrained_Model_Reuse_and_Progressive_Learning_for_Efficient_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "DiffRate: Differentiable Compression Rate for Efficient Vision Transformers", + "base_url": null, + "title_page": null, + "github": "OpenGVLab/DiffRate", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_DiffRate__Differentiable_Compression_Rate_for_Efficient_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.17997", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Bridging Cross-Task Protocol Inconsistency for Distillation in Dense Object Detection", + "base_url": null, + "title_page": null, + "github": "TinyTigerPan/BCKD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Bridging_Cross-task_Protocol_Inconsistency_for_Distillation_in_Dense_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14286", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels", + "base_url": null, + "title_page": null, + "github": "yzd-v/cls_KD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_From_Knowledge_Distillation_to_Self-Knowledge_Distillation_A_Unified_Approach_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13005", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Efficient 3D Semantic Segmentation with Superpoint Transformer", + "base_url": null, + "title_page": null, + "github": "drprojects/superpoint_transformer", + "web_page": null, + "github_page": "https://drprojects.github.io/superpoint-transformer", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Robert_Efficient_3D_Semantic_Segmentation_with_Superpoint_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.08045", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Dataset Quantization", + "base_url": null, + "title_page": null, + "github": "magic-research/Dataset_Quantization", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Dataset_Quantization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10524", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy", + "base_url": null, + "title_page": null, + "github": "JieShibo/PETL-ViT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jie_Revisiting_the_Parameter_Efficiency_of_Adapters_from_the_Perspective_of_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16867", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers", + "base_url": null, + "title_page": null, + "github": "zkkli/RepQ-ViT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_RepQ-ViT_Scale_Reparameterization_for_Post-Training_Quantization_of_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.08254", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Semantically Structured Image Compression via Irregular Group-based Decoupling", + "base_url": null, + "title_page": null, + "github": "IRMVLab/DELFlow", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_Semantically_Structured_Image_Compression_via_Irregular_Group-Based_Decoupling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.02586", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "SeiT: Storage-Efficient Vision Training with Tokens using 1% of Pixel Storage", + "base_url": null, + "title_page": null, + "github": "naver-ai/seit", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_SeiT_Storage-Efficient_Vision_Training_with_Tokens_Using_1_of_Pixel_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11114", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "SMMix: Self-Motivated Image Mixing for Vision Transformers", + "base_url": null, + "title_page": null, + "github": "ChenMnZ/SMMix", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_SMMix_Self-Motivated_Image_Mixing_for_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.12977", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Multi-Label Knowledge Distillation", + "base_url": null, + "title_page": null, + "github": "penghui-yang/L2D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Multi-Label_Knowledge_Distillation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06453", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "UGC: Unified GAN Compression for Efficient Image-to-Image Translation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ren_UGC_Unified_GAN_Compression_for_Efficient_Image-to-Image_Translation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.09310", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos with Spherical Buffers and Padded Convolutions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Parger_MotionDeltaCNN_Sparse_CNN_Inference_of_Frame_Differences_in_Moving_Camera_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.09887", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction", + "base_url": null, + "title_page": null, + "github": "mit-han-lab/efficientvit", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_EfficientViT_Lightweight_Multi-Scale_Attention_for_High-Resolution_Dense_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2205.14756", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "DREAM: Efficient Dataset Distillation by Representative Matching", + "base_url": null, + "title_page": null, + "github": "lyq312318224/DREAM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_DREAM_Efficient_Dataset_Distillation_by_Representative_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.14416", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "INSTA-BNN: Binary Neural Network with INSTAnce-Aware Threshold", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_INSTA-BNN_Binary_Neural_Network_with_INSTAnce-aware_Threshold_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2204.07439", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Deep Incubation: Training Large Models by Divide-and-Conquering", + "base_url": null, + "title_page": null, + "github": "LeapLabTHU/Deep-Incubation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ni_Deep_Incubation_Training_Large_Models_by_Divide-and-Conquering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.04129", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://github.com/google-research/google-research/tree/master/moe_mtl", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_AdaMV-MoE_Adaptive_Multi-Task_Vision_Mixture-of-Experts_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Overcoming Forgetting Catastrophe in Quantization-Aware Training", + "base_url": null, + "title_page": null, + "github": "tinganchen/LifeQuant", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Overcoming_Forgetting_Catastrophe_in_Quantization-Aware_Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Window-based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are more Efficient than Single Models", + "base_url": null, + "title_page": null, + "github": "Guoxoug/window-early-exit", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xia_Window-Based_Early-Exit_Cascades_for_Uncertainty_Estimation_When_Deep_Ensembles_are_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08010", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "ORC: Network Group-based Knowledge Distillation using Online Role Change", + "base_url": null, + "title_page": null, + "github": "choijunyong/ORCKD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Choi_ORC_Network_Group-based_Knowledge_Distillation_using_Online_Role_Change_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.01186", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_RMP-Loss_Regularizing_Membrane_Potential_Distribution_for_Spiking_Neural_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06787", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Structural Alignment for Network Pruning through Partial Regularization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_Structural_Alignment_for_Network_Pruning_through_Partial_Regularization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Automated Knowledge Distillation via Monte Carlo Tree Search", + "base_url": null, + "title_page": null, + "github": "lilujunai/Auto-KD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Automated_Knowledge_Distillation_via_Monte_Carlo_Tree_Search_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "SwiftFormer: Efficient Additive Attention for Transformer-based Real-Time Mobile Vision Applications", + "base_url": null, + "title_page": null, + "github": "Amshaker/SwiftFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shaker_SwiftFormer_Efficient_Additive_Attention_for_Transformer-based_Real-time_Mobile_Vision_Applications_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15446", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Causal-DFQ: Causality Guided Data-Free Network Quantization", + "base_url": null, + "title_page": null, + "github": "42Shawn/Causal-DFQ", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shang_Causal-DFQ_Causality_Guided_Data-Free_Network_Quantization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.13682", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks", + "base_url": null, + "title_page": null, + "github": "Akimoto-Cris/RD_PRUNE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Efficient_Joint_Optimization_of_Layer-Adaptive_Weight_Pruning_in_Deep_Neural_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10438", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle", + "base_url": null, + "title_page": null, + "github": "sunggo/APIB", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Automatic_Network_Pruning_via_Hilbert-Schmidt_Independence_Criterion_Lasso_under_Information_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Distribution Shift Matters for Knowledge Distillation with Webly Collected Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_Distribution_Shift_Matters_for_Knowledge_Distillation_with_Webly_Collected_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11469", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "FastRecon: Few-Shot Industrial Anomaly Detection via Fast Feature Reconstruction", + "base_url": null, + "title_page": null, + "github": "FzJun26th/FastRecon", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_FastRecon_Few-shot_Industrial_Anomaly_Detection_via_Fast_Feature_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "E2VPT: An Effective and Efficient Approach for Visual Prompt Tuning", + "base_url": null, + "title_page": null, + "github": "ChengHan111/E2VPT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_E2VPT_An_Effective_and_Efficient_Approach_for_Visual_Prompt_Tuning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13770", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation", + "base_url": null, + "title_page": null, + "github": "kkakkkka/ETRIS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Bridging_Vision_and_Language_Encoders_Parameter-Efficient_Tuning_for_Referring_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11545", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "SHACIRA: Scalable HAsh-Grid Compression for Implicit Neural Representations", + "base_url": null, + "title_page": null, + "github": "Sharath-girish/Shacira", + "web_page": null, + "github_page": "https://shacira.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Girish_SHACIRA_Scalable_HAsh-grid_Compression_for_Implicit_Neural_Representations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.15848", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "zRr9ZqlmSzY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Efficient Deep Space Filling Curve", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Efficient_Deep_Space_Filling_Curve_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Q-Diffusion: Quantizing Diffusion Models", + "base_url": null, + "title_page": null, + "github": "Xiuyu-Li/q-diffusion", + "web_page": "https://xiuyuli.com/qdiffusion/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Q-Diffusion_Quantizing_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.04304", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Lossy and Lossless (L2) Post-Training Model Size Compression", + "base_url": null, + "title_page": null, + "github": "ModelTC/L2_Compression", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_Lossy_and_Lossless_L2_Post-training_Model_Size_Compression_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04269", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + }, + { + "title": "Robustifying Token Attention for Vision Transformers", + "base_url": null, + "title_page": null, + "github": "guoyongcs/TAPADL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Robustifying_Token_Attention_for_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11126", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Efficient and Scalable Vision" + } +] \ No newline at end of file diff --git a/json_data/2023/main/embodied-vision-active-agents-simulation.json b/json_data/2023/main/embodied-vision-active-agents-simulation.json new file mode 100644 index 0000000..30a7729 --- /dev/null +++ b/json_data/2023/main/embodied-vision-active-agents-simulation.json @@ -0,0 +1,407 @@ +[ + { + "title": "Skill Transformer: A Monolithic Policy for Mobile Manipulation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Skill_Transformer_A_Monolithic_Policy_for_Mobile_Manipulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09873", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "ENTL: Embodied Navigation Trajectory Learner", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kotar_ENTL_Embodied_Navigation_Trajectory_Learner_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02639", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation", + "base_url": null, + "title_page": null, + "github": "hanqingwangai/Dreamwalker", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_DREAMWALKER_Mental_Planning_for_Continuous_Vision-Language_Navigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07498", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Scene Graph Contrastive Learning for Embodied Navigation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Singh_Scene_Graph_Contrastive_Learning_for_Embodied_Navigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Perpetual Humanoid Control for Real-Time Simulated Avatars", + "base_url": null, + "title_page": null, + "github": "DelinQu/qrsc", + "web_page": null, + "github_page": "https://zhengyiluo.github.io/PHC/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_Perpetual_Humanoid_Control_for_Real-time_Simulated_Avatars_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.06456", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "zS6Y00EW37A", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Grounding 3D Object Affordance from 2D Interactions in Images", + "base_url": null, + "title_page": null, + "github": "yyvhang/IAGNet", + "web_page": null, + "github_page": "https://yyvhang.github.io/publications/IAG/index.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Grounding_3D_Object_Affordance_from_2D_Interactions_in_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10437", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "GfCPUM1nAHI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Navigating to Objects Specified by Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://jacobkrantz.github.io/modular_iin", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Krantz_Navigating_to_Objects_Specified_by_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01192", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "273jjBvu48s", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "PEANUT: Predicting and Navigating to Unseen Targets", + "base_url": null, + "title_page": null, + "github": "ajzhai/PEANUT", + "web_page": null, + "github_page": "https://ajzhai.github.io/PEANUT/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhai_PEANUT_Predicting_and_Navigating_to_Unseen_Targets_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.02497", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Context-Aware_Planning_and_Environment-Aware_Memory_for_Instruction_Following_Embodied_Agents_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07241", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Learning Foresightful Dense Visual Affordance for Deformable Object Manipulation", + "base_url": null, + "title_page": null, + "github": "TritiumR/DeformableAffordance", + "web_page": null, + "github_page": "https://hyperplane-lab.github.io/DeformableAffordance/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Learning_Foresightful_Dense_Visual_Affordance_for_Deformable_Object_Manipulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11057", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "aYneBzwhOGs", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Exploiting Proximity-Aware Tasks for Embodied Social Navigation", + "base_url": null, + "title_page": null, + "github": "EnricoCancelli/ProximitySocialNav", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cancelli_Exploiting_Proximity-Aware_Tasks_for_Embodied_Social_Navigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.00767", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Bird's-Eye-View Scene Graph for Vision-Language Navigation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Birds-Eye-View_Scene_Graph_for_Vision-Language_Navigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04758", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Active Neural Mapping", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_Active_Neural_Mapping_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16246", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "psPvanfh7SA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation", + "base_url": null, + "title_page": null, + "github": "chenjinyubuaa/ORAN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Omnidirectional_Information_Gathering_for_Knowledge_Transfer-Based_Audio-Visual_Navigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10306", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + }, + { + "title": "Multi-Object Navigation with Dynamically Learned Neural Implicit Representations", + "base_url": null, + "title_page": null, + "github": "PierreMarza/dynamic_implicit_representations", + "web_page": null, + "github_page": "https://pierremarza.github.io/projects/dynamic_implicit_representations/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Marza_Multi-Object_Navigation_with_Dynamically_Learned_Neural_Implicit_Representations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.05129", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "r_F9M80GPUI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Embodied Vision: Active Agents, Simulation" + } +] \ No newline at end of file diff --git a/json_data/2023/main/explainable-ai-for-cv.json b/json_data/2023/main/explainable-ai-for-cv.json new file mode 100644 index 0000000..193ec39 --- /dev/null +++ b/json_data/2023/main/explainable-ai-for-cv.json @@ -0,0 +1,569 @@ +[ + { + "title": "Towards Improved Input Masking for Convolutional Neural Networks", + "base_url": null, + "title_page": null, + "github": "SriramB-98/layer_masking", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Balasubramanian_Towards_Improved_Input_Masking_for_Convolutional_Neural_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.14646", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "PDiscoNet: Semantically Consistent Part Discovery for Fine-Grained Recognition", + "base_url": null, + "title_page": null, + "github": "robertdvdk/part_detection", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/van_der_Klis_PDiscoNet_Semantically_consistent_part_discovery_for_fine-grained_recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": "https://hal.inrae.fr/hal-04183747", + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Corrupting Neuron Explanations of Deep Visual Features", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Srivastava_Corrupting_Neuron_Explanations_of_Deep_Visual_Features_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.16332", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "ICICLE: Interpretable Class Incremental Continual Learning", + "base_url": null, + "title_page": null, + "github": "gmum/ICICLE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rymarczyk_ICICLE_Interpretable_Class_Incremental_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.07811", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models", + "base_url": null, + "title_page": null, + "github": "ExplainableML/ProbVLM", + "web_page": "https://www.eml-unitue.de/publication/ProbVLM", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Upadhyay_ProbVLM_Probabilistic_Adapter_for_Frozen_Vison-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.00398", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Out-of-Distribution Detection for Monocular Depth Estimation", + "base_url": null, + "title_page": null, + "github": "jhornauer/mde_ood", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hornauer_Out-of-Distribution_Detection_for_Monocular_Depth_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06072", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Studying how to Efficiently and Effectively Guide Models with Explanations", + "base_url": null, + "title_page": null, + "github": "sukrutrao/Model-Guidance", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rao_Studying_How_to_Efficiently_and_Effectively_Guide_Models_with_Explanations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11932", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "g9tKVe3fEcQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Rosetta Neurons: Mining the Common Units in a Model Zoo", + "base_url": null, + "title_page": null, + "github": "yossigandelsman/rosetta_neurons", + "web_page": null, + "github_page": "https://yossigandelsman.github.io/rosetta_neurons/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dravid_Rosetta_Neurons_Mining_the_Common_Units_in_a_Model_Zoo_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.09346", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Prototype-based Dataset Comparison", + "base_url": null, + "title_page": null, + "github": "Nanne/ProtoSim", + "web_page": null, + "github_page": "https://nanne.github.io/ProtoSim/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/van_Noord_Protoype-based_Dataset_Comparison_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02401", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Learning to Identify Critical States for Reinforcement Learning from Videos", + "base_url": null, + "title_page": null, + "github": "AI-Initiative-KAUST/VideoRLCS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Learning_to_Identify_Critical_States_for_Reinforcement_Learning_from_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07795", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Leaping Into Memories: Space-Time Deep Feature Synthesis", + "base_url": null, + "title_page": null, + "github": "alexandrosstergiou/Leaping-Into-Memories", + "web_page": null, + "github_page": "https://alexandrosstergiou.github.io/project_pages/LEAPS/index.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Stergiou_Leaping_Into_Memories_Space-Time_Deep_Feature_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09941", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "MAGI: Multi-Annotated Explanation-Guided Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_MAGI_Multi-Annotated_Explanation-Guided_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability", + "base_url": null, + "title_page": null, + "github": "havelhuang/Eval_XAI_Robustness", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_SAFARI_Versatile_and_Efficient_Evaluations_for_Robustness_of_Interpretability_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.09418", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Do DALL-E and Flamingo Understand Each Other?", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://dalleflamingo.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Do_DALL-E_and_Flamingo_Understand_Each_Other_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.12249", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks", + "base_url": null, + "title_page": null, + "github": "hqhQAQ/EvalProtoPNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Evaluation_and_Improvement_of_Interpretability_for_Self-Explainable_Part-Prototype_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.05946", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope", + "base_url": null, + "title_page": null, + "github": "buyeah1109/MoreauGrad", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_MoreauGrad_Sparse_and_Robust_Interpretation_of_Neural_Networks_via_Moreau_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.05294", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yao_Towards_Understanding_the_Generalization_of_Deepfake_Detectors_from_a_Game-Theoretical_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Counterfactual-based_Saliency_Map_Towards_Visual_Contrastive_Explanations_for_Neural_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Beyond Single Path Integrated Gradients for Reliable Input Attribution via Randomized Path Sampling", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jeon_Beyond_Single_Path_Integrated_Gradients_for_Reliable_Input_Attribution_via_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Learning Support and Trivial Prototypes for Interpretable Image Classification", + "base_url": null, + "title_page": null, + "github": "cwangrun/ST-ProtoPNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Learning_Support_and_Trivial_Prototypes_for_Interpretable_Image_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.04011", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + }, + { + "title": "Visual Explanations via Iterated Integrated Attributions", + "base_url": null, + "title_page": null, + "github": "iia-iccv23/iia", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Barkan_Visual_Explanations_via_Iterated_Integrated_Attributions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.18585", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Explainable AI for CV" + } +] \ No newline at end of file diff --git a/json_data/2023/main/faces-and-gestures.json b/json_data/2023/main/faces-and-gestures.json new file mode 100644 index 0000000..6811829 --- /dev/null +++ b/json_data/2023/main/faces-and-gestures.json @@ -0,0 +1,1217 @@ +[ + { + "title": "DeePoint: Visual Pointing Recognition and Direction Estimation", + "base_url": null, + "title_page": null, + "github": "kyotovision-public/deepoint", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nakamura_DeePoint_Visual_Pointing_Recognition_and_Direction_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06977", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Contactless Pulse Estimation Leveraging Pseudo Labels and Self-Supervision", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Contactless_Pulse_Estimation_Leveraging_Pseudo_Labels_and_Self-Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Most Important Person-Guided Dual-Branch Cross-Patch Attention for Group Affect Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_Most_Important_Person-Guided_Dual-Branch_Cross-Patch_Attention_for_Group_Affect_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.07055", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "ContactGen: Generative Contact Modeling for Grasp Generation", + "base_url": null, + "title_page": null, + "github": "stevenlsw/contactgen", + "web_page": null, + "github_page": "https://stevenlsw.github.io/contactgen/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_ContactGen_Generative_Contact_Modeling_for_Grasp_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.03740", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "pBgaQdMdB3Q", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Imitator: Personalized Speech-Driven 3D Facial Animation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://balamuruganthambiraja.github.io/Imitator/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Thambiraja_Imitator_Personalized_Speech-driven_3D_Facial_Animation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.00023", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "JhXTdjiUCUw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "DVGaze: Dual-View Gaze Estimation", + "base_url": null, + "title_page": null, + "github": "yihuacheng/DVGaze", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_DVGaze_Dual-View_Gaze_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10310", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective", + "base_url": null, + "title_page": null, + "github": "DanJun6737/TransFace", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dan_TransFace_Calibrating_Transformer_Training_for_Face_Recognition_from_a_Data-Centric_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10133", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Towards Unsupervised Domain Generalization for Face Anti-Spoofing", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Towards_Unsupervised_Domain_Generalization_for_Face_Anti-Spoofing_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Reinforced Disentanglement for Face Swapping without Skip Connection", + "base_url": null, + "title_page": null, + "github": "alaist/RD-FS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ren_Reinforced_Disentanglement_for_Face_Swapping_without_Skip_Connection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07928", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "CoSign: Exploring Co-Occurrence Signals in Skeleton-based Continuous Sign Language Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiao_CoSign_Exploring_Co-occurrence_Signals_in_Skeleton-based_Continuous_Sign_Language_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation", + "base_url": null, + "title_page": null, + "github": "psyai-net/EmoTalk_release", + "web_page": null, + "github_page": "https://ziqiaopeng.github.io/emotalk/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Peng_EmoTalk_Speech-Driven_Emotional_Disentanglement_for_3D_Face_Animation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11089", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "0uV2B1m-XjI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "LA-Net: Landmark-Aware Learning for Reliable Facial Expression Recognition under Label Noise", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_LA-Net_Landmark-Aware_Learning_for_Reliable_Facial_Expression_Recognition_under_Label_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09023", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "ASM: Adaptive Skinning Model for High-Quality 3D Face Modeling", + "base_url": null, + "title_page": null, + "github": "LiuLinyun/ASM-unofficial", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_ASM_Adaptive_Skinning_Model_for_High-Quality_3D_Face_Modeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.09423", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Troubleshooting Ethnic Quality Bias with Curriculum Domain Adaptation for Face Image Quality Assessment", + "base_url": null, + "title_page": null, + "github": "oufuzhao/EQBM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ou_Troubleshooting_Ethnic_Quality_Bias_with_Curriculum_Domain_Adaptation_for_Face_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "UniFace: Unified Cross-Entropy Loss for Deep Face Recognition", + "base_url": null, + "title_page": null, + "github": "CVI-SZU/UniFace", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_UniFace_Unified_Cross-Entropy_Loss_for_Deep_Face_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Human Part-Wise 3D Motion Context Learning for Sign Language Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Human_Part-wise_3D_Motion_Context_Learning_for_Sign_Language_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09305", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Weakly-Supervised Text-Driven Contrastive Learning for Facial Behavior Understanding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Weakly-Supervised_Text-Driven_Contrastive_Learning_for_Facial_Behavior_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.00058", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning", + "base_url": null, + "title_page": null, + "github": "zxz267/HaMuCo", + "web_page": null, + "github_page": "https://zxz267.github.io/HaMuCo/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_HaMuCo_Hand_Pose_Estimation_via_Multiview_Collaborative_Self-Supervised_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.00988", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "ReactioNet: Learning High-Order Facial Behavior from Universal Stimulus-Reaction by Dyadic Relation Reasoning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_ReactioNet_Learning_High-Order_Facial_Behavior_from_Universal_Stimulus-Reaction_by_Dyadic_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "CLIP-Cluster: CLIP-Guided Attribute Hallucination for Face Clustering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shen_CLIP-Cluster_CLIP-Guided_Attribute_Hallucination_for_Face_Clustering_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Learning Human Dynamics in Autonomous Driving Scenarios", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Learning_Human_Dynamics_in_Autonomous_Driving_Scenarios_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation", + "base_url": null, + "title_page": null, + "github": "zyhbili/LivelySpeaker", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhi_LivelySpeaker_Towards_Semantic-Aware_Co-Speech_Gesture_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.09294", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Controllable Guide-Space for Generalizable Face Forgery Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Controllable_Guide-Space_for_Generalizable_Face_Forgery_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14039", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Unpaired Multi-Domain Attribute Translation of 3D Facial Shapes with a Square and Symmetric Geometric Map", + "base_url": null, + "title_page": null, + "github": "NaughtyZZ/3D_facial_shape_attribute_translation_ssgmap", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_Unpaired_Multi-domain_Attribute_Translation_of_3D_Facial_Shapes_with_a_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13245", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Emotional Listener Portrait: Neural Listener Head Generation with Emotion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_Emotional_Listener_Portrait_Neural_Listener_Head_Generation_with_Emotion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.00068", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "KCzA5dnXf-I", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://merl.com/demos/steered-diffusion", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nair_Steered_Diffusion_A_Generalized_Framework_for_Plug-and-Play_Conditional_Image_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.00224", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Invariant Feature Regularization for Fair Face Recognition", + "base_url": null, + "title_page": null, + "github": "PanasonicConnect/InvReg", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Invariant_Feature_Regularization_for_Fair_Face_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.14652", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Gloss-Free Sign Language Translation: Improving from Visual-Language Pretraining", + "base_url": null, + "title_page": null, + "github": "zhoubenjia/GFSLT-VLP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Gloss-Free_Sign_Language_Translation_Improving_from_Visual-Language_Pretraining_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14768", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Contrastive Pseudo Learning for Open-World DeepFake Attribution", + "base_url": null, + "title_page": null, + "github": "TencentYoutuResearch/OpenWorld-DeepFakeAttribution", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Contrastive_Pseudo_Learning_for_Open-World_DeepFake_Attribution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11132", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Continual Learning for Personalized Co-Speech Gesture Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://chahuja.com/cdiffgan/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ahuja_Continual_Learning_for_Personalized_Co-speech_Gesture_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "HandR2N2: Iterative 3D Hand Pose Estimation using a Residual Recurrent Neural Network", + "base_url": null, + "title_page": null, + "github": "cwc1260/HandR2N2", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_HandR2N2_Iterative_3D_Hand_Pose_Estimation_Using_a_Residual_Recurrent_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "SPACE: Speech-Driven Portrait Animation with Controllable Expression", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://research.nvidia.com/labs/dir/space/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gururani_SPACE_Speech-driven_Portrait_Animation_with_Controllable_Expression_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.09809", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "DdCvJ8JI2-M", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "How to Boost Face Recognition with StyleGAN?", + "base_url": null, + "title_page": null, + "github": "seva100/stylegan-for-facerec", + "web_page": null, + "github_page": "https://seva100.github.io/stylegan-for-facerec", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sevastopolskiy_How_to_Boost_Face_Recognition_with_StyleGAN_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.10090", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Bsi0RMTdEaI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviour", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://www.idiap.ch/en/dataset/childplay-gaze", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": "https://zenodo.org/record/8252535", + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tafasca_ChildPlay_A_New_Benchmark_for_Understanding_Childrens_Gaze_Behaviour_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.01630", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Robust One-Shot Face Video Re-Enactment using Hybrid Latent Spaces of StyleGAN2", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://trevineoorloff.github.io/FaceVideoReenactment_HybridLatents.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Oorloff_Robust_One-Shot_Face_Video_Re-enactment_using_Hybrid_Latent_Spaces_of_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.07848", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Data-Free Class-Incremental Hand Gesture Recognition", + "base_url": null, + "title_page": null, + "github": "humansensinglab/dfcil-hgr", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Aich_Data-Free_Class-Incremental_Hand_Gesture_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "http://humansensing.cs.cmu.edu/sites/default/files/Data-Free%20Class-Incremental%20Hand%20Gesture%20Recognition_0.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Learning Robust Representations with Information Bottleneck and Memory Network for RGB-D-based Gesture Recognition", + "base_url": null, + "title_page": null, + "github": "Carpumpkin/InBoMem", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Learning_Robust_Representations_with_Information_Bottleneck_and_Memory_Network_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Knowledge-Spreader: Learning Semi-Supervised Facial Action Dynamics by Consistifying Knowledge Granularity", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Knowledge-Spreader_Learning_Semi-Supervised_Facial_Action_Dynamics_by_Consistifying_Knowledge_Granularity_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Face Clustering via Graph Convolutional Networks with Confidence Edges", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Face_Clustering_via_Graph_Convolutional_Networks_with_Confidence_Edges_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "StyleGANEX: StyleGAN-based Manipulation Beyond Cropped Aligned Faces", + "base_url": null, + "title_page": null, + "github": "williamyang1991/StyleGANEX", + "web_page": "https://www.mmlab-ntu.com/project/styleganex/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_StyleGANEX_StyleGAN-Based_Manipulation_Beyond_Cropped_Aligned_Faces_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06146", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "8oK0TXQmxg8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes", + "base_url": null, + "title_page": null, + "github": "anonymous-author-sub/seeable", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Larue_SeeABLE_Soft_Discrepancies_and_Bounded_Contrastive_Learning_for_Exposing_Deepfakes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.11296", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Adaptive Nonlinear Latent Transformation for Conditional Face Editing", + "base_url": null, + "title_page": null, + "github": "Hzzone/AdaTrans", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Adaptive_Nonlinear_Latent_Transformation_for_Conditional_Face_Editing_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07790", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "Semi-Supervised Speech-Driven 3D Facial Animation via Cross-Modal Encoding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Semi-supervised_Speech-driven_3D_Facial_Animation_via_Cross-modal_Encoding_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "ICD-Face: Intra-Class Compactness Distillation for Face Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_ICD-Face_Intra-class_Compactness_Distillation_for_Face_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + }, + { + "title": "C2ST: Cross-Modal Contextualized Sequence Transduction for Continuous Sign Language Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_C2ST_Cross-Modal_Contextualized_Sequence_Transduction_for_Continuous_Sign_Language_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Faces and Gestures" + } +] \ No newline at end of file diff --git a/json_data/2023/main/fairness-privacy-ethics-social-good-transparency-accountability-in-vision.json b/json_data/2023/main/fairness-privacy-ethics-social-good-transparency-accountability-in-vision.json new file mode 100644 index 0000000..2d71aa5 --- /dev/null +++ b/json_data/2023/main/fairness-privacy-ethics-social-good-transparency-accountability-in-vision.json @@ -0,0 +1,1109 @@ +[ + { + "title": "Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wan_Enhancing_Privacy_Preservation_in_Federated_Learning_via_Learning_Rate_Perturbation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation", + "base_url": null, + "title_page": null, + "github": "zj-jayzhang/Federated-Class-Continual-Learning", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_TARGET_Federated_Class-Continual_Learning_via_Exemplar-Free_Distillation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06937", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "FACTS: First Amplify Correlations and then Slice to Discover Bias", + "base_url": null, + "title_page": null, + "github": "yvsriram/FACTS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yenamandra_FACTS_First_Amplify_Correlations_and_Then_Slice_to_Discover_Bias_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.17430", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Computation and Data Efficient Backdoor Attacks", + "base_url": null, + "title_page": null, + "github": "WU-YU-TONG/computational_efficient_backdoor", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Computation_and_Data_Efficient_Backdoor_Attacks_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Global Balanced Experts for Federated Long-Tailed Learning", + "base_url": null, + "title_page": null, + "github": "Spinozaaa/Federated-Long-tailed-Learning", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zeng_Global_Balanced_Experts_for_Federated_Long-Tailed_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Source-Free Domain Adaptive Human Pose Estimation", + "base_url": null, + "title_page": null, + "github": "davidpengucf/SFDAHPE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Peng_Source-free_Domain_Adaptive_Human_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03202", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Gender Artifacts in Visual Datasets", + "base_url": null, + "title_page": null, + "github": "princetonvisualai/gender-artifacts", + "web_page": null, + "github_page": "https://princetonvisualai.github.io/gender-artifacts/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Meister_Gender_Artifacts_in_Visual_Datasets_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.09191", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_FRAug_Tackling_Federated_Learning_with_Non-IID_Features_via_Representation_Augmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2205.14900", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "zPROBE: Zero Peek Robustness Checks for Federated Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ghodsi_zPROBE_Zero_Peek_Robustness_Checks_for_Federated_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.12100", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study", + "base_url": null, + "title_page": null, + "github": "ruoxi-jia-group/CLIP-MIA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ko_Practical_Membership_Inference_Attacks_Against_Large-Scale_Multi-Modal_Models_A_Pilot_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.00108", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "FedPD: Federated Open Set Recognition with Parameter Disentanglement", + "base_url": null, + "title_page": null, + "github": "CityU-AIM-Group/FedPD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_FedPD_Federated_Open_Set_Recognition_with_Parameter_Disentanglement_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "MUter: Machine Unlearning on Adversarially Trained Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_MUter_Machine_Unlearning_on_Adversarially_Trained_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color", + "base_url": null, + "title_page": null, + "github": "SonyResearch/apparent_skincolor", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Thong_Beyond_Skin_Tone_A_Multidimensional_Measure_of_Apparent_Skin_Color_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05148", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "A Multidimensional Analysis of Social Biases in Vision Transformers", + "base_url": null, + "title_page": null, + "github": "jannik-brinkmann/social-biases-in-vision-transformers", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Brinkmann_A_Multidimensional_Analysis_of_Social_Biases_in_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.01948", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Partition-and-Debias: Agnostic Biases Mitigation via a Mixture of Biases-Specific Experts", + "base_url": null, + "title_page": null, + "github": "Jiaxuan-Li/PnD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Partition-And-Debias_Agnostic_Biases_Mitigation_via_a_Mixture_of_Biases-Specific_Experts_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10005", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Rethinking Data Distillation: Do not Overlook Calibration", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Rethinking_Data_Distillation_Do_Not_Overlook_Calibration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12463", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Mining Bias-Target Alignment from Voronoi Cells", + "base_url": null, + "title_page": null, + "github": "renahon/mining_bias_target_alignment_from_voronoi_cells", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nahon_Mining_bias-target_Alignment_from_Voronoi_Cells_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.03691", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Better May not be Fairer: A Study on Subgroup Discrepancy in Image Classification", + "base_url": null, + "title_page": null, + "github": "charismaticchiu/Better-May-Not-Be-Fairer-A-Study-Study-on-Subgroup-Discrepancy-in-Image-Classification", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chiu_Better_May_Not_Be_Fairer_A_Study_on_Subgroup_Discrepancy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.08649", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization", + "base_url": null, + "title_page": null, + "github": "ffhibnese/GIFD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_GIFD_A_Generative_Gradient_Inversion_Method_with_Feature_Domain_Optimization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04699", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach using Synthetic Faces and Human Evaluation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_Benchmarking_Algorithmic_Bias_in_Face_Recognition_An_Experimental_Approach_Using_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05441", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning", + "base_url": null, + "title_page": null, + "github": "imguangyu/FedPerfix", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_FedPerfix_Towards_Partial_Model_Personalization_of_Vision_Transformers_in_Federated_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09160", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Towards Attack-Tolerant Federated Learning via Critical Parameter Analysis", + "base_url": null, + "title_page": null, + "github": "Sungwon-Han/FEDCPA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_Towards_Attack-tolerant_Federated_Learning_via_Critical_Parameter_Analysis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09318", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "What can Discriminator do? Towards Box-Free Ownership Verification of Generative Adversarial Networks", + "base_url": null, + "title_page": null, + "github": "AbstractTeen/gan_ownership_verification", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_What_can_Discriminator_do_Towards_Box-free_Ownership_Verification_of_Generative_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15860", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Robust Heterogeneous Federated Learning under Data Corruption", + "base_url": null, + "title_page": null, + "github": "FangXiuwen/AugHFL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_Robust_Heterogeneous_Federated_Learning_under_Data_Corruption_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Communication-Efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence", + "base_url": null, + "title_page": null, + "github": "Soptq/iccv23-3sfc", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Communication-efficient_Federated_Learning_with_Single-Step_Synthetic_Features_Compressor_for_Faster_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.13562", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning", + "base_url": null, + "title_page": null, + "github": "TsingZ0/GPFL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_GPFL_Simultaneously_Learning_Global_and_Personalized_Feature_Information_for_Personalized_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10279", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention", + "base_url": null, + "title_page": null, + "github": "PKU-SEC-Lab/mpcvit", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zeng_MPCViT_Searching_for_Accurate_and_Efficient_MPC-Friendly_Vision_Transformer_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.13955", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Identification of Systematic Errors of Image Classifiers on Rare Subgroups", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Metzen_Identification_of_Systematic_Errors_of_Image_Classifiers_on_Rare_Subgroups_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05072", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Adaptive Image Anonymization in the Context of Image Classification with Neural Networks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shvai_Adaptive_Image_Anonymization_in_the_Context_of_Image_Classification_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "When do Curricula Work in Federated Learning?", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Vahidian_When_Do_Curricula_Work_in_Federated_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.12712", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Domain Specified Optimization for Deployment Authorization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Domain_Specified_Optimization_for_Deployment_Authorization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_STPrivacy_Spatio-Temporal_Privacy-Preserving_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.03046", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_SAL-ViT_Towards_Latency_Efficient_Private_Inference_on_ViT_using_Selective_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Generative_Gradient_Inversion_via_Over-Parameterized_Networks_in_Federated_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Inspecting the Geographical Representativeness of Images from Text-to-Image Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Basu_Inspecting_the_Geographical_Representativeness_of_Images_from_Text-to-Image_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.11080", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Divide and Conquer: A Two-Step Method for High Quality Face De-Identification with Model Explainability", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wen_Divide_and_Conquer_a_Two-Step_Method_for_High_Quality_Face_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Exploring the Benefits of Visual Prompting in Differential Privacy", + "base_url": null, + "title_page": null, + "github": "EzzzLi/Prom-PATE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Exploring_the_Benefits_of_Visual_Prompting_in_Differential_Privacy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12247", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Towards Fairness-Aware Adversarial Network Pruning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Towards_Fairness-aware_Adversarial_Network_Pruning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "AutoReP: Automatic ReLU Replacement for Fast Private Network Inference", + "base_url": null, + "title_page": null, + "github": "HarveyP123/AutoReP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Peng_AutoReP_Automatic_ReLU_Replacement_for_Fast_Private_Network_Inference_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10134", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Flatness-Aware Minimization for Domain Generalization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Flatness-Aware_Minimization_for_Domain_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11108", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + }, + { + "title": "Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://github.com/NVIDIA/NVFlare/tree/main/research/one-shot-vfl", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Communication-Efficient_Vertical_Federated_Learning_with_Limited_Overlapping_Samples_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16270", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Fairness, Privacy, Ethics, Social-good, Transparency, Accountability in Vision" + } +] \ No newline at end of file diff --git a/json_data/2023/main/first-person-egocentric-vision.json b/json_data/2023/main/first-person-egocentric-vision.json new file mode 100644 index 0000000..991e8c9 --- /dev/null +++ b/json_data/2023/main/first-person-egocentric-vision.json @@ -0,0 +1,191 @@ +[ + { + "title": "Multimodal Distillation for Egocentric Action Recognition", + "base_url": null, + "title_page": null, + "github": "gorjanradevski/multimodal-distillation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Radevski_Multimodal_Distillation_for_Egocentric_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07483", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "First Person (Egocentric) Vision" + }, + { + "title": "Self-Supervised Object Detection from Egocentric Videos", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Akiva_Self-Supervised_Object_Detection_from_Egocentric_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "First Person (Egocentric) Vision" + }, + { + "title": "Multi-Label Affordance Mapping from Egocentric Vision", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mur-Labadia_Multi-label_Affordance_Mapping_from_Egocentric_Vision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02120", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "First Person (Egocentric) Vision" + }, + { + "title": "Ego-Only: Egocentric Action Detection without Exocentric Transferring", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Ego-Only_Egocentric_Action_Detection_without_Exocentric_Transferring_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.01380", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "First Person (Egocentric) Vision" + }, + { + "title": "COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos", + "base_url": null, + "title_page": null, + "github": "leobxpan/COPILOT", + "web_page": "https://sites.google.com/stanford.edu/copilot", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pan_COPILOT_Human-Environment_Collision_Prediction_and_Localization_from_Egocentric_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.01781", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "lxRTPeac8Oo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "First Person (Egocentric) Vision" + }, + { + "title": "EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://mvig-rhos.com/ego_pca", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_EgoPCA_A_New_Framework_for_Egocentric_Hand-Object_Interaction_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02423", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "First Person (Egocentric) Vision" + }, + { + "title": "EgoVLPv2: Egocentric Video-Language Pre-Training with Fusion in the Backbone", + "base_url": null, + "title_page": null, + "github": "facebookresearch/EgoVLPv2", + "web_page": null, + "github_page": "https://shramanpramanick.github.io/EgoVLPv2/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pramanick_EgoVLPv2_Egocentric_Video-Language_Pre-training_with_Fusion_in_the_Backbone_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.05463", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "First Person (Egocentric) Vision" + } +] \ No newline at end of file diff --git a/json_data/2023/main/generative-ai.json b/json_data/2023/main/generative-ai.json new file mode 100644 index 0000000..8c5ba52 --- /dev/null +++ b/json_data/2023/main/generative-ai.json @@ -0,0 +1,650 @@ +[ + { + "title": "CLIPascene: Scene Sketching with Different Types and Levels of Abstraction", + "base_url": null, + "title_page": null, + "github": "yael-vinker/SceneSketch", + "web_page": null, + "github_page": "https://clipascene.github.io/CLIPascene/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Vinker_CLIPascene_Scene_Sketching_with_Different_Types_and_Levels_of_Abstraction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.17256", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "LD-ZNet: A Latent Diffusion Approach for Text-based Image Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://koutilya-pnvr.github.io/LD-ZNet/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/PNVR_LD-ZNet_A_Latent_Diffusion_Approach_for_Text-Based_Image_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12343", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://research.nvidia.com/labs/toronto-ai/texfusion/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_TexFusion_Synthesizing_3D_Textures_with_Text-Guided_Image_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.13772", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://oppo-us-research.github.io/NeuRBF-website/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_NeuRBF_A_Neural_Fields_Representation_with_Adaptive_Radial_Basis_Functions_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://cse.buffalo.edu/~jsyuan/papers/2023/ICCV2023_zhang.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Scalable Diffusion Models with Transformers", + "base_url": null, + "title_page": null, + "github": "facebookresearch/DiT", + "web_page": "https://www.wpeebles.com/DiT", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Peebles_Scalable_Diffusion_Models_with_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.09748", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Texture Generation on 3D Meshes with Point-UV Diffusion", + "base_url": null, + "title_page": null, + "github": "CVMI-Lab/Point-UV-Diffusion", + "web_page": null, + "github_page": "https://cvmi-lab.github.io/Point-UV-Diffusion/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Texture_Generation_on_3D_Meshes_with_Point-UV_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10490", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Generative Novel View Synthesis with 3D-Aware Diffusion Models", + "base_url": null, + "title_page": null, + "github": "NVlabs/genvs", + "web_page": null, + "github_page": "https://nvlabs.github.io/genvs/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chan_Generative_Novel_View_Synthesis_with_3D-Aware_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02602", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning", + "base_url": null, + "title_page": null, + "github": "mkshing/DiffFit-pytorch", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_DiffFit_Unlocking_Transferability_of_Large_Diffusion_Models_via_Simple_Parameter-efficient_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06648", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "VQ3D: Learning a 3D-Aware Generative Model on ImageNet", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://kylesargent.github.io/vq3d", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sargent_VQ3D_Learning_a_3D-Aware_Generative_Model_on_ImageNet_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.06833", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection", + "base_url": null, + "title_page": null, + "github": "EnVision-Research/Ref-NeuS", + "web_page": null, + "github_page": "https://g3956.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ge_Ref-NeuS_Ambiguity-Reduced_Neural_Implicit_Surface_Learning_for_Multi-View_Reconstruction_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10840", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "A Complete Recipe for Diffusion Generative Models", + "base_url": null, + "title_page": null, + "github": "mandt-lab/PSLD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pandey_A_Complete_Recipe_for_Diffusion_Generative_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.01748", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "MMVP: Motion-Matrix-based Video Prediction", + "base_url": null, + "title_page": null, + "github": "Kay1794/MMVP-motion-matrix-based-video-prediction", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhong_MMVP_Motion-Matrix-Based_Video_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16154", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Cross-Ray Neural Radiance Fields for Novel-View Synthesis from Unconstrained Image Collections", + "base_url": null, + "title_page": null, + "github": "YifYang993/CR-NeRF-PyTorch", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Cross-Ray_Neural_Radiance_Fields_for_Novel-View_Synthesis_from_Unconstrained_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08093", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Effective Real Image Editing with Accelerated Iterative Diffusion Inversion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pan_Effective_Real_Image_Editing_with_Accelerated_Iterative_Diffusion_Inversion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04907", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Simulating Fluids in Real-World Still Images", + "base_url": null, + "title_page": null, + "github": "simon3dv/SLR-SFS", + "web_page": null, + "github_page": "https://slr-sfs.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_Simulating_Fluids_in_Real-World_Still_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2204.11335", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Aatrl16t-V8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "FateZero: Fusing Attentions for Zero-Shot Text-based Video Editing", + "base_url": null, + "title_page": null, + "github": "ChenyangQiQi/FateZero", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/QI_FateZero_Fusing_Attentions_for_Zero-shot_Text-based_Video_Editing_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09535", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation", + "base_url": null, + "title_page": null, + "github": "csyxwei/ELITE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/ELITE-library/ELITE", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_ELITE_Encoding_Visual_Concepts_into_Textual_Embeddings_for_Customized_Text-to-Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.13848", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators", + "base_url": null, + "title_page": null, + "github": "Picsart-AI-Research/Text2Video-Zero", + "web_page": null, + "github_page": "https://text2video-zero.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/PAIR/Text2Video-Zero", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Khachatryan_Text2Video-Zero_Text-to-Image_Diffusion_Models_are_Zero-Shot_Video_Generators_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13439", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": "https://www.dropbox.com/s/uv90mi2z598olsq/Text2Video-Zero.MP4?dl=0", + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models", + "base_url": null, + "title_page": null, + "github": "snuvclab/chupa", + "web_page": null, + "github_page": "https://snuvclab.github.io/chupa/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Chupa_Carving_3D_Clothed_Humans_from_Skinned_Shape_Priors_using_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.11870", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "ZHwtbQSsQjw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "DiffPose: Multi-Hypothesis Human Pose Estimation using Diffusion Models", + "base_url": null, + "title_page": null, + "github": "bastianwandt/DiffPose", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Holmquist_DiffPose_Multi-hypothesis_Human_Pose_Estimation_using_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.16487", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation", + "base_url": null, + "title_page": null, + "github": "IDEA-Research/HumanSD", + "web_page": null, + "github_page": "https://idea-research.github.io/HumanSD/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ju_HumanSD_A_Native_Skeleton-Guided_Diffusion_Model_for_Human_Image_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.04269", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "rVy8eWCWRmg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Role-Aware Interaction Generation from Textual Description", + "base_url": null, + "title_page": null, + "github": "line/Human-Interaction-Generation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tanaka_Role-Aware_Interaction_Generation_from_Textual_Description_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "PhysDiff: Physics-Guided Human Motion Diffusion Model", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://nvlabs.github.io/PhysDiff/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yuan_PhysDiff_Physics-Guided_Human_Motion_Diffusion_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.02500", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "y8Tdcvzjfjg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + }, + { + "title": "Forward Flow for Novel View Synthesis of Dynamic Scenes", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://npucvr.github.io/ForwardFlowDNeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Forward_Flow_for_Novel_View_Synthesis_of_Dynamic_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.17390", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "AiUogciQlW8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Generative AI" + } +] \ No newline at end of file diff --git a/json_data/2023/main/geometric-deep-learning.json b/json_data/2023/main/geometric-deep-learning.json new file mode 100644 index 0000000..6dc73d7 --- /dev/null +++ b/json_data/2023/main/geometric-deep-learning.json @@ -0,0 +1,218 @@ +[ + { + "title": "Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation", + "base_url": null, + "title_page": null, + "github": "innerlee/GCR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Get_the_Best_of_Both_Worlds_Improving_Accuracy_and_Transferability_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.01547", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Geometric Deep Learning" + }, + { + "title": "4D Panoptic Segmentation as Invariant and Equivariant Field Prediction", + "base_url": null, + "title_page": null, + "github": "minghanz/EQ-4D-StOP", + "web_page": null, + "github_page": "https://eq-4d-panoptic.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_4D_Panoptic_Segmentation_as_Invariant_and_Equivariant_Field_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15651", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Geometric Deep Learning" + }, + { + "title": "SiLK: Simple Learned Keypoints", + "base_url": null, + "title_page": null, + "github": "facebookresearch/silk", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gleize_SiLK_Simple_Learned_Keypoints_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06194", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Geometric Deep Learning" + }, + { + "title": "SC3K: Self-Supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data", + "base_url": null, + "title_page": null, + "github": "IIT-PAVIS/SC3K", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zohaib_SC3K_Self-supervised_and_Coherent_3D_Keypoints_Estimation_from_Rotated_Noisy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05410", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Geometric Deep Learning" + }, + { + "title": "Geometric Viewpoint Learning with Hyper-Rays and Harmonics Encoding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Min_Geometric_Viewpoint_Learning_with_Hyper-Rays_and_Harmonics_Encoding_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Geometric Deep Learning" + }, + { + "title": "Surface Extraction from Neural Unsigned Distance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Surface_Extraction_from_Neural_Unsigned_Distance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08878", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Geometric Deep Learning" + }, + { + "title": "Learning Adaptive Neighborhoods for Graph Neural Networks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Saha_Learning_Adaptive_Neighborhoods_for_Graph_Neural_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09065", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Geometric Deep Learning" + }, + { + "title": "Why do Networks have Inhibitory/Negative Connections?", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Why_do_networks_have_inhibitorynegative_connections_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.03211", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Geometric Deep Learning" + } +] \ No newline at end of file diff --git a/json_data/2023/main/human-in-the-loop-computer-vision.json b/json_data/2023/main/human-in-the-loop-computer-vision.json new file mode 100644 index 0000000..1ff903e --- /dev/null +++ b/json_data/2023/main/human-in-the-loop-computer-vision.json @@ -0,0 +1,164 @@ +[ + { + "title": "Knowledge-Aware Federated Active Learning with Non-IID Data", + "base_url": null, + "title_page": null, + "github": "ycao5602/KAFAL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Knowledge-Aware_Federated_Active_Learning_with_Non-IID_Data_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.13579", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human-in-the-Loop Computer Vision" + }, + { + "title": "SimpleClick: Interactive Image Segmentation with Simple Vision Transformers", + "base_url": null, + "title_page": null, + "github": "uncbiag/SimpleClick", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_SimpleClick_Interactive_Image_Segmentation_with_Simple_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.11006", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human-in-the-Loop Computer Vision" + }, + { + "title": "InterFormer: Real-Time Interactive Image Segmentation", + "base_url": null, + "title_page": null, + "github": "YouHuang67/InterFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_InterFormer_Real-time_Interactive_Image_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02942", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human-in-the-Loop Computer Vision" + }, + { + "title": "Interactive Class-Agnostic Object Counting", + "base_url": null, + "title_page": null, + "github": "Yifehuang97/ICACount", + "web_page": null, + "github_page": "https://yifehuang97.github.io/ICACountProjectPage/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Interactive_Class-Agnostic_Object_Counting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05277", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human-in-the-Loop Computer Vision" + }, + { + "title": "Agile Modeling: From Concept to Classifier in Minutes", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Stretcu_Agile_Modeling_From_Concept_to_Classifier_in_Minutes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.12948", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human-in-the-Loop Computer Vision" + }, + { + "title": "TiDAL: Learning Training Dynamics for Active Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kye_TiDAL_Learning_Training_Dynamics_for_Active_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.06788", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human-in-the-Loop Computer Vision" + } +] \ No newline at end of file diff --git a/json_data/2023/main/human-poseshape-estimation.json b/json_data/2023/main/human-poseshape-estimation.json new file mode 100644 index 0000000..04ad250 --- /dev/null +++ b/json_data/2023/main/human-poseshape-estimation.json @@ -0,0 +1,1271 @@ +[ + { + "title": "EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild", + "base_url": null, + "title_page": null, + "github": "eth-ait/emdb", + "web_page": null, + "github_page": "https://eth-ait.github.io/emdb/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kaufmann_EMDB_The_Electromagnetic_Database_of_Global_3D_Human_Pose_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16894", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "H66-YE4GUHI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "ReFit: Recurrent Fitting Network for 3D Human Recovery", + "base_url": null, + "title_page": null, + "github": "yufu-wang/ReFit", + "web_page": null, + "github_page": "https://yufu-wang.github.io/refit_humans/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_ReFit_Recurrent_Fitting_Network_for_3D_Human_Recovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11184", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation", + "base_url": null, + "title_page": null, + "github": "rese1f/PoseDA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chai_Global_Adaptation_Meets_Local_Generalization_Unsupervised_Domain_Adaptation_for_3D_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16456", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Spectral Graphormer: Spectral Graph-based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images", + "base_url": null, + "title_page": null, + "github": "eldentse/Spectral-Graphormer", + "web_page": null, + "github_page": "https://eldentse.github.io/Spectral-Graphormer/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tse_Spectral_Graphormer_Spectral_Graph-Based_Transformer_for_Egocentric_Two-Hand_Reconstruction_using_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11015", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "cfsk5e5C_Xs", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling", + "base_url": null, + "title_page": null, + "github": "zxz267/AvatarJLM", + "web_page": null, + "github_page": "https://zxz267.github.io/AvatarJLM/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Realistic_Full-Body_Tracking_from_Sparse_Observations_via_Joint-Level_Modeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08855", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "H2sPFL0T3yk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Rethinking Pose Estimation in Crowds: Overcoming the Detection Information Bottleneck and Ambiguity", + "base_url": null, + "title_page": null, + "github": "amathislab/BUCTD", + "web_page": null, + "github_page": "https://amathislab.github.io/BUCTD/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Rethinking_Pose_Estimation_in_Crowds_Overcoming_the_Detection_Information_Bottleneck_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.07879", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "BHZnA-CZeZY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "HDG-ODE: A Hierarchical Continuous-Time Model for Human Pose Forecasting", + "base_url": null, + "title_page": null, + "github": "SBU-YCX/HDG-ODE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xing_HDG-ODE_A_Hierarchical_Continuous-Time_Model_for_Human_Pose_Forecasting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "AffordPose: A Large-Scale Dataset of Hand-Object Interactions with Affordance-Driven Hand Pose", + "base_url": null, + "title_page": null, + "github": "GentlesJan/AffordPose", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jian_AffordPose_A_Large-Scale_Dataset_of_Hand-Object_Interactions_with_Affordance-Driven_Hand_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08942", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "s89tlzoM_M0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "PhaseMP: Robust 3D Pose Estimation via Phase-Conditioned Human Motion Prior", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_PhaseMP_Robust_3D_Pose_Estimation_via_Phase-conditioned_Human_Motion_Prior_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Synthesizing Diverse Human Motions in 3D Indoor Scenes", + "base_url": null, + "title_page": null, + "github": "zkf1997/DIMOS", + "web_page": null, + "github_page": "https://zkf1997.github.io/DIMOS/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Synthesizing_Diverse_Human_Motions_in_3D_Indoor_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.12411", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "O3VpvETNjcw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://rccchoudhury.github.io/tempo2023/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Choudhury_TEMPO_Efficient_Multi-View_Pose_Estimation_Tracking_and_Forecasting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.07910", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "jxmBQqmVkIw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Diffusion-based 3D Human Pose Estimation with Multi-Hypothesis Aggregation", + "base_url": null, + "title_page": null, + "github": "paTRICK-swk/D3DP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shan_Diffusion-Based_3D_Human_Pose_Estimation_with_Multi-Hypothesis_Aggregation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11579", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_Towards_Robust_and_Smooth_3D_Multi-Person_Pose_Estimation_from_Monocular_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08644", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "d8z8DOE6s4I", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Humans in 4D: Reconstructing and Tracking Humans with Transformers", + "base_url": null, + "title_page": null, + "github": "shubham-goel/4D-Humans", + "web_page": null, + "github_page": "https://shubham-goel.github.io/4dhumans/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/brjathu/HMR2.0", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Goel_Humans_in_4D_Reconstructing_and_Tracking_Humans_with_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.20091", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "v6viHm2-uY4", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "NPC: Neural Point Characters from Video", + "base_url": null, + "title_page": null, + "github": "LemonATsu/NPC-pytorch", + "web_page": null, + "github_page": "https://lemonatsu.github.io/npc/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Su_NPC_Neural_Point_Characters_from_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02013", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Priority-Centric Human Motion Generation in Discrete Latent Space", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kong_Priority-Centric_Human_Motion_Generation_in_Discrete_Latent_Space_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14480", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects", + "base_url": null, + "title_page": null, + "github": "taeksuu/ncho", + "web_page": null, + "github_page": "https://taeksuu.github.io/ncho/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_NCHO_Unsupervised_Learning_for_Neural_3D_Composition_of_Humans_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.14345", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction", + "base_url": null, + "title_page": null, + "github": "hygenie1228/CycleAdapt_RELEASE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nam_Cyclic_Test-Time_Adaptation_on_Monocular_Video_for_3D_Human_Mesh_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06554", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "MHEntropy: Entropy Meets Multiple Hypotheses for Pose and Shape Recovery", + "base_url": null, + "title_page": null, + "github": "gloryyrolg/MHEntropy", + "web_page": null, + "github_page": "https://gloryyrolg.github.io/MHEntropy/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_MHEntropy_Entropy_Meets_Multiple_Hypotheses_for_Pose_and_Shape_Recovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "0riX3iJeVyM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose Estimation", + "base_url": null, + "title_page": null, + "github": "bymaths/probabilistic_triangulation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Probabilistic_Triangulation_for_Uncalibrated_Multi-View_3D_Human_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04756", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_DiffPose_SpatioTemporal_Diffusion_Model_for_Video-Based_Human_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16687", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "TC1szijh2aw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Reconstructing Groups of People with Hypergraph Relational Reasoning", + "base_url": null, + "title_page": null, + "github": "boycehbz/GroupRec", + "web_page": "https://www.yangangwang.com/papers/iccv2023-grouprec/HUANG-GROUPREC-2023-07.html", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Reconstructing_Groups_of_People_with_Hypergraph_Relational_Reasoning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.15844", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "MixSynthFormer: A Transformer Encoder-Like Structure with Mixed Synthetic Self-Attention for Efficient Human Pose Estimation", + "base_url": null, + "title_page": null, + "github": "ireneesun/MixSynthFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_MixSynthFormer_A_Transformer_Encoder-like_Structure_with_Mixed_Synthetic_Self-attention_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "8hkw3H2dlqc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Dynamic Hyperbolic Attention Network for Fine Hand-Object Reconstruction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Leng_Dynamic_Hyperbolic_Attention_Network_for_Fine_Hand-object_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02965", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Human from Blur: Human Pose Tracking from Blurry Images", + "base_url": null, + "title_page": null, + "github": "rozumden/HumanFromBlur", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Human_from_Blur_Human_Pose_Tracking_from_Blurry_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17209", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "i7Mr5gIrvXg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "AG3D: Learning to Generate 3D Avatars from 2D Image Collections", + "base_url": null, + "title_page": null, + "github": "zj-dong/AG3D", + "web_page": null, + "github_page": "https://zj-dong.github.io/AG3D/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_AG3D_Learning_to_Generate_3D_Avatars_from_2D_Image_Collections_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.02312", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "niP1YhJXEBE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion", + "base_url": null, + "title_page": null, + "github": "Sirui-Xu/InterDiff", + "web_page": null, + "github_page": "https://sirui-xu.github.io/InterDiff/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_InterDiff_Generating_3D_Human-Object_Interactions_with_Physics-Informed_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16905", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Ako1n9HEGBo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "SEFD: Learning to Distill Complex Pose and Occlusion", + "base_url": null, + "title_page": null, + "github": "YangChangHee/ICCV2023_SEFD_RELEASE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_SEFD_Learning_to_Distill_Complex_Pose_and_Occlusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "3D Human Mesh Recovery with Sequentially Global Rotation Estimation", + "base_url": null, + "title_page": null, + "github": "kennethwdk/SGRE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_3D_Human_Mesh_Recovery_with_Sequentially_Global_Rotation_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video", + "base_url": null, + "title_page": null, + "github": "kasvii/PMCE", + "web_page": null, + "github_page": "https://kasvii.github.io/PMCE/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/You_Co-Evolution_of_Pose_and_Mesh_for_3D_Human_Body_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10305", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "PHRIT: Parametric Hand Representation with Implicit Template", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_PHRIT_Parametric_Hand_Representation_with_Implicit_Template_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14916", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "HopFIR: Hop-Wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhai_HopFIR_Hop-wise_GraphFormer_with_Intragroup_Joint_Refinement_for_3D_Human_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.14581", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Prior-Guided Source-Free Domain Adaptation for Human Pose Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Raychaudhuri_Prior-guided_Source-free_Domain_Adaptation_for_Human_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13954", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dai_Cloth2Body_Generating_3D_Human_Body_Mesh_from_2D_Clothing_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16189", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "PoseFix: Correcting 3D Human Poses with Natural Language", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://europe.naverlabs.com/research/computer-vision/posefix/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Delmas_PoseFix_Correcting_3D_Human_Poses_with_Natural_Language_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08480", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Group Pose: A Simple Baseline for End-to-End Multi-Person Pose Estimation", + "base_url": null, + "title_page": null, + "github": "Michel-liu/GroupPose", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Group_Pose_A_Simple_Baseline_for_End-to-End_Multi-Person_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07313", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Make-an-Animation: Large-Scale Text-Conditional 3D Human Motion Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://azadis.github.io/make-an-animation/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Azadi_Make-An-Animation_Large-Scale_Text-conditional_3D_Human_Motion_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.09662", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "NSF: Neural Surface Fields for Human Modeling from Monocular Depth", + "base_url": null, + "title_page": null, + "github": "YuxuanSnow/NeuralSurfaceField", + "web_page": "https://yuxuan-xue.com/nsf/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xue_NSF_Neural_Surface_Fields_for_Human_Modeling_from_Monocular_Depth_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14847", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "iVPYQwsNTZM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models", + "base_url": null, + "title_page": null, + "github": "zju3dv/hghoi", + "web_page": null, + "github_page": "https://zju3dv.github.io/hghoi/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pi_Hierarchical_Generation_of_Human-Object_Interactions_with_Diffusion_Probabilistic_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Dynamic Mesh Recovery from Partial Point Cloud Sequence", + "base_url": null, + "title_page": null, + "github": "hojunJang17/DynamicMeshRecovery", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jang_Dynamic_Mesh_Recovery_from_Partial_Point_Cloud_Sequence_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "OgineYrkgRE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "MotionBERT: A Unified Perspective on Learning Human Motion Representations", + "base_url": null, + "title_page": null, + "github": "Walter0807/MotionBERT", + "web_page": null, + "github_page": "https://motionbert.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_MotionBERT_A_Unified_Perspective_on_Learning_Human_Motion_Representations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.06551", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "slSPQ9hNLjM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Novel-View Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views", + "base_url": null, + "title_page": null, + "github": "iscas3dv/HO-NeRF", + "web_page": null, + "github_page": "https://iscas3dv.github.io/HO-NeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qu_Novel-View_Synthesis_and_Pose_Estimation_for_Hand-Object_Interaction_from_Sparse_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11198", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision", + "base_url": null, + "title_page": null, + "github": "DeepWiSe888/OCHID-Fi", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_OCHID-Fi_Occlusion-Robust_Hand_Pose_Estimation_in_3D_via_RF-Vision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10146", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Neural Interactive Keypoint Detection", + "base_url": null, + "title_page": null, + "github": "IDEA-Research/Click-Pose", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Neural_Interactive_Keypoint_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10174", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Plausible Uncertainties for Human Pose Regression", + "base_url": null, + "title_page": null, + "github": "biggzlar/plausible-uncertainties", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bramlage_Plausible_Uncertainties_for_Human_Pose_Regression_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "mMEeU1Zm3iY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer", + "base_url": null, + "title_page": null, + "github": "Frank-ZY-Dou/TORE", + "web_page": null, + "github_page": "https://frank-zy-dou.github.io/projects/Tore/index.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dou_TORE_Token_Reduction_for_Efficient_Human_Mesh_Recovery_with_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.10705", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + }, + { + "title": "Weakly-Supervised 3D Pose Transfer with Keypoints", + "base_url": null, + "title_page": null, + "github": "jinnan-chen/3D-Pose-Transfer", + "web_page": null, + "github_page": "https://jinnan-chen.github.io/ws3dpt/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Weakly-supervised_3D_Pose_Transfer_with_Keypoints_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13459", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Human Pose/Shape Estimation" + } +] \ No newline at end of file diff --git a/json_data/2023/main/humans-3d-modeling-and-driving.json b/json_data/2023/main/humans-3d-modeling-and-driving.json new file mode 100644 index 0000000..22ec7c0 --- /dev/null +++ b/json_data/2023/main/humans-3d-modeling-and-driving.json @@ -0,0 +1,326 @@ +[ + { + "title": "Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models", + "base_url": null, + "title_page": null, + "github": "lukasHoel/text2room", + "web_page": null, + "github_page": "https://lukashoel.github.io/text-to-room/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hollein_Text2Room_Extracting_Textured_3D_Meshes_from_2D_Text-to-Image_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11989", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "fjRnFL91EZc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses", + "base_url": null, + "title_page": null, + "github": "apple/ml-live-pose", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Stier_LivePose_Online_3D_Reconstruction_from_Monocular_Video_with_Dynamic_Camera_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.00054", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "NDDepth: Normal-Distance Assisted Monocular Depth Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shao_NDDepth_Normal-Distance_Assisted_Monocular_Depth_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.10592", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "LATR: 3D Lane Detection from Monocular Images with Transformer", + "base_url": null, + "title_page": null, + "github": "JMoonr/LATR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_LATR_3D_Lane_Detection_from_Monocular_Images_with_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04583", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving", + "base_url": null, + "title_page": null, + "github": "OpenDriveLab/DriveAdapter", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jia_DriveAdapter_Breaking_the_Coupling_Barrier_of_Perception_and_Planning_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.00398", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "Dynamic Point Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://sergeyprokudin.github.io/dpf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Prokudin_Dynamic_Point_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02626", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "i-9eAgS8HEA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "Generalizing Neural Human Fitting to Unseen Poses with Articulated SE(3) Equivariance", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://arteq.is.tue.mpg.de/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_Generalizing_Neural_Human_Fitting_to_Unseen_Poses_With_Articulated_SE3_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.10528", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views", + "base_url": null, + "title_page": null, + "github": "sanweiliti/EgoHMR", + "web_page": null, + "github_page": "https://sanweiliti.github.io/egohmr/egohmr.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Probabilistic_Human_Mesh_Recovery_in_3D_Scenes_from_Egocentric_Views_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06024", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "K6m0BmfMG-E", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "DECO: Dense Estimation of 3D Human-Scene Contact in the Wild", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://deco.is.tue.mpg.de/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tripathi_DECO_Dense_Estimation_of_3D_Human-Scene_Contact_In_The_Wild_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image", + "base_url": null, + "title_page": null, + "github": "PengfeiRen96/DIR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ren_Decoupled_Iterative_Refinement_Framework_for_Interacting_Hands_Reconstruction_from_a_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.02410", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "Chasing Clouds: Differentiable Volumetric Rasterisation of Point Clouds as a Highly Efficient and Accurate Loss for Large-Scale Deformable 3D Registration", + "base_url": null, + "title_page": null, + "github": "mattiaspaul/ChasingClouds", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Heinrich_Chasing_Clouds_Differentiable_Volumetric_Rasterisation_of_Point_Clouds_as_a_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + }, + { + "title": "Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize more and Forget Less", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_Rehearsal-Free_Domain_Continual_Face_Anti-Spoofing_Generalize_More_and_Forget_Less_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09914", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Humans, 3D Modeling, and Driving" + } +] \ No newline at end of file diff --git a/json_data/2023/main/image-and-video-forensics.json b/json_data/2023/main/image-and-video-forensics.json new file mode 100644 index 0000000..9d89a93 --- /dev/null +++ b/json_data/2023/main/image-and-video-forensics.json @@ -0,0 +1,299 @@ +[ + { + "title": "Pre-Training-Free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learning", + "base_url": null, + "title_page": null, + "github": "Knightzjz/NCL-IML", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Pre-Training-Free_Image_Manipulation_Localization_through_Non-Mutually_Exclusive_Contrastive_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14900", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + }, + { + "title": "VADER: Video Alignment Differencing and Retrieval", + "base_url": null, + "title_page": null, + "github": "AlexBlck/vader", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Black_VADER_Video_Alignment_Differencing_and_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13193", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + }, + { + "title": "PIRNet: Privacy-Preserving Image Restoration Network via Wavelet Lifting", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Deng_PIRNet_Privacy-Preserving_Image_Restoration_Network_via_Wavelet_Lifting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + }, + { + "title": "Quality-Agnostic Deepfake Detection with Intra-Model Collaborative Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Le_Quality-Agnostic_Deepfake_Detection_with_Intra-model_Collaborative_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05911", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + }, + { + "title": "Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning", + "base_url": null, + "title_page": null, + "github": "yhZhai/WSCL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhai_Towards_Generic_Image_Manipulation_Detection_with_Weakly-Supervised_Self-Consistency_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01246", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + }, + { + "title": "UCF: Uncovering Common Features for Generalizable Deepfake Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_UCF_Uncovering_Common_Features_for_Generalizable_Deepfake_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.13949", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + }, + { + "title": "SAFL-Net: Semantic-Agnostic Feature Learning Network with Auxiliary Plugins for Image Manipulation Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_SAFL-Net_Semantic-Agnostic_Feature_Learning_Network_with_Auxiliary_Plugins_for_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + }, + { + "title": "DRAW: Defending Camera-Shooted RAW Against Image Manipulation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_DRAW_Defending_Camera-shooted_RAW_Against_Image_Manipulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16418", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + }, + { + "title": "DIRE for Diffusion-Generated Image Detection", + "base_url": null, + "title_page": null, + "github": "ZhendongWang6/DIRE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_DIRE_for_Diffusion-Generated_Image_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09295", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + }, + { + "title": "Uncertainty-Guided Learning for Improving Image Manipulation Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ji_Uncertainty-guided_Learning_for_Improving_Image_Manipulation_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + }, + { + "title": "The Stable Signature: Rooting Watermarks in Latent Diffusion Models", + "base_url": null, + "title_page": null, + "github": "facebookresearch/stable_signature", + "web_page": null, + "github_page": "https://pierrefdz.github.io/publications/stablesignature/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fernandez_The_Stable_Signature_Rooting_Watermarks_in_Latent_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15435", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Forensics" + } +] \ No newline at end of file diff --git a/json_data/2023/main/image-and-video-synthesis.json b/json_data/2023/main/image-and-video-synthesis.json new file mode 100644 index 0000000..9aedcf6 --- /dev/null +++ b/json_data/2023/main/image-and-video-synthesis.json @@ -0,0 +1,3647 @@ +[ + { + "title": "Text-Driven Generative Domain Adaptation with Spectral Consistency Regularization", + "base_url": null, + "title_page": null, + "github": "Victarry/Adaptation-SCR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Text-Driven_Generative_Domain_Adaptation_with_Spectral_Consistency_Regularization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "MosaiQ: Quantum Generative Adversarial Networks for Image Generation on NISQ Computers", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Silver_MosaiQ_Quantum_Generative_Adversarial_Networks_for_Image_Generation_on_NISQ_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11096", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Controllable Visual-Tactile Synthesis", + "base_url": null, + "title_page": null, + "github": "RuihanGao/visual-tactile-synthesis", + "web_page": null, + "github_page": "https://visual-tactile-synthesis.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_Controllable_Visual-Tactile_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.03051", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "TdwPfwsGX3I", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Editing Implicit Assumptions in Text-to-Image Diffusion Models", + "base_url": null, + "title_page": null, + "github": "bahjat-kawar/time-diffusion", + "web_page": null, + "github_page": "https://time-diffusion.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Orgad_Editing_Implicit_Assumptions_in_Text-to-Image_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08084", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars", + "base_url": null, + "title_page": null, + "github": "SamsungLabs/DINAR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Svitov_DINAR_Diffusion_Inpainting_of_Neural_Textures_for_One-Shot_Human_Avatars_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09375", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Smoothness Similarity Regularization for Few-Shot GAN Adaptation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sushko_Smoothness_Similarity_Regularization_for_Few-Shot_GAN_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09717", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_HSR-Diff_Hyperspectral_Image_Super-Resolution_via_Conditional_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.12085", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models", + "base_url": null, + "title_page": null, + "github": "YorkUCVIL/Photoconsistent-NVS", + "web_page": null, + "github_page": "https://yorkucvil.github.io/Photoconsistent-NVS/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Long-Term_Photometric_Consistent_Novel_View_Synthesis_with_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.10700", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_AutoDiffusion_Training-Free_Optimization_of_Time_Steps_and_Architectures_for_Automated_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.10438", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Collecting the Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Textures", + "base_url": null, + "title_page": null, + "github": "NannanLi999/pt_square", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Collecting_The_Puzzle_Pieces_Disentangled_Self-Driven_Human_Pose_Transfer_by_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.01887", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Multi-Directional Subspace Editing in Style-Space", + "base_url": null, + "title_page": null, + "github": "chennaveh/MDSE", + "web_page": null, + "github_page": "https://chennaveh.github.io/MDSE/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Naveh_Multi-Directional_Subspace_Editing_in_Style-Space_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.11825", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces", + "base_url": null, + "title_page": null, + "github": "StelaBou/HyperReenact", + "web_page": null, + "github_page": "https://stelabou.github.io/hyperreenact.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bounareli_HyperReenact_One-Shot_Reenactment_via_Jointly_Learning_to_Refine_and_Retarget_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10797", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Generating Realistic Images from in-the-Wild Sounds", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Generating_Realistic_Images_from_In-the-wild_Sounds_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02405", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "CC3D: Layout-Conditioned Generation of Compositional 3D Scenes", + "base_url": null, + "title_page": null, + "github": "sherwinbahmani/cc3d", + "web_page": null, + "github_page": "https://sherwinbahmani.github.io/cc3d/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bahmani_CC3D_Layout-Conditioned_Generation_of_Compositional_3D_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12074", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "UMFuse: Unified Multi View Fusion for Human Editing Applications", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://mdsrlab.github.io/2023/08/13/UMFuse-ICCV.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jain_UMFuse_Unified_Multi_View_Fusion_for_Human_Editing_Applications_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.10157", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Evaluating Data Attribution for Text-to-Image Models", + "base_url": null, + "title_page": null, + "github": "PeterWang512/GenDataAttribution", + "web_page": null, + "github_page": "https://peterwang512.github.io/GenDataAttribution/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Evaluating_Data_Attribution_for_Text-to-Image_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.09345", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "iO6fiSyyv40", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Neural Characteristic Function Learning for Conditional Image Generation", + "base_url": null, + "title_page": null, + "github": "Zhangjialu126/ccf_gan", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Neural_Characteristic_Function_Learning_for_Conditional_Image_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "WaveIPT: Joint Attention and Flow Alignment in the Wavelet Domain for Pose Transfer", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_WaveIPT_Joint_Attention_and_Flow_Alignment_in_the_Wavelet_domain_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models", + "base_url": null, + "title_page": null, + "github": "microsoft/LayoutGeneration", + "web_page": null, + "github_page": "https://github.com/microsoft/LayoutGeneration/tree/main/LayoutDiffusion", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_LayoutDiffusion_Improving_Graphic_Layout_Generation_by_Discrete_Diffusion_Probabilistic_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11589", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation", + "base_url": null, + "title_page": null, + "github": "AiArt-HDU/HIDA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_Human-Inspired_Facial_Sketch_Synthesis_with_Dynamic_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.00216", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Conceptual and Hierarchical Latent Space Decomposition for Face Editing", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ozkan_Conceptual_and_Hierarchical_Latent_Space_Decomposition_for_Face_Editing_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jeon_Improving_Diversity_in_Zero-Shot_GAN_Adaptation_with_Semantic_Variations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10554", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "BallGAN: 3D-Aware Image Synthesis with a Spherical Background", + "base_url": null, + "title_page": null, + "github": "minjung-s/BallGAN", + "web_page": null, + "github_page": "https://minjung-s.github.io/ballgan", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shin_BallGAN_3D-aware_Image_Synthesis_with_a_Spherical_Background_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.09091", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "RUIWWMiomuY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "End-to-End Diffusion Latent Optimization Improves Classifier Guidance", + "base_url": null, + "title_page": null, + "github": "salesforce/DOODL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wallace_End-to-End_Diffusion_Latent_Optimization_Improves_Classifier_Guidance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13703", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Deep Geometrized Cartoon Line Inbetweening", + "base_url": null, + "title_page": null, + "github": "lisiyao21/AnimeInbet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Siyao_Deep_Geometrized_Cartoon_Line_Inbetweening_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16643", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation", + "base_url": null, + "title_page": null, + "github": "UnitedHuman/UnitedHuman", + "web_page": null, + "github_page": "https://unitedhuman.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fu_UnitedHuman_Harnessing_Multi-Source_Data_for_High-Resolution_Human_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14335", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "pdsfUYFDLSw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Towards_Authentic_Face_Restoration_with_Iterative_Diffusion_Models_and_Beyond_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08996", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "SVDiff: Compact Parameter Space for Diffusion Fine-Tuning", + "base_url": null, + "title_page": null, + "github": "mkshing/svdiff-pytorch", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_SVDiff_Compact_Parameter_Space_for_Diffusion_Fine-Tuning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11305", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices", + "base_url": null, + "title_page": null, + "github": "Picsart-AI-Research/MI-GAN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sargsyan_MI-GAN_A_Simple_Baseline_for_Image_Inpainting_on_Mobile_Devices_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Structure and Content-Guided Video Synthesis with Diffusion Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://research.runwayml.com/gen1", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Esser_Structure_and_Content-Guided_Video_Synthesis_with_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.03011", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Y2_JmgzTeeo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translation", + "base_url": null, + "title_page": null, + "github": "Yuxinn-J/Scenimefy", + "web_page": null, + "github_page": "https://yuxinn-j.github.io/projects/Scenimefy.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/YuxinJ/Scenimefy", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Scenimefy_Learning_to_Craft_Anime_Scene_via_Semi-Supervised_Image-to-Image_Translation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12968", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Efficient-VQGAN_Towards_High-Resolution_Image_Generation_with_Efficient_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.05400", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "A Latent Space of Stochastic Diffusion Models for Zero-Shot Image Editing and Guidance", + "base_url": null, + "title_page": null, + "github": "humansensinglab/cycle-diffusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_A_Latent_Space_of_Stochastic_Diffusion_Models_for_Zero-Shot_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Generative Multiplane Neural Radiance for 3D-Aware Image Generation", + "base_url": null, + "title_page": null, + "github": "VIROBO-15/GMNR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kumar_Generative_Multiplane_Neural_Radiance_for_3D-Aware_Image_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01172", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Parallax-Tolerant Unsupervised Deep Image Stitching", + "base_url": null, + "title_page": null, + "github": "nie-lang/UDIS2", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nie_Parallax-Tolerant_Unsupervised_Deep_Image_Stitching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.08207", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning", + "base_url": null, + "title_page": null, + "github": "desaixie/gait", + "web_page": null, + "github_page": "https://desaixie.github.io/gait-rl/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_GAIT_Generating_Aesthetic_Indoor_Tours_with_Deep_Reinforcement_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "EverLight: Indoor-Outdoor Editable HDR Lighting Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://lvsn.github.io/everlight/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dastjerdi_EverLight_Indoor-Outdoor_Editable_HDR_Lighting_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.13207", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Mk2ZhXxzLRY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Prompt Tuning Inversion for Text-Driven Image Editing using Diffusion Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Prompt_Tuning_Inversion_for_Text-driven_Image_Editing_Using_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.04441", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Efficient Diffusion Training via Min-SNR Weighting Strategy", + "base_url": null, + "title_page": null, + "github": "TiankaiHang/Min-SNR-Diffusion-Training", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hang_Efficient_Diffusion_Training_via_Min-SNR_Weighting_Strategy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09556", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion", + "base_url": null, + "title_page": null, + "github": "showlab/BoxDiff", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_BoxDiff_Text-to-Image_Synthesis_with_Training-Free_Box-Constrained_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10816", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Improving Sample Quality of Diffusion Models using Self-Attention Guidance", + "base_url": null, + "title_page": null, + "github": "KU-CVLAB/Self-Attention-Guidance", + "web_page": null, + "github_page": "https://ku-cvlab.github.io/Self-Attention-Guidance/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hong_Improving_Sample_Quality_of_Diffusion_Models_Using_Self-Attention_Guidance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.00939", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation", + "base_url": null, + "title_page": null, + "github": "EnVision-Research/Selective-Diffusion-Distillation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Not_All_Steps_are_Created_Equal_Selective_Diffusion_Distillation_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08448", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Deep Image Harmonization with Learnable Augmentation", + "base_url": null, + "title_page": null, + "github": "bcmi/SycoNet-Adaptive-Image-Harmonization", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Niu_Deep_Image_Harmonization_with_Learnable_Augmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.00376", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Out-of-Domain GAN Inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation", + "base_url": null, + "title_page": null, + "github": "AbnerVictor/OOD-GAN-inversion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Out-of-Domain_GAN_Inversion_via_Invertibility_Decomposition_for_Photo-Realistic_Human_Face_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.09262", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Bidirectionally Deformable Motion Modulation for Video-based Human Pose Transfer", + "base_url": null, + "title_page": null, + "github": "rocketappslab/bdmm", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Bidirectionally_Deformable_Motion_Modulation_For_Video-based_Human_Pose_Transfer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07754", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Size does Matter: Size-Aware Virtual Try-On via Clothing-Oriented Transformation Try-On Network", + "base_url": null, + "title_page": null, + "github": "cotton6/COTTON-size-does-matter", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Size_Does_Matter_Size-aware_Virtual_Try-on_via_Clothing-oriented_Transformation_Try-on_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs", + "base_url": null, + "title_page": null, + "github": "MoayedHajiAli/VidStyleODE-official", + "web_page": null, + "github_page": "https://cyberiada.github.io/VidStyleODE/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ali_VidStyleODE_Disentangled_Video_Editing_via_StyleGAN_and_NeuralODEs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06020", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Cfh-mgr1isc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Learning Global-Aware Kernel for Image Harmonization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shen_Learning_Global-aware_Kernel_for_Image_Harmonization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.11676", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Expressive Text-to-Image Generation with Rich Text", + "base_url": null, + "title_page": null, + "github": "SongweiGe/rich-text-to-image", + "web_page": null, + "github_page": "https://rich-text-to-image.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/songweig/rich-text-to-image", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ge_Expressive_Text-to-Image_Generation_with_Rich_Text_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06720", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "ihDbAUh0LXk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "A Large-Scale Outdoor Multi-Modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction", + "base_url": null, + "title_page": null, + "github": "luchongshan/OMMO", + "web_page": "https://ommo.luchongshan.com/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_A_Large-Scale_Outdoor_Multi-Modal_Dataset_and_Benchmark_for_Novel_View_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.06782", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": "https://www.loom.com/share/7b9ed35bfb3649eda051398d3a51cda7", + "section": "Image and Video Synthesis" + }, + { + "title": "Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis", + "base_url": null, + "title_page": null, + "github": "Fictionarry/ER-NeRF", + "web_page": null, + "github_page": "https://fictionarry.github.io/ER-NeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Efficient_Region-Aware_Neural_Radiance_Fields_for_High-Fidelity_Talking_Portrait_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09323", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Gc2d3Z8MMuI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Perceptual Artifacts Localization for Image Synthesis Tasks", + "base_url": null, + "title_page": null, + "github": "owenzlz/PAL4VST", + "web_page": null, + "github_page": "https://owenzlz.github.io/PAL4VST/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Perceptual_Artifacts_Localization_for_Image_Synthesis_Tasks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.05590", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis", + "base_url": null, + "title_page": null, + "github": "pmh9960/GCDP", + "web_page": null, + "github_page": "https://pmh9960.github.io/research/GCDP/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_Learning_to_Generate_Semantic_Layouts_for_Higher_Text-Image_Correspondence_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08157", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "StylerDALLE: Language-Guided Style Transfer using a Vector-Quantized Tokenizer of a Large-Scale Generative Model", + "base_url": null, + "title_page": null, + "github": "zipengxuc/StylerDALLE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_StylerDALLE_Language-Guided_Style_Transfer_Using_a_Vector-Quantized_Tokenizer_of_a_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09268", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction", + "base_url": null, + "title_page": null, + "github": "indigopyj/Shortcut-V2V", + "web_page": null, + "github_page": "https://shortcut-v2v.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chung_Shortcut-V2V_Compression_Framework_for_Video-to-Video_Translation_Based_on_Temporal_Redundancy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08011", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Tune-a-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation", + "base_url": null, + "title_page": null, + "github": "showlab/Tune-A-Video", + "web_page": null, + "github_page": "https://tuneavideo.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/Tune-A-Video-library/Tune-A-Video-Training-UI", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Tune-A-Video_One-Shot_Tuning_of_Image_Diffusion_Models_for_Text-to-Video_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.11565", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "BlendFace: Re-Designing Identity Encoders for Face-Swapping", + "base_url": null, + "title_page": null, + "github": "mapooon/BlendFace", + "web_page": null, + "github_page": "https://mapooon.github.io/BlendFacePage/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shiohara_BlendFace_Re-designing_Identity_Encoders_for_Face-Swapping_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10854", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://zxyin.github.io/TH-PAD/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Talking_Head_Generation_with_Probabilistic_Audio-to-Visual_Diffusion_Priors_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.04248", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "CrLXg7Cq8w8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis", + "base_url": null, + "title_page": null, + "github": "zhujiapeng/linkgan", + "web_page": null, + "github_page": "https://zhujiapeng.github.io/linkgan/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_LinkGAN_Linking_GAN_Latents_to_Pixels_for_Controllable_Image_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.04604", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Open-Vocabulary Object Segmentation with Diffusion Models", + "base_url": null, + "title_page": null, + "github": "Lipurple/Grounded-Diffusion", + "web_page": null, + "github_page": "https://lipurple.github.io/Grounded_Diffusion/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Open-vocabulary_Object_Segmentation_with_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.05221", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models", + "base_url": null, + "title_page": null, + "github": "rafaelheid-it/StyleDiffusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_StyleDiffusion_Controllable_Disentangled_Style_Transfer_via_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07863", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "ToonTalker: Cross-Domain Face Reenactment", + "base_url": null, + "title_page": null, + "github": "OpenTalker/ToonTalker", + "web_page": null, + "github_page": "https://opentalker.github.io/ToonTalker/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gong_ToonTalker_Cross-Domain_Face_Reenactment_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12866", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Dense Text-to-Image Generation with Attention Modulation", + "base_url": null, + "title_page": null, + "github": "naver-ai/DenseDiffusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Dense_Text-to-Image_Generation_with_Attention_Modulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12964", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Householder Projector for Unsupervised Latent Semantics Discovery", + "base_url": null, + "title_page": null, + "github": "KingJamesSong/HouseholderGAN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_Householder_Projector_for_Unsupervised_Latent_Semantics_Discovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08012", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation", + "base_url": null, + "title_page": null, + "github": "bcmi/Image-Harmonization-Dataset-ccHarmony", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Niu_Deep_Image_Harmonization_with_Globally_Guided_Feature_Transformation_and_Relation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.00356", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "One-Shot Generative Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "genforce/genda", + "web_page": null, + "github_page": "https://genforce.github.io/genda/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_One-Shot_Generative_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2111.09876", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Hashing Neural Video Decomposition with Multiplicative Residuals in Space-Time", + "base_url": null, + "title_page": null, + "github": "vllab/hashing-nvd", + "web_page": null, + "github_page": "https://lightbulb12294.github.io/hashing-nvd/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chan_Hashing_Neural_Video_Decomposition_with_Multiplicative_Residuals_in_Space-Time_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14022", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Versatile Diffusion: Text, Images and Variations All in One Diffusion Model", + "base_url": null, + "title_page": null, + "github": "SHI-Labs/Versatile-Diffusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/shi-labs/Versatile-Diffusion", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Versatile_Diffusion_Text_Images_and_Variations_All_in_One_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.08332", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis", + "base_url": null, + "title_page": null, + "github": "UCSB-NLP-Chang/Diffusion-SpaceTime-Attn", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Harnessing_the_Spatial-Temporal_Attention_of_Diffusion_Models_for_High-Fidelity_Text-to-Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.03869", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model", + "base_url": null, + "title_page": null, + "github": "vvictoryuki/FreeDoM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_FreeDoM_Training-Free_Energy-Guided_Conditional_Diffusion_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09833", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing", + "base_url": null, + "title_page": null, + "github": "TencentARC/MasaCtrl", + "web_page": null, + "github_page": "https://ljzycmd.github.io/projects/MasaCtrl/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/TencentARC/MasaCtrl", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_MasaCtrl_Tuning-Free_Mutual_Self-Attention_Control_for_Consistent_Image_Synthesis_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.08465", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Personalized Image Generation for Color Vision Deficiency Population", + "base_url": null, + "title_page": null, + "github": "Jiangshuyi0V0/CVD-GAN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Personalized_Image_Generation_for_Color_Vision_Deficiency_Population_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "ReNeRF: Relightable Neural Radiance Fields with Nearfield Lighting", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_ReNeRF_Relightable_Neural_Radiance_Fields_with_Nearfield_Lighting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "iPBesfjNVXM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models", + "base_url": null, + "title_page": null, + "github": "MagicFusion/MagicFusion.github.io", + "web_page": null, + "github_page": "https://magicfusion.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_MagicFusion_Boosting_Text-to-Image_Generation_Performance_by_Fusing_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13126", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap using Pose-Preserved Text-to-Image Diffusion", + "base_url": null, + "title_page": null, + "github": "gwang-kim/PODIA-3D", + "web_page": null, + "github_page": "https://gwang-kim.github.io/podia_3d/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_PODIA-3D_Domain_Adaptation_of_3D_Generative_Model_Across_Large_Domain_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01900", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "KNpbtqeDshk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Pluralistic Aging Diffusion Autoencoder", + "base_url": null, + "title_page": null, + "github": "raywang335/PADA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Pluralistic_Aging_Diffusion_Autoencoder_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11086", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "DPM-OT: A New Diffusion Probabilistic Model based on Optimal Transport", + "base_url": null, + "title_page": null, + "github": "cognaclee/DPM-OT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_DPM-OT_A_New_Diffusion_Probabilistic_Model_Based_on_Optimal_Transport_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11308", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation", + "base_url": null, + "title_page": null, + "github": "yuangan/EAT_code", + "web_page": null, + "github_page": "https://yuangan.github.io/eat/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gan_Efficient_Emotional_Adaptation_for_Audio-Driven_Talking-Head_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04946", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "lp2nSLZp-88", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "DiFaReli: Diffusion Face Relighting", + "base_url": null, + "title_page": null, + "github": "diffusion-face-relighting/difareli_code", + "web_page": null, + "github_page": "https://diffusion-face-relighting.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ponglertnapakorn_DiFaReli_Diffusion_Face_Relighting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.09479", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "TALL: Thumbnail Layout for Deepfake Video Detection", + "base_url": null, + "title_page": null, + "github": "rainy-xu/TALL4Deepfake", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_TALL_Thumbnail_Layout_for_Deepfake_Video_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07494", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_LAW-Diffusion_Complex_Scene_Generation_by_Diffusion_with_Layouts_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06713", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "DreamPose: Fashion Video Synthesis with Stable Diffusion", + "base_url": null, + "title_page": null, + "github": "johannakarras/DreamPose", + "web_page": "https://grail.cs.washington.edu/projects/dreampose/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Karras_DreamPose_Fashion_Video_Synthesis_with_Stable_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06025", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Ablating Concepts in Text-to-Image Diffusion Models", + "base_url": null, + "title_page": null, + "github": "nupurkmr9/concept-ablation", + "web_page": "https://www.cs.cmu.edu/~concept-ablation/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/nupurkmr9/concept-ablation", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kumari_Ablating_Concepts_in_Text-to-Image_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13516", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "DReg-NeRF: Deep Registration for Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": "AIBluefisher/DReg-NeRF", + "web_page": null, + "github_page": "https://aibluefisher.github.io/DReg-NeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_DReg-NeRF_Deep_Registration_for_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09386", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-Shot Image Generation", + "base_url": null, + "title_page": null, + "github": "lingxiao-li/HAE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_The_Euclidean_Space_is_Evil_Hyperbolic_Attribute_Editing_for_Few-shot_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.12347", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Discriminative Class Tokens for Text-to-Image Diffusion Models", + "base_url": null, + "title_page": null, + "github": "idansc/discriminative_class_tokens", + "web_page": null, + "github_page": "https://vesteinn.github.io/disco/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Schwartz_Discriminative_Class_Tokens_for_Text-to-Image_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17155", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "General Image-to-Image Translation with One-Shot Image Guidance", + "base_url": null, + "title_page": null, + "github": "CrystalNeuro/visual-concept-translator", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_General_Image-to-Image_Translation_with_One-Shot_Image_Guidance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14352", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Text2Performer: Text-Driven Human Video Generation", + "base_url": null, + "title_page": null, + "github": "yumingj/Text2Performer", + "web_page": null, + "github_page": "https://yumingj.github.io/projects/Text2Performer.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Text2Performer_Text-Driven_Human_Video_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.08483", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "YwhaJUk_qo0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks", + "base_url": null, + "title_page": null, + "github": "kibeom-hong/aespa-net", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hong_AesPA-Net_Aesthetic_Pattern-Aware_Style_Transfer_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09724", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Controllable Person Image Synthesis with Pose-Constrained Latent Diffusion", + "base_url": null, + "title_page": null, + "github": "BrandonHanx/PoCoLD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_Controllable_Person_Image_Synthesis_with_Pose-Constrained_Latent_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face Inpainting", + "base_url": null, + "title_page": null, + "github": "humansensinglab/PATMAT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Motamed_PATMAT_Person_Aware_Tuning_of_Mask-Aware_Transformer_for_Face_Inpainting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06107", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Virtual Try-On with Pose-Garment Keypoints Guided Inpainting", + "base_url": null, + "title_page": null, + "github": "lizhi-ntu/KGI", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Virtual_Try-On_with_Pose-Garment_Keypoints_Guided_Inpainting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Online Clustered Codebook", + "base_url": null, + "title_page": null, + "github": "lyndonzheng/CVQ-VAE", + "web_page": "https://chuanxiaz.com/cvq/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Online_Clustered_Codebook_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15139", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "g098J5Obxvs", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "InfiniCity: Infinite-Scale City Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://hubert0527.github.io/infinicity/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_InfiniCity_Infinite-Scale_City_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.09637", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "eaoTVZSLPH4", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Make-it-3D: High-fidelity 3D Creation from a Single Image with Diffusion Prior", + "base_url": null, + "title_page": null, + "github": "junshutang/Make-It-3D", + "web_page": null, + "github_page": "https://make-it-3d.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_Make-It-3D_High-fidelity_3D_Creation_from_A_Single_Image_with_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14184", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "2M8JJFeDBFk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "SAMPLING: Scene-Adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://pkuvdig.github.io/SAMPLING/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_SAMPLING_Scene-adaptive_Hierarchical_Multiplane_Images_Representation_for_Novel_View_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.06323", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "StyleLipSync: Style-based Personalized Lip-Sync Video Generation", + "base_url": null, + "title_page": null, + "github": "AMEERAZAM08/StyleLipSync", + "web_page": null, + "github_page": "https://stylelipsync.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ki_StyleLipSync_Style-based_Personalized_Lip-sync_Video_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.00521", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation", + "base_url": null, + "title_page": null, + "github": "johannwyh/StyleInV", + "web_page": "https://www.mmlab-ntu.com/project/styleinv/index.html", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_StyleInV_A_Temporal_Style_Modulated_Inversion_Network_for_Unconditional_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16909", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "R_v_L-32_Vo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "3D-Aware Generative Model for Improved Side-View Image Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jo_3D-Aware_Generative_Model_for_Improved_Side-View_Image_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.10388", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer", + "base_url": null, + "title_page": null, + "github": "YSerin/ZeCon", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Zero-Shot_Contrastive_Loss_for_Text-Guided_Diffusion_Image_Style_Transfer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08622", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "FlipNeRF: Flipped Reflection Rays for Few-Shot Novel View Synthesis", + "base_url": null, + "title_page": null, + "github": "shawn615/FlipNeRF", + "web_page": null, + "github_page": "https://shawn615.github.io/flipnerf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Seo_FlipNeRF_Flipped_Reflection_Rays_for_Few-shot_Novel_View_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.17723", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "_XNsRxzaPjw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Inverse Problem Regularization with Hierarchical Variational Autoencoders", + "base_url": null, + "title_page": null, + "github": "jprost76/PnP-HVAE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Prost_Inverse_Problem_Regularization_with_Hierarchical_Variational_Autoencoders_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11217", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "3D-Aware Blending with Generative NeRFs", + "base_url": null, + "title_page": null, + "github": "naver-ai/BlendNeRF", + "web_page": null, + "github_page": "https://blandocs.github.io/blendnerf", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_3D-aware_Blending_with_Generative_NeRFs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.06608", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "mwLPY-QIxkc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "NeMF: Inverse Volume Rendering with Neural Microflake Field", + "base_url": null, + "title_page": null, + "github": "YoujiaZhang/NeMF", + "web_page": null, + "github_page": "https://youjiazhang.github.io/NeMF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_NeMF_Inverse_Volume_Rendering_with_Neural_Microflake_Field_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.00782", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Preserve your Own Correlation: A Noise Prior for Video Diffusion Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://research.nvidia.com/labs/dir/pyoco/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ge_Preserve_Your_Own_Correlation_A_Noise_Prior_for_Video_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.10474", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "iVS-Net: Learning Human View Synthesis from Internet Videos", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_iVS-Net_Learning_Human_View_Synthesis_from_Internet_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "EGC: Image Generation and Classification via a Diffusion Energy-based Model", + "base_url": null, + "title_page": null, + "github": "GuoQiushan/EGC", + "web_page": null, + "github_page": "https://guoqiushan.github.io/egc.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_EGC_Image_Generation_and_Classification_via_a_Diffusion_Energy-Based_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02012", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Automatic Animation of Hair Blowing in Still Portrait Photos", + "base_url": null, + "title_page": null, + "github": "Rysertio/automatic-hair-blowing", + "web_page": null, + "github_page": "https://nevergiveu.github.io/AutomaticHairBlowing/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiao_Automatic_Animation_of_Hair_Blowing_in_Still_Portrait_Photos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14207", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "HoloFusion: Towards Photo-Realistic 3D Generative Modeling", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://holodiffusion.github.io/holofusion/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Karnewar_HoloFusion_Towards_Photo-realistic_3D_Generative_Modeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14244", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "wJ7PfTgcVgM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Foreground Object Search by Distilling Composite Image Feature", + "base_url": null, + "title_page": null, + "github": "bcmi/Foreground-Object-Search-Dataset-FOSD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Foreground_Object_Search_by_Distilling_Composite_Image_Feature_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04990", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "OrthoPlanes: A Novel Representation for Better 3D-Awareness of GANs", + "base_url": null, + "title_page": null, + "github": "OrthoPlanes/op3d", + "web_page": null, + "github_page": "https://orthoplanes.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_OrthoPlanes_A_Novel_Representation_for_Better_3D-Awareness_of_GANs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.15830", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "o8ghAi975vo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping", + "base_url": null, + "title_page": null, + "github": "3dhumangan/3DHumanGAN", + "web_page": null, + "github_page": "https://3dhumangan.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_3DHumanGAN_3D-Aware_Human_Image_Generation_with_3D_Pose_Mapping_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.07378", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "-bUNfhNYj24", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "MODA: Mapping-Once Audio-Driven Portrait Animation with Dual Attentions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://liuyunfei.net/projects/iccv23-moda/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_MODA_Mapping-Once_Audio-driven_Portrait_Animation_with_Dual_Attentions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10008", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "VO6m49VC3zw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Minimum Latency Deep Online Video Stabilization", + "base_url": null, + "title_page": null, + "github": "liuzhen03/NNDVS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Minimum_Latency_Deep_Online_Video_Stabilization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.02073", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "StableVideo: Text-Driven Consistency-Aware Diffusion Video Editing", + "base_url": null, + "title_page": null, + "github": "rese1f/StableVideo", + "web_page": null, + "github_page": "https://rese1f.github.io/StableVideo/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chai_StableVideo_Text-driven_Consistency-aware_Diffusion_Video_Editing_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09592", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "qKs09aX1AJM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Localizing Object-Level Shape Variations with Text-to-Image Diffusion Models", + "base_url": null, + "title_page": null, + "github": "orpatashnik/local-prompt-mixing", + "web_page": null, + "github_page": "https://orpatashnik.github.io/local-prompt-mixing/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Patashnik_Localizing_Object-Level_Shape_Variations_with_Text-to-Image_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11306", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation", + "base_url": null, + "title_page": null, + "github": "harlanhong/ICCV2023-MCNET", + "web_page": null, + "github_page": "https://harlanhong.github.io/publications/mcnet.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hong_Implicit_Identity_Representation_Conditioned_Memory_Compensation_Network_for_Talking_Head_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09906", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "ESSAformer: Efficient Transformer for Hyperspectral Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "Rexzhan/ESSAformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_ESSAformer_Efficient_Transformer_for_Hyperspectral_Image_Super-resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14010", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "GlueGen: Plug and Play Multi-Modal Encoders for X-to-Image Generation", + "base_url": null, + "title_page": null, + "github": "salesforce/GlueGen", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qin_GlueGen_Plug_and_Play_Multi-modal_Encoders_for_X-to-image_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10056", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "UHDNeRF: Ultra-High-Definition Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_UHDNeRF_Ultra-High-Definition_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "All-to-Key Attention for Arbitrary Style Transfer", + "base_url": null, + "title_page": null, + "github": "LearningHx/StyA2K", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_All-to-Key_Attention_for_Arbitrary_Style_Transfer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.04105", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Diverse Inpainting and Editing with GAN Inversion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yildirim_Diverse_Inpainting_and_Editing_with_GAN_Inversion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15033", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "C9L_4jPNi7k", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution", + "base_url": null, + "title_page": null, + "github": "sichun233746/MoTIF", + "web_page": null, + "github_page": "https://sichun233746.github.io/MoTIF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_MoTIF_Learning_Motion_Trajectories_with_Local_Implicit_Neural_Functions_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07988", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "RANA: Relightable Articulated Neural Avatars", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://nvlabs.github.io/RANA/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Iqbal_RANA_Relightable_Articulated_Neural_Avatars_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.03237", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "s-hIhIMjPqQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "DiffCloth: Diffusion based Garment Synthesis and Manipulation via Structural Cross-Modal Semantic Alignment", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_DiffCloth_Diffusion_Based_Garment_Synthesis_and_Manipulation_via_Structural_Cross-modal_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11206", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Masked Diffusion Transformer is a Strong Image Synthesizer", + "base_url": null, + "title_page": null, + "github": "sail-sg/MDT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/shgao/MDT", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_Masked_Diffusion_Transformer_is_a_Strong_Image_Synthesizer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14389", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model", + "base_url": null, + "title_page": null, + "github": "vvictoryuki/FreeDoM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_FreeDoM_Training-Free_Energy-Guided_Conditional_Diffusion_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09833", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "CLNeRF: Continual Learning Meets NeRF", + "base_url": null, + "title_page": null, + "github": "IntelLabs/CLNeRF", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_CLNeRF_Continual_Learning_Meets_NeRF_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "nLRt6OoDGq0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Rethinking Fast Fourier Convolution in Image Inpainting", + "base_url": null, + "title_page": null, + "github": "1911cty/Unbiased-Fast-Fourier-Convolution", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chu_Rethinking_Fast_Fourier_Convolution_in_Image_Inpainting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Pix2Video: Video Editing using Image Diffusion", + "base_url": null, + "title_page": null, + "github": "duyguceylan/pix2video", + "web_page": null, + "github_page": "https://duyguceylan.github.io/pix2video.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ceylan_Pix2Video_Video_Editing_using_Image_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12688", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Multi-View Spectral Polarization Propagation for Video Glass Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qiao_Multi-view_Spectral_Polarization_Propagation_for_Video_Glass_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction", + "base_url": null, + "title_page": null, + "github": "16lemoing/waldo", + "web_page": null, + "github_page": "https://16lemoing.github.io/waldo/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Le_Moing_WALDO_Future_Video_Synthesis_Using_Object_Layer_Decomposition_and_Parametric_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.14308", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Ray Conditioning: Trading Photo-Consistency for Photo-Realism in Multi-View Image Generation", + "base_url": null, + "title_page": null, + "github": "echen01/ray-conditioning", + "web_page": null, + "github_page": "https://ray-cond.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Ray_Conditioning_Trading_Photo-consistency_for_Photo-realism_in_Multi-view_Image_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.13681", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "S88qmycnOJA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Text-Conditioned_Sampling_Framework_for_Text-to-Image_Generation_with_Masked_Generative_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01515", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + }, + { + "title": "Efficient Video Prediction via Sparsely Conditioned Flow Matching", + "base_url": null, + "title_page": null, + "github": "araachie/river", + "web_page": null, + "github_page": "https://araachie.github.io/river/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Davtyan_Efficient_Video_Prediction_via_Sparsely_Conditioned_Flow_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.14575", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Image and Video Synthesis" + } +] \ No newline at end of file diff --git a/json_data/2023/main/low-level-and-physics-based-vision.json b/json_data/2023/main/low-level-and-physics-based-vision.json new file mode 100644 index 0000000..5a01a21 --- /dev/null +++ b/json_data/2023/main/low-level-and-physics-based-vision.json @@ -0,0 +1,3107 @@ +[ + { + "title": "Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection", + "base_url": null, + "title_page": null, + "github": "xyfJASON/HCL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_Hierarchical_Contrastive_Learning_for_Pattern-Generalizable_Image_Corruption_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14061", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration", + "base_url": null, + "title_page": null, + "github": "miaoyuchun/DDS2M", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Miao_DDS2M_Self-Supervised_Denoising_Diffusion_Spatio-Spectral_Model_for_Hyperspectral_Image_Restoration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06682", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "From Sky to the Ground: A Large-Scale Benchmark and Simple Baseline Towards Real Rain Removal", + "base_url": null, + "title_page": null, + "github": "yunguo224/LHP-Rain", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_From_Sky_to_the_Ground_A_Large-scale_Benchmark_and_Simple_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03867", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "VAPCNet: Viewpoint-Aware 3D Point Cloud Completion", + "base_url": null, + "title_page": null, + "github": "FZH92128/VAPCNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fu_VAPCNet_Viewpoint-Aware_3D_Point_Cloud_Completion_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "AccFlow: Backward Accumulation for Long-Range Optical Flow", + "base_url": null, + "title_page": null, + "github": "mulns/AccFlow", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_AccFlow_Backward_Accumulation_for_Long-Range_Optical_Flow_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13133", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints", + "base_url": null, + "title_page": null, + "github": "ewrfcas/CasMTR", + "web_page": null, + "github_page": "https://ewrfcas.github.io/CasMTR/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Improving_Transformer-based_Image_Matching_by_Cascaded_Capturing_Spatially_Informative_Keypoints_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.02885", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Low-Light_Image_Enhancement_with_Multi-Stage_Residue_Quantization_and_Brightness-Aware_Attention_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Random Sub-Samples Generation for Self-Supervised Real Image Denoising", + "base_url": null, + "title_page": null, + "github": "p1y2z3/SDAP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pan_Random_Sub-Samples_Generation_for_Self-Supervised_Real_Image_Denoising_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16825", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters", + "base_url": null, + "title_page": null, + "github": "Vicky0522/RSFNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ouyang_RSFNet_A_White-Box_Image_Retouching_Approach_using_Region-Specific_Color_Filters_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08682", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Physics-Driven Turbulence Image Restoration with Stochastic Refinement", + "base_url": null, + "title_page": null, + "github": "VITA-Group/PiRN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jaiswal_Physics-Driven_Turbulence_Image_Restoration_with_Stochastic_Refinement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10603", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-Time Performance on Mobile Device", + "base_url": null, + "title_page": null, + "github": "sanechips-multimedia/syenet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gou_SYENet_A_Simple_Yet_Effective_Network_for_Multiple_Low-Level_Vision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08137", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Self-Supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network", + "base_url": null, + "title_page": null, + "github": "jyicu/CBSN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jang_Self-supervised_Image_Denoising_with_Downsampled_Invariance_Loss_and_Conditional_Blind-Spot_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.09507", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Variational Degeneration to Structural Refinement: A Unified Framework for Superimposed Image Decomposition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Variational_Degeneration_to_Structural_Refinement_A_Unified_Framework_for_Superimposed_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Reconstructed Convolution Module based Look-Up Tables for Efficient Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "liuguandu/RC-LUT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Reconstructed_Convolution_Module_Based_Look-Up_Tables_for_Efficient_Image_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08544", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Self-Supervised Pre-Training for Mirror Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://jiaying.link/iccv2023-sslmirror/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Self-supervised_Pre-training_for_Mirror_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Downscaled_Representation_Matters_Improving_Image_Rescaling_with_Collaborative_Downscaled_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.10643", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Self-Supervised Monocular Underwater Depth Recovery, Image Restoration, and a Real-Sea Video Dataset", + "base_url": null, + "title_page": null, + "github": "nishavarghese15/DRUVA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Varghese_Self-supervised_Monocular_Underwater_Depth_Recovery_Image_Restoration_and_a_Real-sea_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Rethinking Video Frame Interpolation from Shutter mode Induced Degradation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ji_Rethinking_Video_Frame_Interpolation_from_Shutter_Mode_Induced_Degradation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Single Image Deblurring with Row-Dependent Blur Magnitude", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ji_Single_Image_Deblurring_with_Row-dependent_Blur_Magnitude_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Multi-View Self-Supervised Disentanglement for General Image Denoising", + "base_url": null, + "title_page": null, + "github": "chqwer2/Multi-view-Self-supervised-Disentanglement-Denoising", + "web_page": null, + "github_page": "https://chqwer2.github.io/MeD/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Multi-view_Self-supervised_Disentanglement_for_General_Image_Denoising_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05049", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Joint Demosaicing and Deghosting of Time-Varying Exposures for Single-Shot HDR Imaging", + "base_url": null, + "title_page": null, + "github": "KAIST-VCLAB/singshot-hdr-demosaicing", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Joint_Demosaicing_and_Deghosting_of_Time-Varying_Exposures_for_Single-Shot_HDR_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "hia_StKdow4", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Diff-Retinex: Rethinking Low-Light Image Enhancement with a Generative Diffusion Model", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yi_Diff-Retinex_Rethinking_Low-light_Image_Enhancement_with_A_Generative_Diffusion_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13164", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Dual Aggregation Transformer for Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "zhengchen1999/DAT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Dual_Aggregation_Transformer_for_Image_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03364", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Video Object Segmentation-Aware Video Frame Interpolation", + "base_url": null, + "title_page": null, + "github": "junsang7777/VOS-VFI", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yoo_Video_Object_Segmentation-aware_Video_Frame_Interpolation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image", + "base_url": null, + "title_page": null, + "github": "jackzou233/RawHDR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zou_RawHDR_High_Dynamic_Range_Image_Reconstruction_from_a_Single_Raw_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02020", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Multi-Scale Residual Low-Pass Filter Network for Image Deblurring", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Multi-Scale_Residual_Low-Pass_Filter_Network_for_Image_Deblurring_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Indoor Depth Recovery based on Deep Unfolding with Non-Local Prior", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dai_Indoor_Depth_Recovery_Based_on_Deep_Unfolding_with_Non-Local_Prior_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Learning Correction Filter via Degradation-Adaptive Regression for Blind Single Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "edbca/DARSR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Learning_Correction_Filter_via_Degradation-Adaptive_Regression_for_Blind_Single_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "ZhengyuLiang24/EPIT", + "web_page": null, + "github_page": "https://zhengyuliang24.github.io/EPIT/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_Learning_Non-Local_Spatial-Angular_Correlation_for_Light_Field_Image_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.08058", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Both Diverse and Realism Matter: Physical Attribute and Style Alignment for Rainy Image Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Both_Diverse_and_Realism_Matter_Physical_Attribute_and_Style_Alignment_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Learned Image Reasoning Prior Penetrates Deep Unfolding Network for Panchromatic and Multi-Spectral Image Fusion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Learned_Image_Reasoning_Prior_Penetrates_Deep_Unfolding_Network_for_Panchromatic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16083", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior", + "base_url": null, + "title_page": null, + "github": "YilinLiu97/FasterDIP-devil-in-upsampling", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_The_Devil_is_in_the_Upsampling_Architectural_Decisions_Made_Simpler_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.11409", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "SimFIR: A Simple Framework for Fisheye Image Rectification with Self-Supervised Representation Learning", + "base_url": null, + "title_page": null, + "github": "fh2019ustc/SimFIR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_SimFIR_A_Simple_Framework_for_Fisheye_Image_Rectification_with_Self-supervised_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09040", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Exploring Temporal Frequency Spectrum in Deep Video Deblurring", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Exploring_Temporal_Frequency_Spectrum_in_Deep_Video_Deblurring_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "ExposureDiffusion: Learning to Expose for Low-Light Image Enhancement", + "base_url": null, + "title_page": null, + "github": "wyf0912/ExposureDiffusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_ExposureDiffusion_Learning_to_Expose_for_Low-light_Image_Enhancement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07710", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "High-Resolution Document Shadow Removal via a Large-Scale Real-World Dataset and a Frequency-Aware Shadow Erasing Net", + "base_url": null, + "title_page": null, + "github": "CXH-Research/DocShadow-SD7K", + "web_page": null, + "github_page": "https://cxh-research.github.io/DocShadow-SD7K/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_High-Resolution_Document_Shadow_Removal_via_A_Large-Scale_Real-World_Dataset_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14221", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Towards Saner Deep Image Registration", + "base_url": null, + "title_page": null, + "github": "tuffr5/Saner-deep-registration", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Duan_Towards_Saner_Deep_Image_Registration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09696", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "VideoFlow: Exploiting Temporal Cues for Multi-Frame Optical Flow Estimation", + "base_url": null, + "title_page": null, + "github": "XiaoyuShi97/VideoFlow", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_VideoFlow_Exploiting_Temporal_Cues_for_Multi-frame_Optical_Flow_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08340", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Scene Matters: Model-based Deep Video Compression", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_Scene_Matters_Model-based_Deep_Video_Compression_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.04557", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Non-Coaxial Event-Guided Motion Deblurring with Spatial Alignment", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://sites.google.com/view/neid2023", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cho_Non-Coaxial_Event-Guided_Motion_Deblurring_with_Spatial_Alignment_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Retinexformer: One-Stage Retinex-based Transformer for Low-Light Image Enhancement", + "base_url": null, + "title_page": null, + "github": "caiyuanhao1998/Retinexformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_Retinexformer_One-stage_Retinex-based_Transformer_for_Low-light_Image_Enhancement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06705", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Feature Modulation Transformer: Cross-Refinement of Global Representation via High-Frequency Prior for Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "AVC2-UESTC/CRAFT-SR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Feature_Modulation_Transformer_Cross-Refinement_of_Global_Representation_via_High-Frequency_Prior_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05022", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "MVPSNet: Fast Generalizable Multi-View Photometric Stereo", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_MVPSNet_Fast_Generalizable_Multi-view_Photometric_Stereo_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.11167", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "FSI: Frequency and Spatial Interactive Learning for Image Restoration in Under-Display Cameras", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_FSI_Frequency_and_Spatial_Interactive_Learning_for_Image_Restoration_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution", + "base_url": null, + "title_page": null, + "github": "Zhaozixiang1228/GDSR-SSDNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Spherical_Space_Feature_Decomposition_for_Guided_Depth_Map_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08942", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Empowering Low-Light Image Enhancer through Customized Learnable Priors", + "base_url": null, + "title_page": null, + "github": "zheng980629/CUE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Empowering_Low-Light_Image_Enhancer_through_Customized_Learnable_Priors_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01958", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Learning Image Harmonization in the Linear Color Space", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Learning_Image_Harmonization_in_the_Linear_Color_Space_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Under-Display Camera Image Restoration with Scattering Effect", + "base_url": null, + "title_page": null, + "github": "NamecantbeNULL/SRUDC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_Under-Display_Camera_Image_Restoration_with_Scattering_Effect_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04163", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "Jiamian-Wang/Iterative-Soft-Shrinkage-SR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Iterative_Soft_Shrinkage_Learning_for_Efficient_Image_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09650", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Single Image Defocus Deblurring via Implicit Neural Inverse Kernels", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Quan_Single_Image_Defocus_Deblurring_via_Implicit_Neural_Inverse_Kernels_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Degradation-Resistant Unfolding Network for Heterogeneous Image Fusion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_Degradation-Resistant_Unfolding_Network_for_Heterogeneous_Image_Fusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Graphics2RAW: Mapping Computer Graphics Images to Sensor RAW Images", + "base_url": null, + "title_page": null, + "github": "SamsungLabs/graphics2raw", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Seo_Graphics2RAW_Mapping_Computer_Graphics_Images_to_Sensor_RAW_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Lighting up NeRF via Unsupervised Decomposition and Enhancement", + "base_url": null, + "title_page": null, + "github": "onpix/LLNeRF", + "web_page": "https://www.whyy.site/paper/llnerf", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Lighting_up_NeRF_via_Unsupervised_Decomposition_and_Enhancement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10664", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches", + "base_url": null, + "title_page": null, + "github": "linxin0/SCPGabNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Unsupervised_Image_Denoising_in_Real-World_Scenarios_via_Self-Collaboration_Parallel_Generative_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06776", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Adverse Weather Removal with Codebook Priors", + "base_url": null, + "title_page": null, + "github": "Owen718/AWRCP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_Adverse_Weather_Removal_with_Codebook_Priors_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "MSRA-SR: Image Super-Resolution Transformer with Multi-Scale Shared Representation Acquisition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_MSRA-SR_Image_Super-resolution_Transformer_with_Multi-scale_Shared_Representation_Acquisition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Deep Video Demoiréing via Compact Invertible Dyadic Decomposition", + "base_url": null, + "title_page": null, + "github": "RuotaoXu/CIDNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Quan_Deep_Video_Demoireing_via_Compact_Invertible_Dyadic_Decomposition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "SILT: Shadow-Aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels", + "base_url": null, + "title_page": null, + "github": "Cralence/SILT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_SILT_Shadow-Aware_Iterative_Label_Tuning_for_Learning_to_Detect_Shadows_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12064", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Innovating Real Fisheye Image Correction with Dual Diffusion Architecture", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Innovating_Real_Fisheye_Image_Correction_with_Dual_Diffusion_Architecture_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Adaptive Illumination Mapping for Shadow Detection in Raw Images", + "base_url": null, + "title_page": null, + "github": "jiayusun/SARA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Adaptive_Illumination_Mapping_for_Shadow_Detection_in_Raw_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "GEDepth: Ground Embedding for Monocular Depth Estimation", + "base_url": null, + "title_page": null, + "github": "qcraftai/gedepth", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_GEDepth_Ground_Embedding_for_Monocular_Depth_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.09975", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Lightweight Image Super-Resolution with Superpixel Token Interaction", + "base_url": null, + "title_page": null, + "github": "ArcticHare105/SPIN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Lightweight_Image_Super-Resolution_with_Superpixel_Token_Interaction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Unfolding Framework with Prior of Convolution-Transformer Mixture and Uncertainty Estimation for Video Snapshot Compressive Imaging", + "base_url": null, + "title_page": null, + "github": "zsm1211/CTM-SCI", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Unfolding_Framework_with_Prior_of_Convolution-Transformer_Mixture_and_Uncertainty_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.11316", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Efficient_Unified_Demosaicing_for_Bayer_and_Non-Bayer_Patterned_Image_Sensors_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10667", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction", + "base_url": null, + "title_page": null, + "github": "haesoochung/LAN-HDR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chung_LAN-HDR_Luminance-based_Alignment_Network_for_High_Dynamic_Range_Video_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11116", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Fine-Grained Visible Watermark Removal", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Niu_Fine-grained_Visible_Watermark_Removal_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "SRFormer: Permuted Self-Attention for Single Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "HVision-NKU/SRFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_SRFormer_Permuted_Self-Attention_for_Single_Image_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09735", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "NeonLeexiang/DLGSANet", + "web_page": null, + "github_page": "https://neonleexiang.github.io/DLGSANet/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_DLGSANet_Lightweight_Dynamic_Local_and_Global_Self-Attention_Networks_for_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.02031", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing", + "base_url": null, + "title_page": null, + "github": "FVL2020/ICCV-2023-MB-TaylorFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qiu_MB-TaylorFormer_Multi-Branch_Efficient_Transformer_Expanded_by_Taylor_Formula_for_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14036", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Multi-Frequency Representation Enhancement with Privilege Information for Video Super-Resolution", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Multi-Frequency_Representation_Enhancement_with_Privilege_Information_for_Video_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "COMPASS: High-Efficiency Deep Image Compression with Arbitrary-Scale Spatial Scalability", + "base_url": null, + "title_page": null, + "github": "ImJongminPark/COMPASS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_COMPASS_High-Efficiency_Deep_Image_Compression_with_Arbitrary-scale_Spatial_Scalability_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.07926", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Zfo3f__suwQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Alignment-Free HDR Deghosting with Semantics Consistent Transformer", + "base_url": null, + "title_page": null, + "github": "Zongwei97/SCTNet", + "web_page": null, + "github_page": "https://steven-tel.github.io/sctnet/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tel_Alignment-free_HDR_Deghosting_with_Semantics_Consistent_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.18135", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection", + "base_url": null, + "title_page": null, + "github": "uzh-rpg/event_representation_study", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zubic_From_Chaos_Comes_Order_Ordering_Event_Representations_for_Object_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.13455", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Data", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fu_Towards_High-Quality_Specular_Highlight_Removal_by_Leveraging_Large-Scale_Synthetic_Data_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.06302", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yoshimura_DynamicISP_Dynamically_Controlled_Image_Signal_Processor_for_Image_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.01146", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Dancing in the Dark: A Benchmark towards General Low-Light Video Enhancement", + "base_url": null, + "title_page": null, + "github": "ciki000/DID", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fu_Dancing_in_the_Dark_A_Benchmark_towards_General_Low-light_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Dec-Adapter: Exploring Efficient Decoder-Side Adapter for Bridging Screen Content and Natural Image Compression", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shen_Dec-Adapter_Exploring_Efficient_Decoder-Side_Adapter_for_Bridging_Screen_Content_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://vlislab22.github.io/OmniZoomer/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_OmniZoomer_Learning_to_Move_and_Zoom_in_on_Sphere_at_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08114", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Pyramid Dual Domain Injection Network for Pan-Sharpening", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_Pyramid_Dual_Domain_Injection_Network_for_Pan-sharpening_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Implicit Neural Representation for Cooperative Low-Light Image Enhancement", + "base_url": null, + "title_page": null, + "github": "Ysz2022/NeRCo", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Implicit_Neural_Representation_for_Cooperative_Low-light_Image_Enhancement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11722", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Physically-Plausible Illumination Distribution Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ershov_Physically-Plausible_Illumination_Distribution_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoising", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_Score_Priors_Guided_Deep_Variational_Inference_for_Unsupervised_Real-World_Single_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04682", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Semantic-Aware Dynamic Parameter for Video Inpainting Transformer", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Semantic-Aware_Dynamic_Parameter_for_Video_Inpainting_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction", + "base_url": null, + "title_page": null, + "github": "MyuLi/PADUT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Pixel_Adaptive_Deep_Unfolding_Transformer_for_Hyperspectral_Image_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10820", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery", + "base_url": null, + "title_page": null, + "github": "YuyanZhou1/Improving-Lens-Flare-Removal", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Improving_Lens_Flare_Removal_with_General-Purpose_Pipeline_and_Multiple_Light_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16460", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionary", + "base_url": null, + "title_page": null, + "github": "lilala0/RFD-ECNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_RFD-ECNet_Extreme_Underwater_Image_Compression_with_Reference_to_Feature_Dictionary_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08721", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction", + "base_url": null, + "title_page": null, + "github": "skchen1993/2023_CEVR", + "web_page": null, + "github_page": "https://skchen1993.github.io/CEVR_web/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Learning_Continuous_Exposure_Value_Representations_for_Single-Image_HDR_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03900", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Az8W2lGegcg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Focal Network for Image Restoration", + "base_url": null, + "title_page": null, + "github": "c-yn/FocalNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cui_Focal_Network_for_Image_Restoration_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "CIRI: Curricular Inactivation for Residue-Aware One-Shot Video Inpainting", + "base_url": null, + "title_page": null, + "github": "Arise-zwy/CIRI", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_CIRI_Curricular_Inactivation_for_Residue-aware_One-shot_Video_Inpainting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Wc4ddkPCFlY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition", + "base_url": null, + "title_page": null, + "github": "liuxiaoyu1104/UNIC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Beyond_Image_Borders_Learning_Feature_Extrapolation_for_Unbounded_Image_Composition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.12042", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces", + "base_url": null, + "title_page": null, + "github": "yinzhicun/MetaF2N", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yin_MetaF2N_Blind_Image_Super-Resolution_by_Learning_Efficient_Model_Adaptation_from_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08113", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Boundary-Aware Divide and Conquer: A Diffusion-based Solution for Unsupervised Shadow Removal", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Boundary-Aware_Divide_and_Conquer_A_Diffusion-Based_Solution_for_Unsupervised_Shadow_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Leveraging Inpainting for Single-Image Shadow Removal", + "base_url": null, + "title_page": null, + "github": "tsingqguo/inpaint4shadow", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Leveraging_Inpainting_for_Single-Image_Shadow_Removal_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.05361", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Hybrid Spectral Denoising Transformer with Guided Attention", + "base_url": null, + "title_page": null, + "github": "Zeqiang-Lai/HSDT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lai_Hybrid_Spectral_Denoising_Transformer_with_Guided_Attention_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09040", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Examining Autoexposure for Challenging Scenes", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tedla_Examining_Autoexposure_for_Challenging_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04542", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "ZeHqNPD1UXg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Self-Supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive", + "base_url": null, + "title_page": null, + "github": "shangwei5/SelfDRSC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shang_Self-supervised_Learning_to_Bring_Dual_Reversed_Rolling_Shutter_Images_Alive_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.19862", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "rRjaL9k2u44", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "DiffIR: Efficient Diffusion Model for Image Restoration", + "base_url": null, + "title_page": null, + "github": "Zj-BinXia/DiffIR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xia_DiffIR_Efficient_Diffusion_Model_for_Image_Restoration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09472", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks", + "base_url": null, + "title_page": null, + "github": "Ephemeral182/UDR-S2Former_deraining", + "web_page": null, + "github_page": "https://ephemeral182.github.io/UDR_S2Former_deraining/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Sparse_Sampling_Transformer_with_Uncertainty-Driven_Ranking_for_Unified_Removal_of_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14153", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution", + "base_url": null, + "title_page": null, + "github": "wdmwhh/MRefSR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_LMR_A_Large-Scale_Multi-Reference_Dataset_for_Reference-Based_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.04970", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Low-Light_Image_Enhancement_with_Illumination-Aware_Gamma_Correction_and_Complete_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08220", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Single Image Reflection Separation via Component Synergy", + "base_url": null, + "title_page": null, + "github": "mingcv/DSRNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_Single_Image_Reflection_Separation_via_Component_Synergy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10027", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Learning Rain Location Prior for Nighttime Deraining", + "base_url": null, + "title_page": null, + "github": "zkawfanx/RLP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Learning_Rain_Location_Prior_for_Nighttime_Deraining_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Exploring Positional Characteristics of Dual-Pixel Data for Camera Autofocus", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Choi_Exploring_Positional_Characteristics_of_Dual-Pixel_Data_for_Camera_Autofocus_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Continuously Masked Transformer for Image Inpainting", + "base_url": null, + "title_page": null, + "github": "keunsoo-ko/CMT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ko_Continuously_Masked_Transformer_for_Image_Inpainting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution", + "base_url": null, + "title_page": null, + "github": "researchmm/VQD-SR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tuo_Learning_Data-Driven_Vector-Quantized_Degradation_Model_for_Animation_Video_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09826", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution", + "base_url": null, + "title_page": null, + "github": "sunny2109/SAFMN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Spatially-Adaptive_Feature_Modulation_for_Efficient_Image_Super-Resolution_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.13800", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation", + "base_url": null, + "title_page": null, + "github": "scott-yjyang/ViWS-Net", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Video_Adverse-Weather-Component_Suppression_Network_via_Weather_Messenger_and_Adversarial_Backpropagation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.13700", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Snow Removal in Video: A New Dataset and a Novel Method", + "base_url": null, + "title_page": null, + "github": "haoyuc/VideoDesnowing", + "web_page": null, + "github_page": "https://haoyuchen.com/VideoDesnowing", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Snow_Removal_in_Video_A_New_Dataset_and_A_Novel_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Boosting Single Image Super-Resolution via Partial Channel Shifting", + "base_url": null, + "title_page": null, + "github": "OwXiaoM/PCS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Boosting_Single_Image_Super-Resolution_via_Partial_Channel_Shifting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Towards Real-World Burst Image Super-Resolution: Benchmark and Method", + "base_url": null, + "title_page": null, + "github": "yjsunnn/FBANet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Towards_Real-World_Burst_Image_Super-Resolution_Benchmark_and_Method_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04803", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvement", + "base_url": null, + "title_page": null, + "github": "Luciennnnnnn/DualFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_On_the_Effectiveness_of_Spectral_Discriminators_for_Perceptual_Quality_Improvement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12027", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "q3LPOeCi6sc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "E2NeRF: Event Enhanced Neural Radiance Fields from Blurry Images", + "base_url": null, + "title_page": null, + "github": "iCVTEAM/E2NeRF", + "web_page": null, + "github_page": "https://icvteam.github.io/E2NeRF.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qi_E2NeRF_Event_Enhanced_Neural_Radiance_Fields_from_Blurry_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "EvTHcLFX8yY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Iterative Denoiser and Noise Estimator for Self-Supervised Image Denoising", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zou_Iterative_Denoiser_and_Noise_Estimator_for_Self-Supervised_Image_Denoising_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising", + "base_url": null, + "title_page": null, + "github": "Srameo/LED", + "web_page": null, + "github_page": "https://srameo.github.io/projects/led-iccv23/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jin_Lighting_Every_Darkness_in_Two_Pairs_A_Calibration-Free_Pipeline_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03448", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Jo8OTAnUYkU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + }, + { + "title": "Fingerprinting Deep Image Restoration Models", + "base_url": null, + "title_page": null, + "github": "painfulloop/Fingerprinting_IR_DNNs", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Quan_Fingerprinting_Deep_Image_Restoration_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level and Physics-based Vision" + } +] \ No newline at end of file diff --git a/json_data/2023/main/low-level-vision-and-theory.json b/json_data/2023/main/low-level-vision-and-theory.json new file mode 100644 index 0000000..68aede7 --- /dev/null +++ b/json_data/2023/main/low-level-vision-and-theory.json @@ -0,0 +1,326 @@ +[ + { + "title": "A 5-Point Minimal Solver for Event Camera Relative Motion Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://mgaoling.github.io/eventail/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_A_5-Point_Minimal_Solver_for_Event_Camera_Relative_Motion_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "hyfGGzZQZh4", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "General Planar Motion from a Pair of 3D Correspondences", + "base_url": null, + "title_page": null, + "github": "jdibenes/gpm", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dibene_General_Planar_Motion_from_a_Pair_of_3D_Correspondences_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "Beyond the Pixel: A Photometrically Calibrated HDR Dataset for Luminance and Color Prediction", + "base_url": null, + "title_page": null, + "github": "lvsn/beyondthepixel", + "web_page": null, + "github_page": "https://lvsn.github.io/beyondthepixel/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bolduc_Beyond_the_Pixel_a_Photometrically_Calibrated_HDR_Dataset_for_Luminance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.12372", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion", + "base_url": null, + "title_page": null, + "github": "Zhaozixiang1228/MMIF-DDFM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DDFM_Denoising_Diffusion_Model_for_Multi-Modality_Image_Fusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06840", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "Iterative Prompt Learning for Unsupervised Backlit Image Enhancement", + "base_url": null, + "title_page": null, + "github": "ZhexinLiang/CLIP-LIT", + "web_page": null, + "github_page": "https://zhexinliang.github.io/CLIP_LIT_page/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_Iterative_Prompt_Learning_for_Unsupervised_Backlit_Image_Enhancement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17569", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "0qbkxNmkNWU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "Red-Fairy/ZeroShotDayNightDA", + "web_page": null, + "github_page": "https://red-fairy.github.io/ZeroShotDayNightDA-Webpage/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_Similarity_Min-Max_Zero-Shot_Day-Night_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08779", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "_Urw6HBjzAk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "Multi-Interactive Feature Learning and a Full-Time Multi-Modality Benchmark for Image Fusion and Segmentation", + "base_url": null, + "title_page": null, + "github": "JinyuanLiu-CV/SegMiF", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Multi-interactive_Feature_Learning_and_a_Full-time_Multi-modality_Benchmark_for_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.02097", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "Computational 3D Imaging with Position Sensors", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Klotz_Computational_3D_Imaging_with_Position_Sensors_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "pL2puwXOY9c", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "Passive Ultra-Wideband Single-Photon Imaging", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://www.dgp.toronto.edu/projects/ultra-wideband/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Passive_Ultra-Wideband_Single-Photon_Imaging_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "Viewing Graph Solvability in Practice", + "base_url": null, + "title_page": null, + "github": "federica-arrigoni/finite-solvability", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Arrigoni_Viewing_Graph_Solvability_in_Practice_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "Minimal Solutions to Generalized Three-View Relative Pose Problem", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ding_Minimal_Solutions_to_Generalized_Three-View_Relative_Pose_Problem_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + }, + { + "title": "SoDaCam: Software-Defined Cameras via Single-Photon Imaging", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://wisionlab.com/project/sodacam/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sundar_SoDaCam_Software-defined_Cameras_via_Single-Photon_Imaging_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.00066", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Low-Level Vision and Theory" + } +] \ No newline at end of file diff --git a/json_data/2023/main/machine-learning-and-dataset.json b/json_data/2023/main/machine-learning-and-dataset.json new file mode 100644 index 0000000..f912092 --- /dev/null +++ b/json_data/2023/main/machine-learning-and-dataset.json @@ -0,0 +1,326 @@ +[ + { + "title": "DiffusionDet: Diffusion Model for Object Detection", + "base_url": null, + "title_page": null, + "github": "ShoufaChen/DiffusionDet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_DiffusionDet_Diffusion_Model_for_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.09788", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "V3Det: Vast Vocabulary Visual Detection Dataset", + "base_url": null, + "title_page": null, + "github": "V3Det/V3Det", + "web_page": "https://v3det.openxlab.org.cn/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_V3Det_Vast_Vocabulary_Visual_Detection_Dataset_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.03752", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking", + "base_url": null, + "title_page": null, + "github": "aharley/pips2", + "web_page": "https://pointodyssey.com/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_PointOdyssey_A_Large-Scale_Synthetic_Dataset_for_Long-Term_Point_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15055", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "BL-1nbA4G0M", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "Label-Free Event-based Object Recognition via Joint Learning with Image Reconstruction from Events", + "base_url": null, + "title_page": null, + "github": "Chohoonhee/Ev-LaFOR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cho_Label-Free_Event-based_Object_Recognition_via_Joint_Learning_with_Image_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09383", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "Vision HGNN: An Image is more than a Graph of Nodes", + "base_url": null, + "title_page": null, + "github": "VITA-Group/ViHGNN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_Vision_HGNN_An_Image_is_More_than_a_Graph_of_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "Revisiting Vision Transformer from the View of Path Ensemble", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chang_Revisiting_Vision_Transformer_from_the_View_of_Path_Ensemble_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06548", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "All in Tokens: Unifying Output Space of Visual Tasks via Soft Token", + "base_url": null, + "title_page": null, + "github": "SwinTransformer/AiT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ning_All_in_Tokens_Unifying_Output_Space_of_Visual_Tasks_via_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.02229", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground", + "base_url": null, + "title_page": null, + "github": "lihaoxin05/StillMix", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Mitigating_and_Evaluating_Static_Bias_of_Action_Representations_in_the_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.12883", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "tlYqLpLGVbU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "Deep Multitask Learning with Progressive Parameter Sharing", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_Deep_Multitask_Learning_with_Progressive_Parameter_Sharing_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "Implicit Temporal Modeling with Learnable Alignment for Video Recognition", + "base_url": null, + "title_page": null, + "github": "Francis-Rings/ILA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tu_Implicit_Temporal_Modeling_with_Learnable_Alignment_for_Video_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.10465", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "Unmasked Teacher: Towards Training-Efficient Video Foundation Models", + "base_url": null, + "title_page": null, + "github": "OpenGVLab/unmasked_teacher", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Unmasked_Teacher_Towards_Training-Efficient_Video_Foundation_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16058", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "pkTwHS36BmY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + }, + { + "title": "Large-Scale Person Detection and Localization using Overhead Fisheye Cameras", + "base_url": null, + "title_page": null, + "github": "BUPT-PRIV/LOAF", + "web_page": null, + "github_page": "https://loafisheye.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Large-Scale_Person_Detection_and_Localization_Using_Overhead_Fisheye_Cameras_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08252", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning and Dataset" + } +] \ No newline at end of file diff --git a/json_data/2023/main/machine-learning-other-than-deep-learning.json b/json_data/2023/main/machine-learning-other-than-deep-learning.json new file mode 100644 index 0000000..260bd36 --- /dev/null +++ b/json_data/2023/main/machine-learning-other-than-deep-learning.json @@ -0,0 +1,299 @@ +[ + { + "title": "Adaptive Calibrator Ensemble: Navigating Test Set Difficulty in Out-of-Distribution Scenarios", + "base_url": null, + "title_page": null, + "github": "insysgroup/Adaptive-Calibrator-Ensemble", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zou_Adaptive_Calibrator_Ensemble_Navigating_Test_Set_Difficulty_in_Out-of-Distribution_Scenarios_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + }, + { + "title": "Anchor Structure Regularization Induced Multi-View Subspace Clustering via Enhanced Tensor Rank Minimization", + "base_url": null, + "title_page": null, + "github": "smallsky-jjt/ASR-ETR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ji_Anchor_Structure_Regularization_Induced_Multi-view_Subspace_Clustering_via_Enhanced_Tensor_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + }, + { + "title": "Meta OOD Learning for Continuously Adaptive OOD Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Meta_OOD_Learning_For_Continuously_Adaptive_OOD_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11705", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + }, + { + "title": "Learning with Diversity: Self-Expanded Equalization for Better Generalized Deep Metric Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_Learning_with_Diversity_Self-Expanded_Equalization_for_Better_Generalized_Deep_Metric_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + }, + { + "title": "Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration", + "base_url": null, + "title_page": null, + "github": "kxzxvbk/Fling", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Bold_but_Cautious_Unlocking_the_Potential_of_Personalized_Federated_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11103", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + }, + { + "title": "Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones are Difficult to Beat", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_Federated_Learning_Over_Images_Vertical_Decompositions_and_Pre-Trained_Backbones_Are_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03237", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + }, + { + "title": "Towards Inadequately Pre-Trained Models in Transfer Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Deng_Towards_Inadequately_Pre-trained_Models_in_Transfer_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2203.04668", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + }, + { + "title": "Reducing Training Time in Cross-Silo Federated Learning using Multigraph Topology", + "base_url": null, + "title_page": null, + "github": "aioz-ai/MultigraphFL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Do_Reducing_Training_Time_in_Cross-Silo_Federated_Learning_Using_Multigraph_Topology_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2207.09657", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + }, + { + "title": "Membrane Potential Batch Normalization for Spiking Neural Networks", + "base_url": null, + "title_page": null, + "github": "yfguo91/MPBN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Membrane_Potential_Batch_Normalization_for_Spiking_Neural_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08359", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + }, + { + "title": "Revisit PCA-based Technique for Out-of-Distribution Detection", + "base_url": null, + "title_page": null, + "github": "SYSU-MIA-GROUP/pca-based-out-of-distribution-detection", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guan_Revisit_PCA-based_Technique_for_Out-of-Distribution_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + }, + { + "title": "Cross-View Topology based Consistent and Complementary Information for Deep Multi-View Clustering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Cross-view_Topology_Based_Consistent_and_Complementary_Information_for_Deep_Multi-view_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Machine Learning (other than Deep Learning)" + } +] \ No newline at end of file diff --git a/json_data/2023/main/medical-and-biological-vision-cell-microscopy.json b/json_data/2023/main/medical-and-biological-vision-cell-microscopy.json new file mode 100644 index 0000000..4c4596d --- /dev/null +++ b/json_data/2023/main/medical-and-biological-vision-cell-microscopy.json @@ -0,0 +1,1082 @@ +[ + { + "title": "CO-PILOT: Dynamic Top-Down Point Cloud with Conditional Neighborhood Aggregation for Multi-Gigapixel Histopathology Image Representation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nakhli_CO-PILOT_Dynamic_Top-Down_Point_Cloud_with_Conditional_Neighborhood_Aggregation_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "SKiT: A Fast Key Information Video Transformer for Online Surgical Phase Recognition", + "base_url": null, + "title_page": null, + "github": "MRUIL/SKiT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_SKiT_a_Fast_Key_Information_Video_Transformer_for_Online_Surgical_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "XNet: Wavelet-based Low and High Frequency Fusion Networks for Fully- and Semi-Supervised Semantic Segmentation of Biomedical Images", + "base_url": null, + "title_page": null, + "github": "Yanfeng-Zhou/XNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_XNet_Wavelet-Based_Low_and_High_Frequency_Fusion_Networks_for_Fully-_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Probabilistic Modeling of Inter- and Intra-Observer Variability in Medical Image Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Schmidt_Probabilistic_Modeling_of_Inter-_and_Intra-observer_Variability_in_Medical_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11397", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation", + "base_url": null, + "title_page": null, + "github": "liuxy1103/CRAC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Learning_Cross-Representation_Affinity_Consistency_for_Sparsely_Supervised_Biomedical_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Dual Meta-Learning with Longitudinally Consistent Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan", + "base_url": null, + "title_page": null, + "github": "ladderlab-xjtu/DuMeta", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Dual_Meta-Learning_with_Longitudinally_Consistent_Regularization_for_One-Shot_Brain_Tissue_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06774", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "BlindHarmony: \"Blind\" Harmonization for MR Images via Flow Model", + "base_url": null, + "title_page": null, + "github": "Hwihuni/BlindHarmony", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jeong_BlindHarmony_Blind_Harmonization_for_MR_Images_via_Flow_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.10732", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Continual Segment: Towards a Single, Unified and Non-Forgetting Continual Segmentation Model of 143 Whole-Body Organs in CT Scans", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ji_Continual_Segment_Towards_a_Single_Unified_and_Non-forgetting_Continual_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection", + "base_url": null, + "title_page": null, + "github": "ljwztc/CLIP-Driven-Universal-Model", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_CLIP-Driven_Universal_Model_for_Organ_Segmentation_and_Tumor_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.00785", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "D1pNk2z3aiQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "LIMITR: Leveraging Local Information for Medical Image-Text Representation", + "base_url": null, + "title_page": null, + "github": "gefend/LIMITR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dawidowicz_LIMITR_Leveraging_Local_Information_for_Medical_Image-Text_Representation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11755", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation", + "base_url": null, + "title_page": null, + "github": "camwew/TADA-MI", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_Taxonomy_Adaptive_Cross-Domain_Adaptation_in_Medical_Imaging_via_Optimization_Trajectory_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14709", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "CuNeRF: Cube-based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution", + "base_url": null, + "title_page": null, + "github": "NarcissusEx/CuNeRF", + "web_page": null, + "github_page": "https://narcissusex.github.io/CuNeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_CuNeRF_Cube-Based_Neural_Radiance_Field_for_Zero-Shot_Medical_Image_Arbitrary-Scale_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16242", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "6m1I88hGmYU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Learning to Distill Global Representation for Sparse-View CT", + "base_url": null, + "title_page": null, + "github": "longzilicart/GloReDi", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Learning_to_Distill_Global_Representation_for_Sparse-View_CT_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08463", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Preserving Tumor Volumes for Unsupervised Medical Image Registration", + "base_url": null, + "title_page": null, + "github": "dddraxxx/Medical-Reg-with-Volume-Preserving", + "web_page": null, + "github_page": "https://dddraxxx.github.io/Volume-Preserving-Registration/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Preserving_Tumor_Volumes_for_Unsupervised_Medical_Image_Registration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.10153", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "µSplit: Image Decomposition for Fluorescence Microscopy", + "base_url": null, + "title_page": null, + "github": "juglab/uSplit", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ashesh_uSplit_Image_Decomposition_for_Fluorescence_Microscopy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.12872", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Rethinking Multi-Contrast MRI Super-Resolution: Rectangle-Window Cross-Attention Transformer and Arbitrary-Scale Upsampling", + "base_url": null, + "title_page": null, + "github": "GuangYuanKK/McASSR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Rethinking_Multi-Contrast_MRI_Super-Resolution_Rectangle-Window_Cross-Attention_Transformer_and_Arbitrary-Scale_Upsampling_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction", + "base_url": null, + "title_page": null, + "github": "Innse/MOTCat", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Multimodal_Optimal_Transport-based_Co-Attention_Transformer_with_Global_Structure_Consistency_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.08330", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "4D Myocardium Reconstruction with Decoupled Motion and Shape Model", + "base_url": null, + "title_page": null, + "github": "yuan-xiaohan/4D-Myocardium-Reconstruction-with-Decoupled-Motion-and-Shape-Model", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yuan_4D_Myocardium_Reconstruction_with_Decoupled_Motion_and_Shape_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14083", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Unsupervised Learning of Object-Centric Embeddings for Cell Instance Segmentation in Microscopy Images", + "base_url": null, + "title_page": null, + "github": "funkelab/cellulus", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wolf_Unsupervised_Learning_of_Object-Centric_Embeddings_for_Cell_Instance_Segmentation_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.08501", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "LightDepth: Single-View Depth Self-Supervision from Illumination Decline", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rodriguez-Puigvert_LightDepth_Single-View_Depth_Self-Supervision_from_Illumination_Decline_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10525", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Jrzzy2JjOCQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "BoMD: Bag of Multi-Label Descriptors for Noisy Chest X-Ray Classification", + "base_url": null, + "title_page": null, + "github": "cyh-0/BoMD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_BoMD_Bag_of_Multi-label_Descriptors_for_Noisy_Chest_X-ray_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2203.01937", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Decomposition-based Variational Network for Multi-Contrast MRI Super-Resolution and Reconstruction", + "base_url": null, + "title_page": null, + "github": "lpcccc-cv/MC-VarNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lei_Decomposition-Based_Variational_Network_for_Multi-Contrast_MRI_Super-Resolution_and_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "TopoSeg: Topology-Aware Nuclear Instance Segmentation", + "base_url": null, + "title_page": null, + "github": "hhlisme/toposeg", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_TopoSeg_Topology-Aware_Nuclear_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Scratch Each Other's Back: Incomplete Multi-Modal Brain Tumor Segmentation via Category Aware Group Self-Support Learning", + "base_url": null, + "title_page": null, + "github": "qysgithubopen/GSS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qiu_Scratch_Each_Others_Back_Incomplete_Multi-Modal_Brain_Tumor_Segmentation_via_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers using a Large Collection of CT Scans", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_CancerUniT_Towards_a_Single_Unified_Model_for_Effective_Detection_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.12291", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Gram-based Attentive Neural Ordinary Differential Equations Network for Video Nystagmography Classification", + "base_url": null, + "title_page": null, + "github": "XiheQiu/Gram-AODE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qiu_Gram-based_Attentive_Neural_Ordinary_Differential_Equations_Network_for_Video_Nystagmography_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "ConSlide: Asynchronous Hierarchical Interaction Transformer with Breakup-Reorganize Rehearsal for Continual Whole Slide Image Analysis", + "base_url": null, + "title_page": null, + "github": "HKU-MedAI/ConSlide", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_ConSlide_Asynchronous_Hierarchical_Interaction_Transformer_with_Breakup-Reorganize_Rehearsal_for_Continual_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13324", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "PRIOR: Prototype Representation Joint Learning from Medical Images and Reports", + "base_url": null, + "title_page": null, + "github": "QtacierP/PRIOR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_PRIOR_Prototype_Representation_Joint_Learning_from_Medical_Images_and_Reports_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12577", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training for X-Ray Diagnosis", + "base_url": null, + "title_page": null, + "github": "MediaBrain-SJTU/MedKLIP", + "web_page": null, + "github_page": "https://chaoyi-wu.github.io/MedKLIP/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_MedKLIP_Medical_Knowledge_Enhanced_Language-Image_Pre-Training_for_X-ray_Diagnosis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.02228", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection", + "base_url": null, + "title_page": null, + "github": "LL3RD/ACFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Affine-Consistent_Transformer_for_Multi-Class_Cell_Nuclei_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.14154", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "A Skeletonization Algorithm for Gradient-based Optimization", + "base_url": null, + "title_page": null, + "github": "martinmenten/skeletonization-for-gradient-based-optimization", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Menten_A_Skeletonization_Algorithm_for_Gradient-Based_Optimization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02527", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Improving Representation Learning for Histopathologic Images with Cluster Constraints", + "base_url": null, + "title_page": null, + "github": "wwyi1828/CluSiam", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Improving_Representation_Learning_for_Histopathologic_Images_with_Cluster_Constraints_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.12334", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Enhancing Modality-Agnostic Representations via Meta-Learning for Brain Tumor Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Konwer_Enhancing_Modality-Agnostic_Representations_via_Meta-Learning_for_Brain_Tumor_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.04308", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "CauSSL: Causality-Inspired Semi-Supervised Learning for Medical Image Segmentation", + "base_url": null, + "title_page": null, + "github": "JuzhengMiao/CauSSL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Miao_CauSSL_Causality-inspired_Semi-supervised_Learning_for_Medical_Image_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "UniverSeg: Universal Medical Image Segmentation", + "base_url": null, + "title_page": null, + "github": "JJGO/UniverSeg", + "web_page": null, + "github_page": "https://universeg.csail.mit.edu/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Butoi_UniverSeg_Universal_Medical_Image_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06131", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "MRM: Masked Relation Modeling for Medical Image Pre-Training with Genetics", + "base_url": null, + "title_page": null, + "github": "CityU-AIM-Group/MRM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_MRM_Masked_Relation_Modeling_for_Medical_Image_Pre-Training_with_Genetics_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Boosting whole Slide Image Classification from the Perspectives of Distribution, Correlation and Magnification", + "base_url": null, + "title_page": null, + "github": "miccaiif/MILBooster", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qu_Boosting_Whole_Slide_Image_Classification_from_the_Perspectives_of_Distribution_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Adaptive Template Transformer for Mitochondria Segmentation in Electron Microscopy Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pan_Adaptive_Template_Transformer_for_Mitochondria_Segmentation_in_Electron_Microscopy_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "Cross-Modal Translation and Alignment for Survival Analysis", + "base_url": null, + "title_page": null, + "github": "FT-ZHOU-ZZZ/CMTA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Cross-Modal_Translation_and_Alignment_for_Survival_Analysis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.12855", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + }, + { + "title": "LNPL-MIL: Learning from Noisy Pseudo Labels for Promoting Multiple Instance Learning in whole Slide Image", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shao_LNPL-MIL_Learning_from_Noisy_Pseudo_Labels_for_Promoting_Multiple_Instance_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Medical and Biological Vision; Cell Microscopy" + } +] \ No newline at end of file diff --git a/json_data/2023/main/motion-estimation-matching-and-tracking.json b/json_data/2023/main/motion-estimation-matching-and-tracking.json new file mode 100644 index 0000000..ee92043 --- /dev/null +++ b/json_data/2023/main/motion-estimation-matching-and-tracking.json @@ -0,0 +1,1595 @@ +[ + { + "title": "TMR: Text-to-Motion Retrieval using Contrastive 3D Human Motion Synthesis", + "base_url": null, + "title_page": null, + "github": "Mathux/TMR", + "web_page": null, + "github_page": "https://mathis.petrovich.fr/tmr/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/Mathux/TMR", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Petrovich_TMR_Text-to-Motion_Retrieval_Using_Contrastive_3D_Human_Motion_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.00976", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "FK0RukgDEtM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Sequential Texts Driven Cohesive Motions Synthesis with Natural Transitions", + "base_url": null, + "title_page": null, + "github": "Druthrie/ST2M", + "web_page": null, + "github_page": "https://druthrie.github.io/sequential-texts-to-motion/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Sequential_Texts_Driven_Cohesive_Motions_Synthesis_with_Natural_Transitions_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction", + "base_url": null, + "title_page": null, + "github": "MediaBrain-SJTU/AuxFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Auxiliary_Tasks_Benefit_3D_Skeleton-based_Human_Motion_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08942", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Explicit Motion Disentangling for Efficient Optical Flow Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Deng_Explicit_Motion_Disentangling_for_Efficient_Optical_Flow_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "TrackFlow: Multi-Object tracking with Normalizing Flows", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mancusi_TrackFlow_Multi-Object_tracking_with_Normalizing_Flows_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11513", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "HumanMAC: Masked Motion Completion for Human Motion Prediction", + "base_url": null, + "title_page": null, + "github": "LinghaoChan/HumanMAC", + "web_page": "https://lhchen.top/Human-MAC/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_HumanMAC_Masked_Motion_Completion_for_Human_Motion_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.03665", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "vfde9GdUHBs", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Geometrized Transformer for Self-Supervised Homography Estimation", + "base_url": null, + "title_page": null, + "github": "ruc-aimc-lab/GeoFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Geometrized_Transformer_for_Self-Supervised_Homography_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving", + "base_url": null, + "title_page": null, + "github": "duke-vision/semantic-unsup-flow-release", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yuan_SemARFlow_Injecting_Semantics_into_Unsupervised_Optical_Flow_Estimation_for_Autonomous_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06209", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "XYBTolH2S8A", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "NeSS-ST: Detecting Good and Stable Keypoints with a Neural Stability Score and the Shi-Tomasi Detector", + "base_url": null, + "title_page": null, + "github": "KonstantinPakulev/NeSS-ST", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pakulev_NeSS-ST_Detecting_Good_and_Stable_Keypoints_with_a_Neural_Stability_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Robust Object Modeling for Visual Tracking", + "base_url": null, + "title_page": null, + "github": "dawnyc/ROMTrack", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_Robust_Object_Modeling_for_Visual_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05140", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Social Diffusion: Long-Term Multiple Human Motion Anticipation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tanke_Social_Diffusion_Long-term_Multiple_Human_Motion_Anticipation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kang_Exploring_Lightweight_Hierarchical_Vision_Transformers_for_Efficient_Visual_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06904", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "HMD-NeMo: Online 3D Avatar Motion Generation from Sparse Observations", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Aliakbarian_HMD-NeMo_Online_3D_Avatar_Motion_Generation_From_Sparse_Observations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11261", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Learning Fine-Grained Features for Pixel-Wise Video Correspondences", + "base_url": null, + "title_page": null, + "github": "qianduoduolr/Spa-then-Temp", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Learning_Fine-Grained_Features_for_Pixel-Wise_Video_Correspondences_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03040", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "2ZCVUoiyM0U", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "GAFlow: Incorporating Gaussian Attention into Optical Flow", + "base_url": null, + "title_page": null, + "github": "LA30/GAFlow", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_GAFlow_Incorporating_Gaussian_Attention_into_Optical_Flow_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Occ2Net: Robust Image Matching based on 3D Occupancy Estimation for Occluded Regions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_Occ2Net_Robust_Image_Matching_Based_on_3D_Occupancy_Estimation_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16160", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://jiyewise.github.io/projects/LAMA/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Locomotion-Action-Manipulation_Synthesizing_Human-Scene_Interactions_in_Complex_3D_Environments_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.02667", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Trajectory Unified Transformer for Pedestrian Trajectory Prediction", + "base_url": null, + "title_page": null, + "github": "lssiair/TUTR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_Trajectory_Unified_Transformer_for_Pedestrian_Trajectory_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "TMA: Temporal Motion Aggregation for Event-based Optical Flow", + "base_url": null, + "title_page": null, + "github": "ispc-lab/TMA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_TMA_Temporal_Motion_Aggregation_for_Event-based_Optical_Flow_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11629", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Taming Contrast Maximization for Learning Sequential, Low-Latency, Event-based Optical Flow", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://mavlab.tudelft.nl/taming_event_flow/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Paredes-Valles_Taming_Contrast_Maximization_for_Learning_Sequential_Low-latency_Event-based_Optical_Flow_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "vkYimENc494", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "GlueStick: Robust Image Matching by Sticking Points and Lines Together", + "base_url": null, + "title_page": null, + "github": "cvg/GlueStick", + "web_page": "https://iago-suarez.com/gluestick/", + "github_page": null, + "colab": "https://colab.research.google.com/github/cvg/GlueStick/blob/main/gluestick_matching_demo.ipynb", + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pautrat_GlueStick_Robust_Image_Matching_by_Sticking_Points_and_Lines_Together_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02008", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "JmpddJ5pfz8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "DARTH: Holistic Test-Time Adaptation for Multiple Object Tracking", + "base_url": null, + "title_page": null, + "github": "mattiasegu/darth", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Segu_DARTH_Holistic_Test-time_Adaptation_for_Multiple_Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "S-TREK: Sequential Translation and Rotation Equivariant Keypoints for Local Feature Extraction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Santellani_S-TREK_Sequential_Translation_and_Rotation_Equivariant_Keypoints_for_Local_Feature_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14598", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation", + "base_url": null, + "title_page": null, + "github": "yoxu515/MITS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Integrating_Boxes_and_Masks_A_Multi-Object_Framework_for_Unified_Visual_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13266", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://fabiendelattre.com/robust-rotation-estimation/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Delattre_Robust_Frame-to-Frame_Camera_Rotation_Estimation_in_Crowded_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08588", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "SL4QBedLu9Q", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Sparse Instance Conditioned Multimodal Trajectory Prediction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Sparse_Instance_Conditioned_Multimodal_Trajectory_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment", + "base_url": null, + "title_page": null, + "github": "facebookresearch/PoseDiffusion", + "web_page": null, + "github_page": "https://posediffusion.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_PoseDiffusion_Solving_Pose_Estimation_via_Diffusion-aided_Bundle_Adjustment_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.15667", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking", + "base_url": null, + "title_page": null, + "github": "dsx0511/3DMOTFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ding_3DMOTFormer_Graph_Transformer_for_Online_3D_Multi-Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06635", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Fast Inference and Update of Probabilistic Density Estimation on Trajectory Prediction", + "base_url": null, + "title_page": null, + "github": "meaten/FlowChain-ICCV2023", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Maeda_Fast_Inference_and_Update_of_Probabilistic_Density_Estimation_on_Trajectory_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08824", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Supervised Homography Learning with Realistic Dataset Generation", + "base_url": null, + "title_page": null, + "github": "JianghaiSCU/RealSH", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Supervised_Homography_Learning_with_Realistic_Dataset_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15353", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Joint-Relation Transformer for Multi-Person Motion Prediction", + "base_url": null, + "title_page": null, + "github": "MediaBrain-SJTU/JRTransformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Joint-Relation_Transformer_for_Multi-Person_Motion_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04808", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Event-based Temporally Dense Optical Flow Estimation with Sequential Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ponghiran_Event-based_Temporally_Dense_Optical_Flow_Estimation_with_Sequential_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.01244", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "3D Motion Magnification: Visualizing Subtle Motions from Time-Varying Radiance Fields", + "base_url": null, + "title_page": null, + "github": "3d-motion-magnification/3d-motion-mag", + "web_page": null, + "github_page": "https://3d-motion-magnification.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_3D_Motion_Magnification_Visualizing_Subtle_Motions_from_Time-Varying_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03757", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "ljar4GAFkUk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Learning Optical Flow from Event Camera with Rendered Dataset", + "base_url": null, + "title_page": null, + "github": "boomluo02/ADMFlow", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_Learning_Optical_Flow_from_Event_Camera_with_Rendered_Dataset_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11011", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Persistent-Transient Duality: A Multi-Mechanism Approach for Modeling Human-Object Interaction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tran_Persistent-Transient_Duality_A_Multi-Mechanism_Approach_for_Modeling_Human-Object_Interaction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12729", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "nVOQdI8g7AY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Deep Homography Mixture for Single Image Rolling Shutter Correction", + "base_url": null, + "title_page": null, + "github": "DavidYan2001/Deep_RS-HM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_Deep_Homography_Mixture_for_Single_Image_Rolling_Shutter_Correction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Fast Neural Scene Flow", + "base_url": null, + "title_page": null, + "github": "Lilac-Lee/FastNSF", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Fast_Neural_Scene_Flow_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.09121", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "RLSAC: Reinforcement Learning Enhanced Sample Consensus for End-to-End Robust Estimation", + "base_url": null, + "title_page": null, + "github": "IRMVLab/RLSAC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nie_RLSAC_Reinforcement_Learning_Enhanced_Sample_Consensus_for_End-to-End_Robust_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05318", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking", + "base_url": null, + "title_page": null, + "github": "MCG-NJU/MeMOTR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_MeMOTR_Long-Term_Memory-Augmented_Transformer_for_Multi-Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15700", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors", + "base_url": null, + "title_page": null, + "github": "slothfulxtx/MBPTrack3D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_MBPTrack_Improving_3D_Point_Cloud_Tracking_with_Memory_Networks_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05071", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Zl_4LnoX_Ak", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes", + "base_url": null, + "title_page": null, + "github": "MCG-NJU/SportsMOT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cui_SportsMOT_A_Large_Multi-Object_Tracking_Dataset_in_Multiple_Sports_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.05170", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Heterogeneous_Diversity_Driven_Active_Learning_for_Multi-Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration", + "base_url": null, + "title_page": null, + "github": "Garfield-kh/TM2D", + "web_page": null, + "github_page": "https://garfield-kh.github.io/TM2D/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gong_TM2D_Bimodality_Driven_3D_Dance_Generation_via_Music-Text_Integration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02419", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "6QQFXG4s7iQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Synchronize_Feature_Extracting_and_Matching_A_Single_Branch_Framework_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12549", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking", + "base_url": null, + "title_page": null, + "github": "yolomax/ColTrack", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Collaborative_Tracking_Learning_for_Frame-Rate-Insensitive_Multi-Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05911", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "CiteTracker: Correlating Image and Text for Visual Tracking", + "base_url": null, + "title_page": null, + "github": "NorahGreen/CiteTracker", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_CiteTracker_Correlating_Image_and_Text_for_Visual_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11322", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://sinc.is.tue.mpg.de/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Athanasiou_SINC_Spatial_Composition_of_3D_Human_Motions_for_Simultaneous_Action_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.10417", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "uwUriDnKTLI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Uncertainty-Aware Unsupervised Multi-Object Tracking", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Uncertainty-aware_Unsupervised_Multi-Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15409", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework", + "base_url": null, + "title_page": null, + "github": "Jaraxxus-Me/PVT_pp", + "web_page": null, + "github_page": "https://jaraxxus-me.github.io/ICCV2023_PVTpp/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_PVT_A_Simple_End-to-End_Latency-Aware_Visual_Tracking_Framework_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting", + "base_url": null, + "title_page": null, + "github": "inhwanbae/EigenTrajectory", + "web_page": null, + "github_page": "https://ihbae.com/publication/eigentrajectory/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bae_EigenTrajectory_Low-Rank_Descriptors_for_Multi-Modal_Trajectory_Forecasting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09306", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation", + "base_url": null, + "title_page": null, + "github": "danqu130/RPEFlow", + "web_page": null, + "github_page": "https://npucvr.github.io/RPEFlow/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wan_RPEFlow_Multimodal_Fusion_of_RGB-PointCloud-Event_for_Joint_Optical_Flow_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.15082", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Multi-Scale Bidirectional Recurrent Network with Hybrid Correlation for Point Cloud based Scene Flow Estimation", + "base_url": null, + "title_page": null, + "github": "cwc1260/MSBRN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_Multi-Scale_Bidirectional_Recurrent_Network_with_Hybrid_Correlation_for_Point_Cloud_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking", + "base_url": null, + "title_page": null, + "github": "chengche6230/ReST", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_ReST_A_Reconfigurable_Spatial-Temporal_Graph_Model_for_Multi-Camera_Multi-Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13229", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "TAPIR: Tracking any Point with Per-Frame Initialization and Temporal Refinement", + "base_url": null, + "title_page": null, + "github": "google-deepmind/tapnet", + "web_page": null, + "github_page": "https://deepmind-tapir.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Doersch_TAPIR_Tracking_Any_Point_with_Per-Frame_Initialization_and_Temporal_Refinement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.08637", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "I1DQJH3v7Nk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_IHNet_Iterative_Hierarchical_Network_Guided_by_High-Resolution_Estimated_Information_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Can Language Models Learn to Listen?", + "base_url": null, + "title_page": null, + "github": "sanjayss34/lm-listener", + "web_page": "https://people.eecs.berkeley.edu/~evonne_ng/projects/text2listen/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ng_Can_Language_Models_Learn_to_Listen_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10897", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "djpSOhdIU8M", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "XVO: Generalized Visual Odometry via Cross-Modal Self-Training", + "base_url": null, + "title_page": null, + "github": "h2xlab/XVO", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lai_XVO_Generalized_Visual_Odometry_via_Cross-Modal_Self-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Distracting Downpour: Adversarial Weather Attacks for Motion Estimation", + "base_url": null, + "title_page": null, + "github": "cv-stuttgart/DistractingDownpour", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Schmalfuss_Distracting_Downpour_Adversarial_Weather_Attacks_for_Motion_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.06716", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + }, + { + "title": "Foreground-Background Distribution Modeling Transformer for Visual Object Tracking", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Foreground-Background_Distribution_Modeling_Transformer_for_Visual_Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Motion Estimation, Matching and Tracking" + } +] \ No newline at end of file diff --git a/json_data/2023/main/multimodal-learning.json b/json_data/2023/main/multimodal-learning.json new file mode 100644 index 0000000..8a332a1 --- /dev/null +++ b/json_data/2023/main/multimodal-learning.json @@ -0,0 +1,812 @@ +[ + { + "title": "SLAN: Self-Locator Aided Network for Vision-Language Understanding", + "base_url": null, + "title_page": null, + "github": "scok30/SLAN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhai_SLAN_Self-Locator_Aided_Network_for_Vision-Language_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.16208", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Long_Task-Oriented_Multi-Modal_Mutual_Leaning_for_Vision-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17169", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance", + "base_url": null, + "title_page": null, + "github": "microsoft/Cream", + "web_page": null, + "github_page": "https://github.com/microsoft/Cream/tree/main/TinyCLIP", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_TinyCLIP_CLIP_Distillation_via_Affinity_Mimicking_and_Weight_Inheritance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.12314", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval", + "base_url": null, + "title_page": null, + "github": "ninatu/in_style", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shvetsova_In-Style_Bridging_Text_and_Uncurated_Videos_with_Style_Transfer_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08928", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Preserving Modality Structure Improves Multi-Modal Learning", + "base_url": null, + "title_page": null, + "github": "Swetha5/Multi_Sinkhorn_Knopp", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Swetha_Preserving_Modality_Structure_Improves_Multi-Modal_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13077", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "KmyFxfUOGcY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Distribution-Aware Prompt Tuning for Vision-Language Models", + "base_url": null, + "title_page": null, + "github": "mlvlab/DAPT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cho_Distribution-Aware_Prompt_Tuning_for_Vision-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03406", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "IranQin/SupFusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qin_SupFusion_Supervised_LiDAR-Camera_Fusion_for_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.07084", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Distribution-Consistent Modal Recovering for Incomplete Multimodal Learning", + "base_url": null, + "title_page": null, + "github": "mdswyz/DiCMoR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Distribution-Consistent_Modal_Recovering_for_Incomplete_Multimodal_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Fg-T2M_Fine-Grained_Text-Driven_Human_Motion_Generation_via_Diffusion_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.06284", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Cross-Modal Orthogonal High-Rank Augmentation for RGB-Event Transformer-Trackers", + "base_url": null, + "title_page": null, + "github": "ZHU-Zhiyu/High-Rank_RGB-Event_Tracker", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Cross-Modal_Orthogonal_High-Rank_Augmentation_for_RGB-Event_Transformer-Trackers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.04129", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "eP-ALM: Efficient Perceptual Augmentation of Language Models", + "base_url": null, + "title_page": null, + "github": "mshukor/eP-ALM", + "web_page": null, + "github_page": "https://mshukor.github.io/eP-ALM.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shukor_eP-ALM_Efficient_Perceptual_Augmentation_of_Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11403", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Generating Visual Scenes from Touch", + "base_url": null, + "title_page": null, + "github": "fredfyyang/vision-from-touch", + "web_page": null, + "github_page": "https://fredfyyang.github.io/vision-from-touch/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Generating_Visual_Scenes_from_Touch_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.15117", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Multimodal High-Order Relation Transformer for Scene Boundary Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Multimodal_High-order_Relation_Transformer_for_Scene_Boundary_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Muscles in Action", + "base_url": null, + "title_page": null, + "github": "mchiquier/musclesinaction", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chiquier_Muscles_in_Action_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.02978", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Self-Evolved Dynamic Expansion Model for Task-Free Continual Learning", + "base_url": null, + "title_page": null, + "github": "dtuzi123/SEDEM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_Self-Evolved_Dynamic_Expansion_Model_for_Task-Free_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Multi-Event Video-Text Retrieval", + "base_url": null, + "title_page": null, + "github": "gengyuanmax/MeVTR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Multi-Event_Video-Text_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11551", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Referring Image Segmentation using Text Supervision", + "base_url": null, + "title_page": null, + "github": "fawnliu/TRIS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Referring_Image_Segmentation_Using_Text_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14575", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning", + "base_url": null, + "title_page": null, + "github": "NMS05/Audio-Visual-Deception-Detection-DOLOS-Dataset-and-Parameter-Efficient-Crossmodal-Learning", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Audio-Visual_Deception_Detection_DOLOS_Dataset_and_Parameter-Efficient_Crossmodal_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12745", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "EMMN: Emotional Motion Memory Network for Audio-Driven Emotional Talking Face Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tan_EMMN_Emotional_Motion_Memory_Network_for_Audio-driven_Emotional_Talking_Face_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-Training", + "base_url": null, + "title_page": null, + "github": "tyhuang0428/CLIP2Point", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_CLIP2Point_Transfer_CLIP_to_Point_Cloud_Classification_with_Image-Depth_Pre-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.01055", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Speech2Lip: High-Fidelity Speech to Lip Generation by Learning from a Short Video", + "base_url": null, + "title_page": null, + "github": "CVMI-Lab/Speech2Lip", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Speech2Lip_High-fidelity_Speech_to_Lip_Generation_by_Learning_from_a_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04814", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "GrowCLIP: Data-Aware Automatic Model Growing for Large-Scale Contrastive Language-Image Pre-Training", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Deng_GrowCLIP_Data-Aware_Automatic_Model_Growing_for_Large-scale_Contrastive_Language-Image_Pre-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11331", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "A Retrospect to Multi-Prompt Learning Across Vision and Language", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_A_Retrospect_to_Multi-prompt_Learning_across_Vision_and_Language_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules", + "base_url": null, + "title_page": null, + "github": "zhiqic/ChartReader", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_ChartReader_A_Unified_Framework_for_Chart_Derendering_and_Comprehension_without_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02173", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "VIOGL4gF06w", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Boosting Multi-Modal Model Performance with Adaptive Gradient Modulation", + "base_url": null, + "title_page": null, + "github": "lihong2303/AGM_ICCV2023", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Boosting_Multi-modal_Model_Performance_with_Adaptive_Gradient_Modulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07686", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "ViLLA: Fine-Grained Vision-Language Representation Learning from Real-World Data", + "base_url": null, + "title_page": null, + "github": "StanfordMIMI/villa", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Varma_ViLLA_Fine-Grained_Vision-Language_Representation_Learning_from_Real-World_Data_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11194", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Robust Referring Video Object Segmentation with Cyclic Structural Consensus", + "base_url": null, + "title_page": null, + "github": "lxa9867/R2VOS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Robust_Referring_Video_Object_Segmentation_with_Cyclic_Structural_Consensus_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2207.01203", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Fantasia3D: Disentangling Geometry and Appearance for High-Quality Text-to-3D Content Creation", + "base_url": null, + "title_page": null, + "github": "Gorilla-Lab-SCUT/Fantasia3D", + "web_page": null, + "github_page": "https://fantasia3d.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Fantasia3D_Disentangling_Geometry_and_Appearance_for_High-quality_Text-to-3D_Content_Creation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13873", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Xbzl4HzFiNo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation", + "base_url": null, + "title_page": null, + "github": "KevinLight831/CTP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_CTPTowards_Vision-Language_Continual_Pretraining_via_Compatible_Momentum_Contrast_and_Topology_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07146", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + }, + { + "title": "Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning", + "base_url": null, + "title_page": null, + "github": "HaibiaoXuan/Narrator", + "web_page": null, + "github_page": "https://haibiaoxuan.github.io/Narrator/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xuan_Narrator_Towards_Natural_Control_of_Human-Scene_Interaction_Generation_via_Relationship_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09410", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Multimodal Learning" + } +] \ No newline at end of file diff --git a/json_data/2023/main/navigation-and-autonomous-driving.json b/json_data/2023/main/navigation-and-autonomous-driving.json new file mode 100644 index 0000000..f57299b --- /dev/null +++ b/json_data/2023/main/navigation-and-autonomous-driving.json @@ -0,0 +1,1379 @@ +[ + { + "title": "Robust Monocular Depth Estimation under Challenging Conditions", + "base_url": null, + "title_page": null, + "github": "md4all/md4all", + "web_page": null, + "github_page": "https://md4all.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gasperini_Robust_Monocular_Depth_Estimation_under_Challenging_Conditions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09711", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "UMC: A Unified Bandwidth-Efficient and Multi-Resolution based Collaborative Perception Framework", + "base_url": null, + "title_page": null, + "github": "ispc-lab/UMC", + "web_page": null, + "github_page": "https://tianhangwang.github.io/UMC/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_UMC_A_Unified_Bandwidth-efficient_and_Multi-resolution_based_Collaborative_Perception_Framework_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12400", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "View Consistent Purification for Accurate Cross-View Localization", + "base_url": null, + "title_page": null, + "github": "ShanWang-Shan/PureACL-website", + "web_page": null, + "github_page": "https://shanwang-shan.github.io/PureACL-website/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_View_Consistent_Purification_for_Accurate_Cross-View_Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08110", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Semi-Supervised Semantics-Guided Adversarial Training for Robust Trajectory Prediction", + "base_url": null, + "title_page": null, + "github": "jrcblue/SSAT-for-Motion-Prediction", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiao_Semi-supervised_Semantics-guided_Adversarial_Training_for_Robust_Trajectory_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2205.14230", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping", + "base_url": null, + "title_page": null, + "github": "JunyuanDeng/NeRF-LOAM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Deng_NeRF-LOAM_Neural_Implicit_Representation_for_Large-Scale_Incremental_LiDAR_Odometry_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10709", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models", + "base_url": null, + "title_page": null, + "github": "xiyuez2/MapPrior", + "web_page": null, + "github_page": "https://mapprior.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_MapPrior_Birds-Eye_View_Map_Layout_Estimation_with_Generative_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12963", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Hidden Biases of End-to-End Driving Models", + "base_url": null, + "title_page": null, + "github": "autonomousvision/carla_garage", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jaeger_Hidden_Biases_of_End-to-End_Driving_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.07957", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "ChrPW8RdqQU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Search for or Navigate to? Dual Adaptive Thinking for Object Navigation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dang_Search_for_or_Navigate_to_Dual_Adaptive_Thinking_for_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.00553", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "BiFF: Bi-Level Future Fusion with Polyline-based Coordinate for Interactive Trajectory Prediction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_BiFF_Bi-level_Future_Fusion_with_Polyline-based_Coordinate_for_Interactive_Trajectory_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.14161", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Towards Zero Domain Gap: A Comprehensive Study of Realistic LiDAR Simulation for Autonomy Testing", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://waabi.ai/lidar-dg/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Manivasagam_Towards_Zero_Domain_Gap_A_Comprehensive_Study_of_Realistic_LiDAR_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Clustering based Point Cloud Representation Learning for 3D Analysis", + "base_url": null, + "title_page": null, + "github": "FengZicai/Cluster3Dseg", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_Clustering_based_Point_Cloud_Representation_Learning_for_3D_Analysis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14605", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation", + "base_url": null, + "title_page": null, + "github": "KUIS-AI/adapt", + "web_page": null, + "github_page": "https://kuis-ai.github.io/adapt/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Aydemir_ADAPT_Efficient_Multi-Agent_Trajectory_Prediction_with_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14187", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Driving", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_MV-DeepSDF_Implicit_Modeling_with_Multi-Sweep_Point_Clouds_for_3D_Vehicle_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16715", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "k9RbDA1nE7s", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Learning Vision-and-Language Navigation from YouTube Videos", + "base_url": null, + "title_page": null, + "github": "JeremyLinky/YouTube-VLN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Learning_Vision-and-Language_Navigation_from_YouTube_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11984", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_TrajPAC_Towards_Robustness_Verification_of_Pedestrian_Trajectory_Prediction_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05985", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "VAD: Vectorized Scene Representation for Efficient Autonomous Driving", + "base_url": null, + "title_page": null, + "github": "hustvl/VAD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_VAD_Vectorized_Scene_Representation_for_Efficient_Autonomous_Driving_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12077", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Traj-MAE: Masked Autoencoders for Trajectory Prediction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://jiazewang.com/projects/trajmae.html", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Traj-MAE_Masked_Autoencoders_for_Trajectory_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06697", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Sparse Point Guided 3D Lane Detection", + "base_url": null, + "title_page": null, + "github": "YaoChengTang/Sparse-Point-Guided-3D-Lane-Detection", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yao_Sparse_Point_Guided_3D_Lane_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "A Simple Vision Transformer for Weakly Semi-Supervised 3D Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_A_Simple_Vision_Transformer_for_Weakly_Semi-supervised_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Learn TAROT with MENTOR: A Meta-Learned Self-Supervised Approach for Trajectory Prediction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pourkeshavarz_Learn_TAROT_with_MENTOR_A_Meta-Learned_Self-Supervised_Approach_for_Trajectory_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "FocalFormer3D: Focusing on Hard Instance for 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "NVlabs/FocalFormer3D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_FocalFormer3D_Focusing_on_Hard_Instance_for_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04556", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Scene as Occupancy", + "base_url": null, + "title_page": null, + "github": "OpenDriveLab/OccNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tong_Scene_as_Occupancy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.02851", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Real-Time Neural Rasterization for Large Scenes", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://waabi.ai/NeuRas/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Real-Time_Neural_Rasterization_for_Large_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2311.05607", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "A Game of Bundle Adjustment - Learning Efficient Convergence", + "base_url": null, + "title_page": null, + "github": "amirbelder/A-Game-of-Bundle-Adjustment---Learning-Efficient-Convergence", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Belder_A_Game_of_Bundle_Adjustment_-_Learning_Efficient_Convergence_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13270", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Efficient Transformer-based 3D Object Detection with Dynamic Token Halting", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_Efficient_Transformer-based_3D_Object_Detection_with_Dynamic_Token_Halting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05078", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration", + "base_url": null, + "title_page": null, + "github": "IRMVLab/RegFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_RegFormer_An_Efficient_Projection-Aware_Transformer_Network_for_Large-Scale_Point_Cloud_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12384", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "CASSPR: Cross Attention Single Scan Place Recognition", + "base_url": null, + "title_page": null, + "github": "Yan-Xia/CASSPR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xia_CASSPR_Cross_Attention_Single_Scan_Place_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.12542", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Recursive Video Lane Detection", + "base_url": null, + "title_page": null, + "github": "dongkwonjin/RVLD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jin_Recursive_Video_Lane_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11106", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Z0FaOqVrN5w", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Parametric Depth based Feature Representation Learning for Object Detection and Segmentation in Bird's-Eye View", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Parametric_Depth_Based_Feature_Representation_Learning_for_Object_Detection_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.04106", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "SHIFT3D: Synthesizing Hard Inputs for Tricking 3D Detectors", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_SHIFT3D_Synthesizing_Hard_Inputs_For_Tricking_3D_Detectors_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05810", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Bootstrap Motion Forecasting With Self-Consistent Constraints", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_Bootstrap_Motion_Forecasting_With_Self-Consistent_Constraints_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2204.05859", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Towards Viewpoint Robustness in Bird's Eye View Segmentation", + "base_url": null, + "title_page": null, + "github": "NVlabs/viewpoint-robustness", + "web_page": null, + "github_page": "https://nvlabs.github.io/viewpoint-robustness/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Klinghoffer_Towards_Viewpoint_Robustness_in_Birds_Eye_View_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05192", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "R-Pred: Two-Stage Motion Prediction via Tube-Query Attention-based Trajectory Refinement", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Choi_R-Pred_Two-Stage_Motion_Prediction_Via_Tube-Query_Attention-Based_Trajectory_Refinement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.08609", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "INT2: Interactive Trajectory Prediction at Intersections", + "base_url": null, + "title_page": null, + "github": "AIR-DISCOVER/INT2", + "web_page": "https://int2.cn/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_INT2_Interactive_Trajectory_Prediction_at_Intersections_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "KNkuakDvgVc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception", + "base_url": null, + "title_page": null, + "github": "ZRandomize/MatrixVT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_MatrixVT_Efficient_Multi-Camera_to_BEV_Transformation_for_3D_Perception_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.10593", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding", + "base_url": null, + "title_page": null, + "github": "zaplm/DriverAttention", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Unsupervised_Self-Driving_Attention_Prediction_via_Uncertainty_Mining_and_Knowledge_Embedding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09706", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_SVQNet_Sparse_Voxel-Adjacent_Query_Network_for_4D_Spatio-Temporal_LiDAR_Semantic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13323", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "MotionLM: Multi-Agent Motion Forecasting as Language Modeling", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Seff_MotionLM_Multi-Agent_Motion_Forecasting_as_Language_Modeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16534", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Improving Online Lane Graph Extraction by Object-Lane Clustering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Can_Improving_Online_Lane_Graph_Extraction_by_Object-Lane_Clustering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10947", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Najibi_Unsupervised_3D_Perception_with_2D_Vision-Language_Distillation_for_Autonomous_Driving_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14491", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Self-Supervised Monocular Depth Estimation by Direction-Aware Cumulative Convolution Network", + "base_url": null, + "title_page": null, + "github": "wencheng256/DaCCN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_Self-Supervised_Monocular_Depth_Estimation_by_Direction-aware_Cumulative_Convolution_Network_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05605", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Ordered Atomic Activity for Fine-Grained Interactive Traffic Scenario Understanding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Agarwal_Ordered_Atomic_Activity_for_Fine-grained_Interactive_Traffic_Scenario_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://drive.google.com/file/d/1Jwzzr0puAWte5xa-xQwOAnpAXsBsSw7f/view", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_DistillBEV_Boosting_Multi-Camera_3D_Object_Detection_with_Cross-Modal_Knowledge_Distillation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.15109", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://www.vis.xyz/pub/vtd/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Video_Task_Decathlon_Unifying_Image_and_Video_Tasks_in_Autonomous_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04422", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "MV-Map: Offboard HD-Map Generation with Multi-View Consistency", + "base_url": null, + "title_page": null, + "github": "ZiYang-xie/MV-Map", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_MV-Map_Offboard_HD-Map_Generation_with_Multi-view_Consistency_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.08851", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Towards Universal LiDAR-based 3D Object Detection by Multi-Domain Knowledge Transfer", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Towards_Universal_LiDAR-Based_3D_Object_Detection_by_Multi-Domain_Knowledge_Transfer_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "Forecast-MAE: Self-Supervised Pre-Training for Motion Forecasting with Masked Autoencoders", + "base_url": null, + "title_page": null, + "github": "jchengai/forecast-mae", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_Forecast-MAE_Self-supervised_Pre-training_for_Motion_Forecasting_with_Masked_Autoencoders_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09882", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "UniFusion: Unified Multi-View Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View", + "base_url": null, + "title_page": null, + "github": "cfzd/UniFusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qin_UniFusion_Unified_Multi-View_Fusion_Transformer_for_Spatial-Temporal_Representation_in_Birds-Eye-View_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2207.08536", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images", + "base_url": null, + "title_page": null, + "github": "zjuluolun/BEVPlace", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_BEVPlace_Learning_LiDAR-based_Place_Recognition_using_Birds_Eye_View_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.14325", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "CORE: Cooperative Reconstruction for Multi-Agent Perception", + "base_url": null, + "title_page": null, + "github": "zllxot/CORE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_CORE_Cooperative_Reconstruction_for_Multi-Agent_Perception_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11514", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + }, + { + "title": "MetaBEV: Solving Sensor Failures for 3D Detection and Map Segmentation", + "base_url": null, + "title_page": null, + "github": "ChongjianGE/MetaBEV", + "web_page": null, + "github_page": "https://chongjiange.github.io/metabev.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ge_MetaBEV_Solving_Sensor_Failures_for_3D_Detection_and_Map_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.09801", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "TiEQpYq77Xo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Navigation and Autonomous Driving" + } +] \ No newline at end of file diff --git a/json_data/2023/main/neural-generative-models.json b/json_data/2023/main/neural-generative-models.json new file mode 100644 index 0000000..031e664 --- /dev/null +++ b/json_data/2023/main/neural-generative-models.json @@ -0,0 +1,920 @@ +[ + { + "title": "Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models", + "base_url": null, + "title_page": null, + "github": "nanlliu/Unsupervised-Compositional-Concepts-Discovery", + "web_page": null, + "github_page": "https://energy-based-model.github.io/unsupervised-concept-discovery/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Unsupervised_Compositional_Concepts_Discovery_with_Text-to-Image_Generative_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.05357", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Human Preference Score: Better Aligning Text-to-Image Models with Human Preference", + "base_url": null, + "title_page": null, + "github": "tgxs002/align_sd", + "web_page": null, + "github_page": "https://tgxs002.github.io/align_sd_web/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Human_Preference_Score_Better_Aligning_Text-to-Image_Models_with_Human_Preference_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14420", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "DLT: Conditioned Layout Generation with Joint Discrete-Continuous Diffusion Layout Transformer", + "base_url": null, + "title_page": null, + "github": "wix-incubator/DLT", + "web_page": null, + "github_page": "https://wix-incubator.github.io/DLT/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Levi_DLT_Conditioned_layout_generation_with_Joint_Discrete-Continuous_Diffusion_Layout_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.03755", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Anti-DreamBooth: Protecting users from Personalized Text-to-Image Synthesis", + "base_url": null, + "title_page": null, + "github": "VinAIResearch/Anti-DreamBooth", + "web_page": null, + "github_page": "https://anti-dreambooth.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Van_Le_Anti-DreamBooth_Protecting_Users_from_Personalized_Text-to-image_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15433", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "GECCO: Geometrically-Conditioned Point Diffusion Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://jatentaki.github.io/publication/10-03-2023", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tyszkiewicz_GECCO_Geometrically-Conditioned_Point_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05916", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "DiffDreamer: Towards Consistent Unsupervised Single-View Scene Extrapolation with Conditional Diffusion Models", + "base_url": null, + "title_page": null, + "github": "primecai/DiffDreamer", + "web_page": null, + "github_page": "https://primecai.github.io/diffdreamer", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_DiffDreamer_Towards_Consistent_Unsupervised_Single-view_Scene_Extrapolation_with_Conditional_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.12131", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "UukyiAqlwcw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Guided Motion Diffusion for Controllable Human Motion Synthesis", + "base_url": null, + "title_page": null, + "github": "korrawe/guided-motion-diffusion", + "web_page": null, + "github_page": "https://korrawe.github.io/gmd-project/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Karunratanakul_Guided_Motion_Diffusion_for_Controllable_Human_Motion_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.12577", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "giw0pLIKdsA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "COOP: Decoupling and Coupling of Whole-Body Grasping Pose Generation", + "base_url": null, + "title_page": null, + "github": "zhengyanzhao1997/COOP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_COOP_Decoupling_and_Coupling_of_Whole-Body_Grasping_Pose_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Zero-Shot Spatial Layout Conditioning for Text-to-Image Diffusion Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Couairon_Zero-Shot_Spatial_Layout_Conditioning_for_Text-to-Image_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.13754", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-Shot and Few-Shot Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "AIRI-Institute/StyleDomain", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Alanov_StyleDomain_Efficient_and_Lightweight_Parameterizations_of_StyleGAN_for_One-shot_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.10229", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://jeffreyxiang.github.io/GRAM-HD/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiang_GRAM-HD_3D-Consistent_Image_Generation_at_High_Resolution_with_Generative_Radiance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.07255", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Uqzs4uN6v8M", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Your Diffusion Model is Secretly a Zero-Shot Classifier", + "base_url": null, + "title_page": null, + "github": "diffusion-classifier/diffusion-classifier", + "web_page": null, + "github_page": "https://diffusion-classifier.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Your_Diffusion_Model_is_Secretly_a_Zero-Shot_Classifier_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16203", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Learning Hierarchical Features with Joint Latent Space Energy-based Prior", + "base_url": null, + "title_page": null, + "github": "jcui1224/hierarchical-representation-ebm", + "web_page": null, + "github_page": "https://jcui1224.github.io/hierarchical-representation-ebm-proj/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cui_Learning_Hierarchical_Features_with_Joint_Latent_Space_Energy-Based_Prior_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.09604", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_ActFormer_A_GAN-based_Transformer_towards_General_Action-Conditioned_3D_Human_Motion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2203.07706", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Landscape Learning for Neural Network Inversion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Landscape_Learning_for_Neural_Network_Inversion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.09027", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Diffusion in Style", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://ivrl.github.io/diffusion-in-style/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Everaert_Diffusion_in_Style_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "3Ge98E4x4JA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions", + "base_url": null, + "title_page": null, + "github": "princeton-computational-imaging/Diffusion-SDF", + "web_page": "https://light.princeton.edu/publication/diffusion-sdf/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chou_Diffusion-SDF_Conditional_Generative_Modeling_of_Signed_Distance_Functions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.13757", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "GETAvatar: Generative Textured Meshes for Animatable Human Avatars", + "base_url": null, + "title_page": null, + "github": "magic-research/GETAvatar", + "web_page": null, + "github_page": "https://getavatar.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_GETAvatar_Generative_Textured_Meshes_for_Animatable_Human_Avatars_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "A-STAR: Test-Time Attention Segregation and Retention for Text-to-Image Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Agarwal_A-STAR_Test-time_Attention_Segregation_and_Retention_for_Text-to-image_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.14544", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "TF-ICON: Diffusion-based Training-Free Cross-Domain Image Composition", + "base_url": null, + "title_page": null, + "github": "Shilin-LU/TF-ICON", + "web_page": null, + "github_page": "https://shilin-lu.github.io/tf-icon.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_TF-ICON_Diffusion-Based_Training-Free_Cross-Domain_Image_Composition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12493", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Breaking The Limits of Text-Conditioned 3D Motion Synthesis with Elaborative Descriptions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qian_Breaking_The_Limits_of_Text-conditioned_3D_Motion_Synthesis_with_Elaborative_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction", + "base_url": null, + "title_page": null, + "github": "BarqueroGerman/BeLFusion", + "web_page": null, + "github_page": "https://barquerogerman.github.io/BeLFusion/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Barquero_BeLFusion_Latent_Diffusion_for_Behavior-Driven_Human_Motion_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.14304", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Delta Denoising Score", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://delta-denoising-score.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hertz_Delta_Denoising_Score_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.07090", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Mimic3D: Thriving 3D-Aware GANs via 3D-to-2D Imitation", + "base_url": null, + "title_page": null, + "github": "SeanChenxy/Mimic3D", + "web_page": null, + "github_page": "https://seanchenxy.github.io/Mimic3DWeb/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Mimic3D_Thriving_3D-Aware_GANs_via_3D-to-2D_Imitation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09036", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "DreamBooth3D: Subject-Driven Text-to-3D Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://dreambooth3d.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Raj_DreamBooth3D_Subject-Driven_Text-to-3D_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13508", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "kKVDrbfvOoA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Feature Proliferation - the \"Cancer\" in StyleGAN and its Treatments", + "base_url": null, + "title_page": null, + "github": "songc42/Feature-proliferation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_Feature_Proliferation_--_the_Cancer_in_StyleGAN_and_its_Treatments_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.08921", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "aXiGRakMu3k", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Unsupervised Facial Performance Editing via Vector-Quantized StyleGAN Representations", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kicanaoglu_Unsupervised_Facial_Performance_Editing_via_Vector-Quantized_StyleGAN_Representations_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "3D-Aware Image Generation using 2D Diffusion Models", + "base_url": null, + "title_page": null, + "github": "JeffreyXiang/ivid", + "web_page": null, + "github_page": "https://jeffreyxiang.github.io/ivid/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiang_3D-aware_Image_Generation_using_2D_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17905", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Neural Collage Transfer: Artistic Reconstruction via Material Manipulation", + "base_url": null, + "title_page": null, + "github": "northadventure/CollageRL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Neural_Collage_Transfer_Artistic_Reconstruction_via_Material_Manipulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2311.02202", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption", + "base_url": null, + "title_page": null, + "github": "sjtuplayer/few-shot-diffusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_Phasic_Content_Fusing_Diffusion_Model_with_Directional_Distribution_Consistency_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03729", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction", + "base_url": null, + "title_page": null, + "github": "Lakonik/SSDNeRF", + "web_page": null, + "github_page": "https://lakonik.github.io/ssdnerf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Single-Stage_Diffusion_NeRF_A_Unified_Approach_to_3D_Generation_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06714", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Erasing Concepts from Diffusion Models", + "base_url": null, + "title_page": null, + "github": "rohitgandikota/erasing", + "web_page": "https://erasing.baulab.info/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gandikota_Erasing_Concepts_from_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.07345", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding", + "base_url": null, + "title_page": null, + "github": "jiangyzy/GOAE", + "web_page": null, + "github_page": "https://eg3d-goae.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yuan_Make_Encoder_Great_Again_in_3D_GAN_Inversion_through_Geometry_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12326", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "CptQDMqM9Pc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + }, + { + "title": "HairNeRF: Geometry-Aware Image Synthesis for Hairstyle Transfer", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chang_HairNeRF_Geometry-Aware_Image_Synthesis_for_Hairstyle_Transfer_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Neural Generative Models" + } +] \ No newline at end of file diff --git a/json_data/2023/main/object-pose-estimation-and-tracking.json b/json_data/2023/main/object-pose-estimation-and-tracking.json new file mode 100644 index 0000000..15d372f --- /dev/null +++ b/json_data/2023/main/object-pose-estimation-and-tracking.json @@ -0,0 +1,434 @@ +[ + { + "title": "MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency", + "base_url": null, + "title_page": null, + "github": "Mumuqiao/MixCycle", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_MixCycle_Mixup_Assisted_Semi-Supervised_3D_Single_Object_Tracking_with_Cycle_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09219", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimation", + "base_url": null, + "title_page": null, + "github": "junzastar/DFTr_Voting", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Deep_Fusion_Transformer_Network_with_Weighted_Vector-Wise_Keypoints_Voting_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05438", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "IST-Net: Prior-Free Category-Level Pose Estimation with Implicit Space Transformation", + "base_url": null, + "title_page": null, + "github": "CVMI-Lab/IST-Net", + "web_page": "https://sites.google.com/view/cvmi-ist-net/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_IST-Net_Prior-Free_Category-Level_Pose_Estimation_with_Implicit_Space_Transformation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13479", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Adaptive and Background-Aware Vision Transformer for Real-Time UAV Tracking", + "base_url": null, + "title_page": null, + "github": "xyyang317/Aba-ViTrack", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Adaptive_and_Background-Aware_Vision_Transformer_for_Real-Time_UAV_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "VI-Net: Boosting Category-Level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations", + "base_url": null, + "title_page": null, + "github": "JiehongLin/VI-Net", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_VI-Net_Boosting_Category-level_6D_Object_Pose_Estimation_via_Learning_Decoupled_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09916", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Tracking by Natural Language Specification with Long Short-Term Context Decoupling", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Tracking_by_Natural_Language_Specification_with_Long_Short-term_Context_Decoupling_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network", + "base_url": null, + "title_page": null, + "github": "RuyiLian/CheckerPose", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lian_CheckerPose_Progressive_Dense_Keypoint_Localization_for_Object_Pose_Estimation_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16874", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Deep Active Contours for Real-Time 6-DoF Object Tracking", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://zju3dv.github.io/deep_ac/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Deep_Active_Contours_for_Real-time_6-DoF_Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Learning_Symmetry-Aware_Geometry_Correspondences_for_6D_Object_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Query6DoF: Learning Sparse Queries as Implicit Shape Prior for Category-Level 6DoF Pose Estimation", + "base_url": null, + "title_page": null, + "github": "hustvl/Query6DoF", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Query6DoF_Learning_Sparse_Queries_as_Implicit_Shape_Prior_for_Category-Level_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "SOCS: Semantically-Aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations", + "base_url": null, + "title_page": null, + "github": "wanboyan/SOCS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wan_SOCS_Semantically-Aware_Object_Coordinate_Space_for_Category-Level_6D_Object_Pose_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10346", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation", + "base_url": null, + "title_page": null, + "github": "YangHai-1218/PseudoFlow", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hai_Pseudo_Flow_Consistency_for_Self-Supervised_6D_Object_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10016", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "wjm4hLTn5Bw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Tracking by 3D Model Estimation of Unknown Objects in Videos", + "base_url": null, + "title_page": null, + "github": "rozumden/tracking-by-3d", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rozumnyi_Tracking_by_3D_Model_Estimation_of_Unknown_Objects_in_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06419", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "fpY9B3ruJ7E", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Algebraically Rigorous Quaternion Framework for the Neural Network Pose Estimation Problem", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Algebraically_Rigorous_Quaternion_Framework_for_the_Neural_Network_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation", + "base_url": null, + "title_page": null, + "github": "fulliu/lc", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Linear-Covariance_Loss_for_End-to-End_Learning_of_6D_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11516", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + }, + { + "title": "Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction", + "base_url": null, + "title_page": null, + "github": "cvg/VP-Estimation-with-Prior-Gravity", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pautrat_Vanishing_Point_Estimation_in_Uncalibrated_Images_with_Prior_Gravity_Direction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10694", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Object Pose Estimation and Tracking" + } +] \ No newline at end of file diff --git a/json_data/2023/main/photogrammetry-and-remote-sensing.json b/json_data/2023/main/photogrammetry-and-remote-sensing.json new file mode 100644 index 0000000..bd93bff --- /dev/null +++ b/json_data/2023/main/photogrammetry-and-remote-sensing.json @@ -0,0 +1,299 @@ +[ + { + "title": "Re:PolyWorld - A Graph Neural Network for Polygonal Scene Parsing", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zorzi_RePolyWorld_-_A_Graph_Neural_Network_for_Polygonal_Scene_Parsing_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + }, + { + "title": "SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://satlas-pretrain.allen.ai/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bastani_SatlasPretrain_A_Large-Scale_Dataset_for_Remote_Sensing_Image_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.15660", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + }, + { + "title": "Large-Scale Land Cover Mapping with Fine-Grained Classes via Class-Aware Semi-Supervised Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Large-Scale_Land_Cover_Mapping_with_Fine-Grained_Classes_via_Class-Aware_Semi-Supervised_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + }, + { + "title": "Large Selective Kernel Network for Remote Sensing Object Detection", + "base_url": null, + "title_page": null, + "github": "zcablii/LSKNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Large_Selective_Kernel_Network_for_Remote_Sensing_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09030", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + }, + { + "title": "Towards Geospatial Foundation Models via Continual Pretraining", + "base_url": null, + "title_page": null, + "github": "mmendiet/GFM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mendieta_Towards_Geospatial_Foundation_Models_via_Continual_Pretraining_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.04476", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + }, + { + "title": "Regularized Primitive Graph Learning for Unified Vector Mapping", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Regularized_Primitive_Graph_Learning_for_Unified_Vector_Mapping_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.13963", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + }, + { + "title": "Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery", + "base_url": null, + "title_page": null, + "github": "Hengwei-Zhao96/T-HOneCls", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Class_Prior-Free_Positive-Unlabeled_Learning_with_Taylor_Variational_Loss_for_Hyperspectral_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.15081", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + }, + { + "title": "MapFormer: Boosting Change Detection by using Pre-Change Information", + "base_url": null, + "title_page": null, + "github": "mxbh/mapformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bernhard_MapFormer_Boosting_Change_Detection_by_Using_Pre-change_Information_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17859", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + }, + { + "title": "Sample4Geo: Hard Negative Sampling for Cross-View Geo-Localisation", + "base_url": null, + "title_page": null, + "github": "Skyy93/Sample4Geo", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Deuser_Sample4Geo_Hard_Negative_Sampling_For_Cross-View_Geo-Localisation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11851", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + }, + { + "title": "PanFlowNet: A Flow-based Deep Network for Pan-Sharpening", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_PanFlowNet_A_Flow-Based_Deep_Network_for_Pan-Sharpening_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.07774", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + }, + { + "title": "Seeing Beyond the Patch: Scale-Adaptive Semantic Segmentation of High-Resolution Remote Sensing Imagery based on Reinforcement Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Seeing_Beyond_the_Patch_Scale-Adaptive_Semantic_Segmentation_of_High-resolution_Remote_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.15372", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Photogrammetry and Remote Sensing" + } +] \ No newline at end of file diff --git a/json_data/2023/main/privacy-security-fairness-and-explainability.json b/json_data/2023/main/privacy-security-fairness-and-explainability.json new file mode 100644 index 0000000..cd5d93e --- /dev/null +++ b/json_data/2023/main/privacy-security-fairness-and-explainability.json @@ -0,0 +1,218 @@ +[ + { + "title": "Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction", + "base_url": null, + "title_page": null, + "github": "WenjiaWang0312/Zolly", + "web_page": null, + "github_page": "https://wenjiawang0312.github.io/projects/zolly/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Zolly_Zoom_Focal_Length_Correctly_for_Perspective-Distorted_Human_Mesh_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13796", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Privacy, Security, Fairness, and Explainability" + }, + { + "title": "ACLS: Adaptive and Conditional Label Smoothing for Network Calibration", + "base_url": null, + "title_page": null, + "github": "cvlab-yonsei/ACLS", + "web_page": null, + "github_page": "https://cvlab.yonsei.ac.kr/projects/ACLS/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_ACLS_Adaptive_and_Conditional_Label_Smoothing_for_Network_Calibration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11911", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Privacy, Security, Fairness, and Explainability" + }, + { + "title": "PGFed: Personalize Each Client's Global Objective for Federated Learning", + "base_url": null, + "title_page": null, + "github": "ljaiverson/pgfed", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_PGFed_Personalize_Each_Clients_Global_Objective_for_Federated_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.01448", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Privacy, Security, Fairness, and Explainability" + }, + { + "title": "Overwriting Pretrained Bias with Finetuning Data", + "base_url": null, + "title_page": null, + "github": "princetonvisualai/overcoming-pretraining-bias", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Overwriting_Pretrained_Bias_with_Finetuning_Data_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06167", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": "https://www.researchgate.net/publication/369199104_Overcoming_Bias_in_Pretrained_Models_by_Manipulating_the_Finetuning_Dataset", + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Privacy, Security, Fairness, and Explainability" + }, + { + "title": "ITI-GEN: Inclusive Text-to-Image Generation", + "base_url": null, + "title_page": null, + "github": "humansensinglab/ITI-GEN", + "web_page": null, + "github_page": "https://czhang0528.github.io/iti-gen", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_ITI-GEN_Inclusive_Text-to-Image_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05569", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Privacy, Security, Fairness, and Explainability" + }, + { + "title": "FunnyBirds: A Synthetic Vision Dataset for a Part-based Analysis of Explainable AI Methods", + "base_url": null, + "title_page": null, + "github": "visinf/funnybirds", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hesse_FunnyBirds_A_Synthetic_Vision_Dataset_for_a_Part-Based_Analysis_of_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06248", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Privacy, Security, Fairness, and Explainability" + }, + { + "title": "X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events", + "base_url": null, + "title_page": null, + "github": "daibopku/X-VoE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dai_X-VoE_Measuring_eXplanatory_Violation_of_Expectation_in_Physical_Events_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10441", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Privacy, Security, Fairness, and Explainability" + }, + { + "title": "Adaptive Testing of Computer Vision Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_Adaptive_Testing_of_Computer_Vision_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.02774", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Privacy, Security, Fairness, and Explainability" + } +] \ No newline at end of file diff --git a/json_data/2023/main/recognition-categorization.json b/json_data/2023/main/recognition-categorization.json new file mode 100644 index 0000000..10c3cf4 --- /dev/null +++ b/json_data/2023/main/recognition-categorization.json @@ -0,0 +1,1352 @@ +[ + { + "title": "Cross Contrasting Feature Perturbation for Domain Generalization", + "base_url": null, + "title_page": null, + "github": "hackmebroo/CCFP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Cross_Contrasting_Feature_Perturbation_for_Domain_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12502", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_Flexible_Visual_Recognition_by_Evidential_Modeling_of_Confusion_and_Ignorance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.07403", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Abdelfattah_CDUL_CLIP-Driven_Unsupervised_Learning_for_Multi-Label_Image_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16634", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "RankMixup: Ranking-based Mixup Training for Network Calibration", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://cvlab.yonsei.ac.kr/projects/RankMixup/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Noh_RankMixup_Ranking-Based_Mixup_Training_for_Network_Calibration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11990", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Label-Noise Learning with Intrinsically Long-Tailed Data", + "base_url": null, + "title_page": null, + "github": "Wakings/TABASCO", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Label-Noise_Learning_with_Intrinsically_Long-Tailed_Data_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.09833", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Parallel Attention Interaction Network for Few-Shot Skeleton-based Action Recognition", + "base_url": null, + "title_page": null, + "github": "starrycos/PAINet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Parallel_Attention_Interaction_Network_for_Few-Shot_Skeleton-Based_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Rethinking Mobile Block for Efficient Attention-based Models", + "base_url": null, + "title_page": null, + "github": "zhangzjn/EMO", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Rethinking_Mobile_Block_for_Efficient_Attention-based_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.01146", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Read-Only Prompt Optimization for Vision-Language Few-Shot Learning", + "base_url": null, + "title_page": null, + "github": "mlvlab/RPO", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Read-only_Prompt_Optimization_for_Vision-Language_Few-shot_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14960", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Understanding Self-Attention Mechanism via Dynamical System Perspective", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Understanding_Self-attention_Mechanism_via_Dynamical_System_Perspective_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09939", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels", + "base_url": null, + "title_page": null, + "github": "wannature/COMIC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Learning_in_Imperfect_Environment_Multi-Label_Classification_with_Long-Tailed_Distribution_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.10539", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "What do Neural Networks Learn in Image Classification? A Frequency Shortcut Perspective", + "base_url": null, + "title_page": null, + "github": "nis-research/nn-frequency-shortcuts", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_What_do_neural_networks_learn_in_image_classification_A_frequency_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09829", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity", + "base_url": null, + "title_page": null, + "github": "ltong1130ztr/HAFrame", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_Inducing_Neural_Collapse_to_a_Fixed_Hierarchy-Aware_Frame_for_Reducing_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05689", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Unified Out-of-Distribution Detection: A Model-Specific Perspective", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Averly_Unified_Out-Of-Distribution_Detection_A_Model-Specific_Perspective_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06813", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "A Unified Framework for Robustness on Diverse Sampling Errors", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jeon_A_Unified_Framework_for_Robustness_on_Diverse_Sampling_Errors_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Scene-Aware Label Graph Learning for Multi-Label Image Classification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Scene-Aware_Label_Graph_Learning_for_Multi-Label_Image_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Holistic Label Correction for Noisy Multi-Label Classification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xia_Holistic_Label_Correction_for_Noisy_Multi-Label_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Strip-MLP: Efficient Token Interaction for Vision MLP", + "base_url": null, + "title_page": null, + "github": "Med-Process/Strip_MLP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Strip-MLP_Efficient_Token_Interaction_for_Vision_MLP_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11458", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "EQ-Net: Elastic Quantization Neural Networks", + "base_url": null, + "title_page": null, + "github": "xuke225/EQ-Net", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_EQ-Net_Elastic_Quantization_Neural_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07650", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Data-Free Knowledge Distillation for Fine-Grained Visual Categorization", + "base_url": null, + "title_page": null, + "github": "RoryShao/DFKD-FGVC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shao_Data-free_Knowledge_Distillation_for_Fine-grained_Visual_Categorization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Shift from Texture-Bias to Shape-Bias: Edge Deformation-based Augmentation for Robust Object Recognition", + "base_url": null, + "title_page": null, + "github": "C0notSilly/-ICCV-23-Edge-Deformation-based-Online-Augmentation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_Shift_from_Texture-bias_to_Shape-bias_Edge_Deformation-based_Augmentation_for_Robust_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognition", + "base_url": null, + "title_page": null, + "github": "leeisack/Latent-OFER", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Latent-OFER_Detect_Mask_and_Reconstruct_with_Latent_Vectors_for_Occluded_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11404", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "DR-Tune: Improving Fine-Tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration", + "base_url": null, + "title_page": null, + "github": "weeknan/DR-Tune", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_DR-Tune_Improving_Fine-tuning_of_Pretrained_Visual_Models_by_Distribution_Regularization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12058", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Understanding the Feature Norm for Out-of-Distribution Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_Understanding_the_Feature_Norm_for_Out-of-Distribution_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.05316", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Multi-View Active Fine-Grained Visual Recognition", + "base_url": null, + "title_page": null, + "github": "PRIS-CV/AFGR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Du_Multi-View_Active_Fine-Grained_Visual_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.01153", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-Trained Diffusion Models", + "base_url": null, + "title_page": null, + "github": "cure-lab/DiffGuard", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_DIFFGUARD_Semantic_Mismatch-Guided_Out-of-Distribution_Detection_Using_Pre-Trained_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07687", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Task-Aware Adaptive Learning for Cross-Domain Few-Shot Learning", + "base_url": null, + "title_page": null, + "github": "PRIS-CV/TA2-Net", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Task-aware_Adaptive_Learning_for_Cross-domain_Few-shot_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Improving Adversarial Robustness of Masked Autoencoders via Test-Time Frequency-Domain Prompting", + "base_url": null, + "title_page": null, + "github": "shikiw/RobustMAE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Improving_Adversarial_Robustness_of_Masked_Autoencoders_via_Test-time_Frequency-domain_Prompting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10315", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Saliency Regularization for Self-Training with Partial Annotations", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Saliency_Regularization_for_Self-Training_with_Partial_Annotations_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Learning Gabor Texture Features for Fine-Grained Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Learning_Gabor_Texture_Features_for_Fine-Grained_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05396", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding", + "base_url": null, + "title_page": null, + "github": "OpenGVLab/UniFormerV2", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_UniFormerV2_Unlocking_the_Potential_of_Image_ViTs_for_Video_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.09552", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "RankMatch: Fostering Confidence and Consistency in Learning with Noisy Labels", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_RankMatch_Fostering_Confidence_and_Consistency_in_Learning_with_Noisy_Labels_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "MetaGCD: Learning to Continually Learn in Generalized Category Discovery", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_MetaGCD_Learning_to_Continually_Learn_in_Generalized_Category_Discovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11063", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "FerKD: Surgical Label Adaptation for Efficient Distillation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shen_FerKD_Surgical_Label_Adaptation_for_Efficient_Distillation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Point-Query Quadtree for Crowd Counting, Localization, and more", + "base_url": null, + "title_page": null, + "github": "cxliu0/PET", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Point-Query_Quadtree_for_Crowd_Counting_Localization_and_More_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13814", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Nearest Neighbor Guidance for Out-of-Distribution Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_Nearest_Neighbor_Guidance_for_Out-of-Distribution_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Bayesian Optimization Meets Self-Distillation", + "base_url": null, + "title_page": null, + "github": "sooperset/boss", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Bayesian_Optimization_Meets_Self-Distillation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.12666", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "When Prompt-based Incremental Learning does not Meet Strong Pretraining", + "base_url": null, + "title_page": null, + "github": "TOM-tym/APG", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_When_Prompt-based_Incremental_Learning_Does_Not_Meet_Strong_Pretraining_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10445", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "When to Learn what: Model-Adaptive Data Augmentation Curriculum", + "base_url": null, + "title_page": null, + "github": "JackHck/MADAug", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hou_When_to_Learn_What_Model-Adaptive_Data_Augmentation_Curriculum_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04747", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Parametric Information Maximization for Generalized Category Discovery", + "base_url": null, + "title_page": null, + "github": "ThalesGroup/pim-generalized-category-discovery", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chiaroni_Parametric_Information_Maximization_for_Generalized_Category_Discovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.00334", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Boosting Few-Shot Action Recognition with Graph-Guided Hybrid Matching", + "base_url": null, + "title_page": null, + "github": "jiazheng-xing/GgHM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xing_Boosting_Few-shot_Action_Recognition_with_Graph-guided_Hybrid_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09346", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Domain Generalization via Rationale Invariance", + "base_url": null, + "title_page": null, + "github": "liangchen527/RIDG", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Domain_Generalization_via_Rationale_Invariance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11158", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Masked Spiking Transformer", + "base_url": null, + "title_page": null, + "github": "bic-L/Masked-Spiking-Transformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Masked_Spiking_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.01208", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Prototype Reminiscence and Augmented Asymmetric Knowledge Aggregation for Non-Exemplar Class-Incremental Learning", + "base_url": null, + "title_page": null, + "github": "ShiWuxuan/PRAKA", + "web_page": null, + "github_page": "https://shiwuxuan.github.io/PRAKA-project/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_Prototype_Reminiscence_and_Augmented_Asymmetric_Knowledge_Aggregation_for_Non-Exemplar_Class-Incremental_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "jNCvQN7SD9s", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Distilled Reverse Attention Network for Open-World Compositional Zero-Shot Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Distilled_Reverse_Attention_Network_for_Open-world_Compositional_Zero-Shot_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.00404", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Candidate-Aware Selective Disambiguation based on Normalized Entropy for Instance-Dependent Partial-Label Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_Candidate-aware_Selective_Disambiguation_Based_On_Normalized_Entropy_for_Instance-dependent_Partial-label_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No", + "base_url": null, + "title_page": null, + "github": "xmed-lab/CLIPN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_CLIPN_for_Zero-Shot_OOD_Detection_Teaching_CLIP_to_Say_No_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12213", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Self-Similarity Driven Scale-Invariant Learning for Weakly Supervised Person Search", + "base_url": null, + "title_page": null, + "github": "Wangbenzhi/SSL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Self-similarity_Driven_Scale-invariant_Learning_for_Weakly_Supervised_Person_Search_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.12986", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Sample-Wise Label Confidence Incorporation for Learning with Noisy Labels", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ahn_Sample-wise_Label_Confidence_Incorporation_for_Learning_with_Noisy_Labels_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples", + "base_url": null, + "title_page": null, + "github": "xiaoboxia/CoDis", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xia_Combating_Noisy_Labels_with_Sample_Selection_by_Mining_High-Discrepancy_Examples_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + }, + { + "title": "Spatial-Aware Token for Weakly Supervised Object Localization", + "base_url": null, + "title_page": null, + "github": "wpy1999/SAT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Spatial-Aware_Token_for_Weakly_Supervised_Object_Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10438", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Categorization" + } +] \ No newline at end of file diff --git a/json_data/2023/main/recognition-detection.json b/json_data/2023/main/recognition-detection.json new file mode 100644 index 0000000..f6abc9e --- /dev/null +++ b/json_data/2023/main/recognition-detection.json @@ -0,0 +1,1973 @@ +[ + { + "title": "Random Boxes are Open-World Object Detectors", + "base_url": null, + "title_page": null, + "github": "scuwyh2000/RandBox", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Random_Boxes_Are_Open-world_Object_Detectors_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08249", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection", + "base_url": null, + "title_page": null, + "github": "hustvl/MIMDet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_Unleashing_Vanilla_Vision_Transformer_with_Masked_Image_Modeling_for_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2204.02964", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations", + "base_url": null, + "title_page": null, + "github": "xmuqimingxia/CoIn", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xia_CoIn_Contrastive_Instance_Feature_Mining_for_Outdoor_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "A Dynamic Dual-Processing Object Detection Framework Inspired by the Brain's Recognition Mechanism", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_A_Dynamic_Dual-Processing_Object_Detection_Framework_Inspired_by_the_Brains_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Anchor-Intermediate Detector: Decoupling and Coupling Bounding Boxes for Accurate Object Detection", + "base_url": null, + "title_page": null, + "github": "YilongLv/AID", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lv_Anchor-Intermediate_Detector_Decoupling_and_Coupling_Bounding_Boxes_for_Accurate_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.05666", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Inter-Realization Channels: Unsupervised Anomaly Detection Beyond One-Class Classification", + "base_url": null, + "title_page": null, + "github": "DeclanMcIntosh/InReaCh", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/McIntosh_Inter-Realization_Channels_Unsupervised_Anomaly_Detection_Beyond_One-Class_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Deep Equilibrium Object Detection", + "base_url": null, + "title_page": null, + "github": "MCG-NJU/DEQDet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Deep_Equilibrium_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09564", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "RecursiveDet: End-to-End Region-based Recursive Object Detection", + "base_url": null, + "title_page": null, + "github": "bravezzzzzz/RecursiveDet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_RecursiveDet_End-to-End_Region-Based_Recursive_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13619", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Small Object Detection via Coarse-to-Fine Proposal Generation and Imitation Learning", + "base_url": null, + "title_page": null, + "github": "shaunyuan22/CFINet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yuan_Small_Object_Detection_via_Coarse-to-fine_Proposal_Generation_and_Imitation_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09534", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation", + "base_url": null, + "title_page": null, + "github": "iSEE-Laboratory/ASAG", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fu_ASAG_Building_Strong_One-Decoder-Layer_Sparse_Detectors_via_Adaptive_Sparse_Anchor_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09242", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts", + "base_url": null, + "title_page": null, + "github": "alibaba/easyrobust", + "web_page": null, + "github_page": "https://github.com/alibaba/easyrobust/tree/main/benchmarks/coco_o", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mao_COCO-O_A_Benchmark_for_Object_Detectors_under_Natural_Distribution_Shifts_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12730", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Generative Prompt Model for Weakly Supervised Object Localization", + "base_url": null, + "title_page": null, + "github": "callsys/GenPromp", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Generative_Prompt_Model_for_Weakly_Supervised_Object_Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09756", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lao_UniKD_Universal_Knowledge_Distillation_for_Mimicking_Homogeneous_or_Heterogeneous_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "PNI: Industrial Anomaly Detection using Position and Neighborhood Information", + "base_url": null, + "title_page": null, + "github": "wogur110/PNI_Anomaly_Detection", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bae_PNI__Industrial_Anomaly_Detection_using_Position_and_Neighborhood_Information_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.12634", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Masked Autoencoders are Stronger Knowledge Distillers", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lao_Masked_Autoencoders_Are_Stronger_Knowledge_Distillers_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "GPA-3D: Geometry-Aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds", + "base_url": null, + "title_page": null, + "github": "Liz66666/GPA3D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_GPA-3D_Geometry-aware_Prototype_Alignment_for_Unsupervised_Domain_Adaptive_3D_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08140", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "ADNet: Lane Shape Prediction via Anchor Decomposition", + "base_url": null, + "title_page": null, + "github": "Sephirex-X/ADNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiao_ADNet_Lane_Shape_Prediction_via_Anchor_Decomposition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10481", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Periodically Exchange Teacher-Student for Source-Free Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Periodically_Exchange_Teacher-Student_for_Source-Free_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Towards Fair and Comprehensive Comparisons for Image-based 3D Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Towards_Fair_and_Comprehensive_Comparisons_for_Image-Based_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.05447", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://xianpeng919.github.io/monoxiver/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Monocular_3D_Object_Detection_with_Bounding_Box_Denoising_in_3D_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01289", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Template-Guided Hierarchical Feature Restoration for Anomaly Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Template-guided_Hierarchical_Feature_Restoration_for_Anomaly_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "ALWOD: Active Learning for Weakly-Supervised Object Detection", + "base_url": null, + "title_page": null, + "github": "seqam-lab/ALWOD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_ALWOD_Active_Learning_for_Weakly-Supervised_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.07914", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "ProtoFL: Unsupervised Federated Learning via Prototypical Distillation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_ProtoFL_Unsupervised_Federated_Learning_via_Prototypical_Distillation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12450", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Efficient Adaptive Human-Object Interaction Detection with Concept-Guided Memory", + "base_url": null, + "title_page": null, + "github": "ltttpku/ADA-CM", + "web_page": null, + "github_page": "https://ltttpku.github.io/ADA-CM/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lei_Efficient_Adaptive_Human-Object_Interaction_Detection_with_Concept-guided_Memory_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03696", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Detection Transformer with Stable Matching", + "base_url": null, + "title_page": null, + "github": "IDEA-Research/Stable-DINO", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Detection_Transformer_with_Stable_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.04742", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection", + "base_url": null, + "title_page": null, + "github": "hikvision-research/opera", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Distilling_DETR_with_Visual-Linguistic_Knowledge_for_Open-Vocabulary_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Anomaly Detection Under Distribution Shift", + "base_url": null, + "title_page": null, + "github": "mala-lab/ADShift", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Anomaly_Detection_Under_Distribution_Shift_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13845", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Detecting Objects with Context-Likelihood Graphs and Graph Refinement", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bhowmik_Detecting_Objects_with_Context-Likelihood_Graphs_and_Graph_Refinement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.12395", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Unsupervised Object Localization with Representer Point Selection", + "base_url": null, + "title_page": null, + "github": "yeonghwansong/UOLwRPS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_Unsupervised_Object_Localization_with_Representer_Point_Selection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04172", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "DETR does not Need Multi-Scale or Locality Design", + "base_url": null, + "title_page": null, + "github": "impiga/Plain-DETR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_DETR_Does_Not_Need_Multi-Scale_or_Locality_Design_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.01904", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Deep Directly-Trained Spiking Neural Networks for Object Detection", + "base_url": null, + "title_page": null, + "github": "BICLab/EMS-YOLO", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Su_Deep_Directly-Trained_Spiking_Neural_Networks_for_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11411", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data", + "base_url": null, + "title_page": null, + "github": "dschinagl/gace", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Schinagl_GACE_Geometry_Aware_Confidence_Enhancement_for_Black-Box_3D_Object_Detectors_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.20319", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "StageInteractor: Query-based Object Detector with Cross-Stage Interaction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Teng_StageInteractor_Query-based_Object_Detector_with_Cross-stage_Interaction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.04978", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Adaptive Rotated Convolution for Rotated Object Detection", + "base_url": null, + "title_page": null, + "github": "LeapLabTHU/ARC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pu_Adaptive_Rotated_Convolution_for_Rotated_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.07820", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Decoupled_DETR_Spatially_Disentangling_Localization_and_Classification_for_Improved_End-to-End_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.15955", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Exploring Transformers for Open-World Instance Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Exploring_Transformers_for_Open-world_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04206", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "DDG-Net: Discriminability-Driven Graph Network for Weakly-Supervised Temporal Action Localization", + "base_url": null, + "title_page": null, + "github": "XiaojunTang22/ICCV2023-DDGNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_DDG-Net_Discriminability-Driven_Graph_Network_for_Weakly-supervised_Temporal_Action_Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16415", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment", + "base_url": null, + "title_page": null, + "github": "Atten4Vis/GroupDETR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Group_DETR_Fast_DETR_Training_with_Group-Wise_One-to-Many_Assignment_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2207.13085", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Category-Aware Allocation Transformer for Weakly Supervised Object Localization", + "base_url": null, + "title_page": null, + "github": "zhiweichen0012/CATR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Category-aware_Allocation_Transformer_for_Weakly_Supervised_Object_Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "The Devil is in the Crack Orientation: A New Perspective for Crack Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_The_Devil_is_in_the_Crack_Orientation_A_New_Perspective_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Clusterformer: Cluster-based Transformer for 3D Object Detection in Point Clouds", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pei_Clusterformer_Cluster-based_Transformer_for_3D_Object_Detection_in_Point_Clouds_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Less is more: Focus Attention for Efficient DETR", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://github.com/huawei-noah/noah-research/tree/master/Focus-DETR", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Less_is_More_Focus_Attention_for_Efficient_DETR_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12612", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "DFA3D: 3D Deformable Attention for 2D-to-3D Feature Lifting", + "base_url": null, + "title_page": null, + "github": "IDEA-Research/3D-deformable-attention", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_DFA3D_3D_Deformable_Attention_For_2D-to-3D_Feature_Lifting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12972", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Multi-Label Self-Supervised Learning with Scene Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Multi-Label_Self-Supervised_Learning_with_Scene_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03286", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Cascade-DETR: Delving into High-Quality Universal Object Detection", + "base_url": null, + "title_page": null, + "github": "SysCV/cascade-detr", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_Cascade-DETR_Delving_into_High-Quality_Universal_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11035", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Representation Disparity-Aware Distillation for 3D Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Representation_Disparity-aware_Distillation_for_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10308", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hashmi_FeatEnHancer_Enhancing_Hierarchical_Features_for_Object_Detection_and_Beyond_Under_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03594", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "DetZero: Rethinking Offboard 3D Object Detection with Long-Term Sequential Point Clouds", + "base_url": null, + "title_page": null, + "github": "PJLab-ADG/DetZero", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_DetZero_Rethinking_Offboard_3D_Object_Detection_with_Long-term_Sequential_Point_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.06023", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "DETRs with Collaborative Hybrid Assignments Training", + "base_url": null, + "title_page": null, + "github": "Sense-X/Co-DETR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zong_DETRs_with_Collaborative_Hybrid_Assignments_Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.12860", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Open-Vocabulary Object Detection with an Open Corpus", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Open-Vocabulary_Object_Detection_With_an_Open_Corpus_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-Positive Mining", + "base_url": null, + "title_page": null, + "github": "saksham-s/SparseDet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Suri_SparseDet_Improving_Sparsely_Annotated_Object_Detection_with_Pseudo-positive_Mining_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2201.04620", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model", + "base_url": null, + "title_page": null, + "github": "Loco-Roco/DiffAD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Unsupervised_Surface_Anomaly_Detection_with_Diffusion_Probabilistic_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation", + "base_url": null, + "title_page": null, + "github": "Haiyang-W/UniTR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_UniTR_A_Unified_and_Efficient_Multi-Modal_Transformer_for_Birds-Eye-View_Representation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07732", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection", + "base_url": null, + "title_page": null, + "github": "xcyao00/FOD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yao_Focus_the_Discrepancy_Intra-_and_Inter-Correlation_Learning_for_Image_Anomaly_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.02983", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "MonoNeRD: NeRF-Like Representations for Monocular 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "cskkxjk/MonoNeRD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_MonoNeRD_NeRF-like_Representations_for_Monocular_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09421", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Integrally Migrating Pre-Trained Transformer Encoder-Decoders for Visual Object Detection", + "base_url": null, + "title_page": null, + "github": "LiewFeng/imTED", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Integrally_Migrating_Pre-trained_Transformer_Encoder-decoders_for_Visual_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2205.09613", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Generating Dynamic Kernels via Transformers for Lane Detection", + "base_url": null, + "title_page": null, + "github": "czyczyyzc/CondLSTR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Generating_Dynamic_Kernels_via_Transformers_for_Lane_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Meta-ZSDETR: Zero-Shot DETR with Meta-Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Meta-ZSDETR_Zero-shot_DETR_with_Meta-learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09540", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes", + "base_url": null, + "title_page": null, + "github": "ucas-vg/PointTinyBenchmark", + "web_page": null, + "github_page": "https://github.com/ucas-vg/PointTinyBenchmark/tree/SSD-Det", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Spatial_Self-Distillation_for_Object_Detection_with_Inaccurate_Bounding_Boxes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12101", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "AlignDet: Aligning Pre-Training and Fine-Tuning in Object Detection", + "base_url": null, + "title_page": null, + "github": "liming-ai/AlignDet", + "web_page": null, + "github_page": "https://liming-ai.github.io/AlignDet", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_AlignDet_Aligning_Pre-training_and_Fine-tuning_in_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11077", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "MULLER: Multilayer Laplacian Resizer for Vision", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://github.com/google-research/google-research/tree/master/muller", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tu_MULLER_Multilayer_Laplacian_Resizer_for_Vision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02859", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Unilaterally_Aggregated_Contrastive_Learning_with_Hierarchical_Augmentation_for_Anomaly_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10155", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "DETRDistill: A Universal Knowledge Distillation Framework for DETR-Families", + "base_url": null, + "title_page": null, + "github": "BIVLab-USTC/DETRDistill", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chang_DETRDistill_A_Universal_Knowledge_Distillation_Framework_for_DETR-families_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.10156", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Delving into Motion-Aware Matching for Monocular 3D Object Tracking", + "base_url": null, + "title_page": null, + "github": "kuanchihhuang/MoMA-M3T", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Delving_into_Motion-Aware_Matching_for_Monocular_3D_Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11607", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "FB-BEV: BEV Representation from Forward-Backward View Transformations", + "base_url": null, + "title_page": null, + "github": "NVlabs/FB-BEV", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_FB-BEV_BEV_Representation_from_Forward-Backward_View_Transformations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.02236", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Learning from Noisy Data for Semi-Supervised 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "zehuichen123/NoiseDet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Learning_from_Noisy_Data_for_Semi-Supervised_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Boosting Long-Tailed Object Detection via Step-Wise Learning on Smooth-Tail Data", + "base_url": null, + "title_page": null, + "github": "dongnana777/Long-tailed-object-detection", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Boosting_Long-tailed_Object_Detection_via_Step-wise_Learning_on_Smooth-tail_Data_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.12833", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Objects do not Disappear: Video Object Detection by Single-Frame Object Location Anticipation", + "base_url": null, + "title_page": null, + "github": "L-KID/Video-object-detection-by-location-anticipation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Objects_Do_Not_Disappear_Video_Object_Detection_by_Single-Frame_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04770", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Unified Visual Relationship Detection with Vision and Language Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://github.com/google-research/scenic/tree/main/scenic/projects/univrd", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Unified_Visual_Relationship_Detection_with_Vision_and_Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08998", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Universal Domain Adaptation via Compressive Attention Matching", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Universal_Domain_Adaptation_via_Compressive_Attention_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.11862", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Unsupervised Domain Adaptive Detection with Network Stability Analysis", + "base_url": null, + "title_page": null, + "github": "tiankongzhang/NSA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Unsupervised_Domain_Adaptive_Detection_with_Network_Stability_Analysis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08182", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "ImGeoNet: Image-Induced Geometry-Aware Voxel Representation for Multi-View 3D Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://ttaoretw.github.io/imgeonet/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tu_ImGeoNet_Image-induced_Geometry-aware_Voxel_Representation_for_Multi-view_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09098", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + }, + { + "title": "Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection", + "base_url": null, + "title_page": null, + "github": "Yinyf0804/WSOD-CBL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yin_Cyclic-Bootstrap_Labeling_for_Weakly_Supervised_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05991", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Detection" + } +] \ No newline at end of file diff --git a/json_data/2023/main/recognition-retrieval.json b/json_data/2023/main/recognition-retrieval.json new file mode 100644 index 0000000..d4167f6 --- /dev/null +++ b/json_data/2023/main/recognition-retrieval.json @@ -0,0 +1,839 @@ +[ + { + "title": "Unsupervised Feature Representation Learning for Domain-Generalized Cross-Domain Image Retrieval", + "base_url": null, + "title_page": null, + "github": "conghui1002/DG-UCDIR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_Unsupervised_Feature_Representation_Learning_for_Domain-generalized_Cross-domain_Image_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "DEDRIFT: Robust Similarity Search under Content Drift", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Baranchuk_DEDRIFT_Robust_Similarity_Search_under_Content_Drift_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.02752", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Global Features are All You Need for Image Retrieval and Reranking", + "base_url": null, + "title_page": null, + "github": "ShihaoShao-GH/SuperGlobal", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shao_Global_Features_are_All_You_Need_for_Image_Retrieval_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06954", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "HSE: Hybrid Species Embedding for Deep Metric Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_HSE_Hybrid_Species_Embedding_for_Deep_Metric_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Discrepant and Multi-Instance Proxies for Unsupervised Person Re-Identification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zou_Discrepant_and_Multi-Instance_Proxies_for_Unsupervised_Person_Re-Identification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Towards Grand Unified Representation Learning for Unsupervised Visible-Infrared Person Re-Identification", + "base_url": null, + "title_page": null, + "github": "yangbincv/GUR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Towards_Grand_Unified_Representation_Learning_for_Unsupervised_Visible-Infrared_Person_Re-Identification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition", + "base_url": null, + "title_page": null, + "github": "gmberton/EigenPlaces", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Berton_EigenPlaces_Training_Viewpoint_Robust_Models_for_Visual_Place_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10832", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Simple Baselines for Interactive Video Retrieval with Questions and Answers", + "base_url": null, + "title_page": null, + "github": "kevinliang888/IVR-QA-baselines", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_Simple_Baselines_for_Interactive_Video_Retrieval_with_Questions_and_Answers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10402", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Fan-Beam Binarization Difference Projection (FB-BDP): A Novel Local Object Descriptor for Fine-Grained Leaf Image Retrieval", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Fan-Beam_Binarization_Difference_Projection_FB-BDP_A_Novel_Local_Object_Descriptor_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Conditional Cross Attention Network for Multi-Space Embedding without Entanglement in Only a SINGLE Network", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_Conditional_Cross_Attention_Network_for_Multi-Space_Embedding_without_Entanglement_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13254", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Learning Concordant Attention via Target-Aware Alignment for Visible-Infrared Person Re-Identification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Learning_Concordant_Attention_via_Target-aware_Alignment_for_Visible-Infrared_Person_Re-identification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Person Re-Identification without Identification via Event Anonymization", + "base_url": null, + "title_page": null, + "github": "IIT-PAVIS/ReId_without_Id", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ahmad_Person_Re-Identification_without_Identification_via_Event_anonymization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04402", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Divide&Classify: Fine-Grained Classification for City-Wide Visual Geo-Localization", + "base_url": null, + "title_page": null, + "github": "ga1i13o/Divide-and-Classify", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Trivigno_DivideClassify_Fine-Grained_Classification_for_City-Wide_Visual_Geo-Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning", + "base_url": null, + "title_page": null, + "github": "mohwald/gandtr", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mohwald_Dark_Side_Augmentation_Generating_Diverse_Night_Examples_for_Metric_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16351", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "zlT-GJOcgYw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guan_PIDRo_Parallel_Isomeric_Attention_with_Dynamic_Routing_for_Text-Video_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Unified Pre-Training with Pseudo Texts for Text-to-Image Person Re-Identification", + "base_url": null, + "title_page": null, + "github": "ZhiyinShao-H/UniPT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shao_Unified_Pre-Training_with_Pseudo_Texts_for_Text-To-Image_Person_Re-Identification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01420", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Modality Unifying Network for Visible-Infrared Person Re-Identification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Modality_Unifying_Network_for_Visible-Infrared_Person_Re-Identification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.06262", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change", + "base_url": null, + "title_page": null, + "github": "PengBoXiangShang/deepchange", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_DeepChange_A_Long-Term_Person_Re-Identification_Benchmark_with_Clothes_Change_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval", + "base_url": null, + "title_page": null, + "github": "ChiYeungLaw/LexLIP-ICCV23", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_LexLIP_Lexicon-Bottlenecked_Language-Image_Pre-Training_for_Large-Scale_Image-Text_Sparse_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.02908", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification", + "base_url": null, + "title_page": null, + "github": "XiangboYin/DPIS_USVLReID", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_Dual_Pseudo-Labels_Interactive_Self-Training_for_Semi-Supervised_Visible-Infrared_Person_Re-Identification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "BT2: Backward-Compatible Training with Basis Transformation", + "base_url": null, + "title_page": null, + "github": "YifeiZhou02/BT-2", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_BT2_Backward-compatible_Training_with_Basis_Transformation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.03989", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Prototypical Mixing and Retrieval-based Refinement for Label Noise-Resistant Image Retrieval", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Prototypical_Mixing_and_Retrieval-Based_Refinement_for_Label_Noise-Resistant_Image_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Learning Spatial-Context-Aware Global Visual Feature Representation for Instance Image Retrieval", + "base_url": null, + "title_page": null, + "github": "Zy-Zhang/SpCa", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Learning_Spatial-context-aware_Global_Visual_Feature_Representation_for_Instance_Image_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval", + "base_url": null, + "title_page": null, + "github": "bassyess/CFCD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Coarse-to-Fine_Learning_Compact_Discriminative_Representation_for_Single-Stage_Image_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04008", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Visible-Infrared Person Re-Identification via Semantic Alignment and Affinity Inference", + "base_url": null, + "title_page": null, + "github": "xiaoye-hhh/SAAI", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_Visible-Infrared_Person_Re-Identification_via_Semantic_Alignment_and_Affinity_Inference_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Part-Aware Transformer for Generalizable Person Re-Identification", + "base_url": null, + "title_page": null, + "github": "liyuke65535/Part-Aware-Transformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ni_Part-Aware_Transformer_for_Generalizable_Person_Re-identification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03322", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://cmp.felk.cvut.cz/univ_emb/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ypsilantis_Towards_Universal_Image_Embeddings_A_Large-Scale_Dataset_and_Challenge_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01858", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video Retrieval", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Dual_Learning_with_Dynamic_Knowledge_Distillation_for_Partially_Relevant_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "Fine-Grained Unsupervised Domain Adaptation for Gait Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Fine-grained_Unsupervised_Domain_Adaptation_for_Gait_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "TsWfYqz8qbk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "FashionNTM: Multi-Turn Fashion Image Retrieval via Cascaded Memory", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://sites.google.com/eng.ucsd.edu/fashionntm", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pal_FashionNTM_Multi-turn_Fashion_Image_Retrieval_via_Cascaded_Memory_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10170", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + }, + { + "title": "CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition", + "base_url": null, + "title_page": null, + "github": "rayguan97/crossloc3d", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guan_CrossLoc3D_Aerial-Ground_Cross-Source_3D_Place_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17778", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition: Retrieval" + } +] \ No newline at end of file diff --git a/json_data/2023/main/recognition-segmentation-and-shape-analysis.json b/json_data/2023/main/recognition-segmentation-and-shape-analysis.json new file mode 100644 index 0000000..c669bc7 --- /dev/null +++ b/json_data/2023/main/recognition-segmentation-and-shape-analysis.json @@ -0,0 +1,326 @@ +[ + { + "title": "Segment Anything", + "base_url": null, + "title_page": null, + "github": "facebookresearch/segment-anything", + "web_page": "https://segment-anything.com/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kirillov_Segment_Anything_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02643", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "Shape Analysis of Euclidean Curves under Frenet-Serret Framework", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chassat_Shape_Analysis_of_Euclidean_Curves_under_Frenet-Serret_Framework_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "Unmasking Anomalies in Road-Scene Segmentation", + "base_url": null, + "title_page": null, + "github": "shyam671/Mask2Anomaly-Unmasking-Anomalies-in-Road-Scene-Segmentation", + "web_page": null, + "github_page": null, + "colab": "https://colab.research.google.com/drive/1iMF5lWj3J8zlIJFkekXC3ipQo2semJfL?usp=sharing", + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nandan_Unmasking_Anomalies_in_Road-Scene_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13316", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "High Quality Entity Segmentation", + "base_url": null, + "title_page": null, + "github": "qqlu/Entity", + "web_page": null, + "github_page": "http://luqi.info/entityv2.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qi_High_Quality_Entity_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.05776", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "Towards Open-Vocabulary Video Instance Segmentation", + "base_url": null, + "title_page": null, + "github": "haochenheheda/LVVIS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Towards_Open-Vocabulary_Video_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01715", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "Beyond One-to-One: Rethinking the Referring Image Segmentation", + "base_url": null, + "title_page": null, + "github": "toggle1995/RIS-DMMI", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_Beyond_One-to-One_Rethinking_the_Referring_Image_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13853", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "Multiple Instance Learning Framework with Masked Hard Instance Mining for whole Slide Image Classification", + "base_url": null, + "title_page": null, + "github": "DearCaat/MHIM-MIL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_Multiple_Instance_Learning_Framework_with_Masked_Hard_Instance_Mining_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15254", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning", + "base_url": null, + "title_page": null, + "github": "bair-climate-initiative/scale-mae", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Reed_Scale-MAE_A_Scale-Aware_Masked_Autoencoder_for_Multiscale_Geospatial_Representation_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.14532", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval", + "base_url": null, + "title_page": null, + "github": "IMCCretrieval/ProST", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Progressive_Spatio-Temporal_Prototype_Matching_for_Text-Video_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "Towards Deeply Unified Depth-Aware Panoptic Segmentation with Bi-Directional Guidance Learning", + "base_url": null, + "title_page": null, + "github": "jwh97nn/DeepDPS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_Towards_Deeply_Unified_Depth-aware_Panoptic_Segmentation_with_Bi-directional_Guidance_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14786", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "LogicSeg: Parsing Visual Semantics with Neural Logic Learning and Reasoning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_LogicSeg_Parsing_Visual_Semantics_with_Neural_Logic_Learning_and_Reasoning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.13556", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + }, + { + "title": "ASIC: Aligning Sparse in-the-Wild Image Collections", + "base_url": null, + "title_page": null, + "github": "kampta/asic", + "web_page": null, + "github_page": "https://kampta.github.io/asic/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gupta_ASIC_Aligning_Sparse_in-the-wild_Image_Collections_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16201", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "fLjkkMriuoY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Recognition, Segmentation, and Shape Analysis" + } +] \ No newline at end of file diff --git a/json_data/2023/main/representation-learning.json b/json_data/2023/main/representation-learning.json new file mode 100644 index 0000000..2b78058 --- /dev/null +++ b/json_data/2023/main/representation-learning.json @@ -0,0 +1,1082 @@ +[ + { + "title": "WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant Analysis", + "base_url": null, + "title_page": null, + "github": "ivalab/WDiscOOD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_WDiscOOD_Out-of-Distribution_Detection_via_Whitened_Linear_Discriminant_Analysis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.07543", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Pairwise Similarity Learning is SimPLE", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://simple.is.tue.mpg.de/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wen_Pairwise_Similarity_Learning_is_SimPLE_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.09449", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier", + "base_url": null, + "title_page": null, + "github": "ZexiLee/ICCV-2023-FedETF", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_No_Fear_of_Classifier_Biases_Neural_Collapse_Inspired_Federated_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10058", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Generalizable Neural Fields as Partially Observed Neural Processes", + "base_url": null, + "title_page": null, + "github": "its-gucci/partially-observed-neural-processes", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gu_Generalizable_Neural_Fields_as_Partially_Observed_Neural_Processes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.06660", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "M2T: Masking Transformers Twice for Faster Decoding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mentzer_M2T_Masking_Transformers_Twice_for_Faster_Decoding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.07313", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Keep it SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?", + "base_url": null, + "title_page": null, + "github": "billpsomas/simpool", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Psomas_Keep_It_SimPool_Who_Said_Supervised_Transformers_Suffer_from_Attention_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.06891", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Improving Pixel-based MIM by Reducing Wasted Modeling Capability", + "base_url": null, + "title_page": null, + "github": "open-mmlab/mmpretrain", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Improving_Pixel-based_MIM_by_Reducing_Wasted_Modeling_Capability_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.00261", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration", + "base_url": null, + "title_page": null, + "github": "kechunl/AdaCode", + "web_page": null, + "github_page": "https://kechunl.github.io/AdaCode/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Learning_Image-Adaptive_Codebooks_for_Class-Agnostic_Image_Restoration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.06513", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "7jMYUjq-wwE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Quality Diversity for Visual Pre-Training", + "base_url": null, + "title_page": null, + "github": "ruchikachavhan/quality-diversity-pretraining", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chavhan_Quality_Diversity_for_Visual_Pre-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Subclass-Balancing Contrastive Learning for Long-Tailed Recognition", + "base_url": null, + "title_page": null, + "github": "JackHck/SBCL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hou_Subclass-balancing_Contrastive_Learning_for_Long-tailed_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.15925", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Mastering Spatial Graph Prediction of Road Networks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sotiris_Mastering_Spatial_Graph_Prediction_of_Road_Networks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.00828", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Poincaré ResNet", + "base_url": null, + "title_page": null, + "github": "maxvanspengler/poincare-resnet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/van_Spengler_Poincare_ResNet_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14027", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Exploring Model Transferability through the Lens of Potential Energy", + "base_url": null, + "title_page": null, + "github": "lixiaotong97/PED", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Exploring_Model_Transferability_through_the_Lens_of_Potential_Energy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.15074", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Improving CLIP Fine-Tuning Performance", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Improving_CLIP_Fine-tuning_Performance_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Unsupervised Manifold Linearizing and Clustering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ding_Unsupervised_Manifold_Linearizing_and_Clustering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.01805", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Generalized Sum Pooling for Metric Learning", + "base_url": null, + "title_page": null, + "github": "yetigurbuz/generalized-sum-pooling", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gurbuz_Generalized_Sum_Pooling_for_Metric_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09228", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Partition Speeds Up Learning Implicit Neural Representations based on Exponential-Increase Hypothesis", + "base_url": null, + "title_page": null, + "github": "1999kevin/INR-Partition", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Partition_Speeds_Up_Learning_Implicit_Neural_Representations_Based_on_Exponential-Increase_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.14184", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "The Effectiveness of MAE Pre-Pretraining for Billion-Scale Pretraining", + "base_url": null, + "title_page": null, + "github": "facebookresearch/maws", + "web_page": null, + "github_page": "https://facebookresearch.github.io/maws/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Singh_The_Effectiveness_of_MAE_Pre-Pretraining_for_Billion-Scale_Pretraining_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13496", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Token-Label Alignment for Vision Transformers", + "base_url": null, + "title_page": null, + "github": "Euphoria16/TL-Align", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiao_Token-Label_Alignment_for_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.06455", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Efficiently Robustify Pre-Trained Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jain_Efficiently_Robustify_Pre-Trained_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.07499", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "OFVL-MS: Once for Visual Localization Across Multiple Indoor Scenes", + "base_url": null, + "title_page": null, + "github": "mooncake199809/UFVL-Net", + "web_page": null, + "github_page": "https://github.com/mooncake199809/UFVL-Net/tree/main/configs/ofvl_ms", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xie_OFVL-MS_Once_for_Visual_Localization_across_Multiple_Indoor_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11928", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Feature Prediction Diffusion Model for Video Anomaly Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_Feature_Prediction_Diffusion_Model_for_Video_Anomaly_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Joint Implicit Neural Representation for High-Fidelity and Compact Vector Fonts", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Joint_Implicit_Neural_Representation_for_High-fidelity_and_Compact_Vector_Fonts_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "How Far Pre-Trained Models are from Neural Collapse on the Target Dataset Informs their Transferability", + "base_url": null, + "title_page": null, + "github": "BUserName/NCTI", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_How_Far_Pre-trained_Models_Are_from_Neural_Collapse_on_the_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions", + "base_url": null, + "title_page": null, + "github": "wangck20/OPERA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_OPERA_Omni-Supervised_Representation_Learning_with_Hierarchical_Supervisions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.05557", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Perceptual Grouping in Contrastive Vision-Language Models", + "base_url": null, + "title_page": null, + "github": "kahnchana/clippy", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ranasinghe_Perceptual_Grouping_in_Contrastive_Vision-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.09996", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Fully Attentional Networks with Self-Emerging Token Labeling", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Fully_Attentional_Networks_with_Self-emerging_Token_Labeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Instance and Category Supervision are Alternate Learners for Continual Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tian_Instance_and_Category_Supervision_are_Alternate_Learners_for_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-Training", + "base_url": null, + "title_page": null, + "github": "HongYan1123/SkeletonMAE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_SkeletonMAE_Graph-based_Masked_Autoencoder_for_Skeleton_Sequence_Pre-training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08476", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Motion-Guided Masking for Spatiotemporal Representation Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_Motion-Guided_Masking_for_Spatiotemporal_Representation_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12962", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": "https://www.amazon.science/publications/motion-guided-masking-for-spatiotemporal-representation-learning", + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Data Augmented Flatness-Aware Gradient Projection for Continual Learning", + "base_url": null, + "title_page": null, + "github": "EnnengYang/DFGP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Data_Augmented_Flatness-aware_Gradient_Projection_for_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Take-a-Photo: 3D-to-2D Generative Pre-Training of Point Cloud Models", + "base_url": null, + "title_page": null, + "github": "wangzy22/TAP", + "web_page": "https://tap.ivg-research.xyz/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Take-A-Photo_3D-to-2D_Generative_Pre-training_of_Point_Cloud_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14971", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "BiViT: Extremely Compressed Binary Vision Transformers", + "base_url": null, + "title_page": null, + "github": "ThisisBillhe/BiViT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_BiViT_Extremely_Compressed_Binary_Vision_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.07091", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Spatio-Temporal Crop Aggregation for Video Representation Learning", + "base_url": null, + "title_page": null, + "github": "Separius/SCALE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sameni_Spatio-Temporal_Crop_Aggregation_for_Video_Representation_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.17042", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning", + "base_url": null, + "title_page": null, + "github": "HanjaeKim98/CoT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Hierarchical_Visual_Primitive_Experts_for_Compositional_Zero-Shot_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04016", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Semantic Information in Contrastive Learning", + "base_url": null, + "title_page": null, + "github": "sjiang95/semcl", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Quan_Semantic_Information_in_Contrastive_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Cross-Domain Product Representation Learning for Rich-Content E-Commerce", + "base_url": null, + "title_page": null, + "github": "adxcreative/COPE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bai_Cross-Domain_Product_Representation_Learning_for_Rich-Content_E-Commerce_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05550", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_Contrastive_Continuity_on_Augmentation_Stability_Rehearsal_for_Continual_Self-Supervised_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness", + "base_url": null, + "title_page": null, + "github": "MKYucel/hybrid_augment", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yucel_HybridAugment_Unified_Frequency_Spectra_Perturbations_for_Model_Robustness_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11823", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + }, + { + "title": "Unleashing Text-to-Image Diffusion Models for Visual Perception", + "base_url": null, + "title_page": null, + "github": "wl-zhao/VPD", + "web_page": "https://vpd.ivg-research.xyz/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Unleashing_Text-to-Image_Diffusion_Models_for_Visual_Perception_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.02153", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning" + } +] \ No newline at end of file diff --git a/json_data/2023/main/scene-analysis-and-understanding.json b/json_data/2023/main/scene-analysis-and-understanding.json new file mode 100644 index 0000000..6b6a7bc --- /dev/null +++ b/json_data/2023/main/scene-analysis-and-understanding.json @@ -0,0 +1,1082 @@ +[ + { + "title": "Generalized Few-Shot Point Cloud Segmentation via Geometric Words", + "base_url": null, + "title_page": null, + "github": "Pixie8888/GFS-3DSeg_GWs", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Generalized_Few-Shot_Point_Cloud_Segmentation_via_Geometric_Words_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11222", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer", + "base_url": null, + "title_page": null, + "github": "shiyujiao/Boosting3DoFAccuracy", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_Boosting_3-DoF_Ground-to-Satellite_Camera_Localization_Accuracy_via_Geometry-Guided_Cross-View_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08015", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization", + "base_url": null, + "title_page": null, + "github": "minnjung/EP2P-Loc", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_EP2P-Loc_End-to-End_3D_Point_to_2D_Pixel_Localization_for_Large-Scale_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.07471", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Multi-Task View Synthesis with Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": "zsh2000/MuvieNeRF", + "web_page": null, + "github_page": "https://zsh2000.github.io/mtvs.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Multi-task_View_Synthesis_with_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.17450", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Multi-Task Learning with Knowledge Distillation for Dense Prediction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Multi-Task_Learning_with_Knowledge_Distillation_for_Dense_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World", + "base_url": null, + "title_page": null, + "github": "Yuqifan1117/CaCao", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Visually-Prompted_Language_Model_for_Fine-Grained_Scene_Graph_Generation_in_an_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13233", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "XiaRho/CMDA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xia_CMDA_Cross-Modality_Domain_Adaptation_for_Nighttime_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15942", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_VQA-GNN_Reasoning_with_Multimodal_Knowledge_via_Graph_Neural_Networks_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2205.11501", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Disentangle then Parse: Night-Time Semantic Segmentation with Illumination Disentanglement", + "base_url": null, + "title_page": null, + "github": "w1oves/DTP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Disentangle_then_Parse_Night-time_Semantic_Segmentation_with_Illumination_Disentanglement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09362", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Visual Traffic Knowledge Graph Generation from Scene Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "http://www.nlpr.ia.ac.cn/pal/RS10K.html", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Visual_Traffic_Knowledge_Graph_Generation_from_Scene_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Agglomerative Transformer for Human-Object Interaction Detection", + "base_url": null, + "title_page": null, + "github": "six6607/AGER", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tu_Agglomerative_Transformer_for_Human-Object_Interaction_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08370", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation", + "base_url": null, + "title_page": null, + "github": "google-deepmind/threednel", + "web_page": null, + "github_page": "https://probcomp.github.io/nel/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_3D_Neural_Embedding_Likelihood_Probabilistic_Inverse_Graphics_for_Robust_6D_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.03744", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation", + "base_url": null, + "title_page": null, + "github": "franciszzj/HiLo", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_HiLo_Exploiting_High_Low_Frequency_Relations_for_Unbiased_Panoptic_Scene_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15994", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "RLIPv2: Fast Scaling of Relational Language-Image Pre-Training", + "base_url": null, + "title_page": null, + "github": "JacobYuan7/RLIPv2", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yuan_RLIPv2_Fast_Scaling_of_Relational_Language-Image_Pre-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09351", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase", + "base_url": null, + "title_page": null, + "github": "PJLab-ADG/PCSeg", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_UniSeg_A_Unified_Multi-Modal_LiDAR_Segmentation_Network_and_the_OpenPCSeg_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05573", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "See more and Know More: Zero-Shot Point Cloud Segmentation via Multi-Modal Visual Data", + "base_url": null, + "title_page": null, + "github": "4DVLab/See_More_Know_More", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_See_More_and_Know_More_Zero-shot_Point_Cloud_Segmentation_via_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10782", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Compositional Feature Augmentation for Unbiased Scene Graph Generation", + "base_url": null, + "title_page": null, + "github": "HKUST-LongGroup/CFA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Compositional_Feature_Augmentation_for_Unbiased_Scene_Graph_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06712", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Multi-Weather Image Restoration via Domain Translation", + "base_url": null, + "title_page": null, + "github": "pwp1208/Domain_Translation_Multi-weather_Restoration", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Patil_Multi-weather_Image_Restoration_via_Domain_Translation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "CLIPTER: Looking at the Bigger Picture in Scene Text Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Aberdam_CLIPTER_Looking_at_the_Bigger_Picture_in_Scene_Text_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.07464", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Towards Models that Can See and Read", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ganz_Towards_Models_that_Can_See_and_Read_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.07389", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving", + "base_url": null, + "title_page": null, + "github": "weiyithu/SurroundOcc", + "web_page": null, + "github_page": "https://weiyithu.github.io/SurroundOcc/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_SurroundOcc_Multi-camera_3D_Occupancy_Prediction_for_Autonomous_Driving_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09551", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "DDP: Diffusion Model for Dense Visual Prediction", + "base_url": null, + "title_page": null, + "github": "JiYuanFeng/DDP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ji_DDP_Diffusion_Model_for_Dense_Visual_Prediction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17559", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Understanding 3D Object Interaction from a Single Image", + "base_url": null, + "title_page": null, + "github": "JasonQSY/3DOI", + "web_page": null, + "github_page": "https://jasonqsy.github.io/3DOI/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qian_Understanding_3D_Object_Interaction_from_a_Single_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.09664", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "YDIL93XxHyk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces", + "base_url": null, + "title_page": null, + "github": "QianyiWu/objectsdf_plus", + "web_page": "https://wuqianyi.top/objectsdf++", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_ObjectSDF_Improved_Object-Compositional_Neural_Implicit_Surfaces_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07868", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "aR7TAW-tLkE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors", + "base_url": null, + "title_page": null, + "github": "mikuhatsune/equivariance", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhong_Improving_Equivariance_in_State-of-the-Art_Supervised_Depth_and_Normal_Predictors_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16646", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "CrossMatch: Source-Free Domain Adaptive Semantic Segmentation via Cross-Modal Consistency Training", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yin_CrossMatch_Source-Free_Domain_Adaptive_Semantic_Segmentation_via_Cross-Modal_Consistency_Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://visual.cs.brown.edu/projects/semantic-attention-flow-fields-webpage/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_Semantic_Attention_Flow_Fields_for_Monocular_Dynamic_Scene_Decomposition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.01526", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Holistic Geometric Feature Learning for Structured Reconstruction", + "base_url": null, + "title_page": null, + "github": "Geo-Tell/F-Learn", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Holistic_Geometric_Feature_Learning_for_Structured_Reconstruction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.09622", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Scalable Multi-Temporal Remote Sensing Change Data Generation via Simulating Stochastic Change Process", + "base_url": null, + "title_page": null, + "github": "Z-Zheng/Changen", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Scalable_Multi-Temporal_Remote_Sensing_Change_Data_Generation_via_Simulating_Stochastic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.17031", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_TaskExpert_Dynamically_Assembling_Multi-Task_Representations_with_Memorial_Mixture-of-Experts_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15324", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Thinking Image Color Aesthetics Assessment: Models, Datasets and Benchmarks", + "base_url": null, + "title_page": null, + "github": "woshidandan/Image-Color-Aesthetics-Assessment", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_Thinking_Image_Color_Aesthetics_Assessment_Models_Datasets_and_Benchmarks_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning", + "base_url": null, + "title_page": null, + "github": "taohan10200/STEERER", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_STEERER_Resolving_Scale_Variations_for_Counting_and_Localization_via_Selective_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10468", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Object-Aware Gaze Target Detection", + "base_url": null, + "title_page": null, + "github": "francescotonini/object-aware-gaze-target-detection", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tonini_Object-aware_Gaze_Target_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09662", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Weakly Supervised Referring Image Segmentation with Intra-Chunk and Inter-Chunk Consistency", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Weakly_Supervised_Referring_Image_Segmentation_with_Intra-Chunk_and_Inter-Chunk_Consistency_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Vision Relation Transformer for Unbiased Scene Graph Generation", + "base_url": null, + "title_page": null, + "github": "visinf/veto", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sudhakaran_Vision_Relation_Transformer_for_Unbiased_Scene_Graph_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09472", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "N4YqmfDY-t0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "DDIT: Semantic Scene Completion via Deformable Deep Implicit Templates", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_DDIT_Semantic_Scene_Completion_via_Deformable_Deep_Implicit_Templates_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "DQS3D: Densely-Matched Quantization-Aware Semi-Supervised 3D Detection", + "base_url": null, + "title_page": null, + "github": "AIR-DISCOVER/DQS3D", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_DQS3D_Densely-matched_Quantization-aware_Semi-supervised_3D_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.13031", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Shape Anchor Guided Holistic Indoor Scene Understanding", + "base_url": null, + "title_page": null, + "github": "Geo-Tell/AncRec", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Shape_Anchor_Guided_Holistic_Indoor_Scene_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11133", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "SGAligner: 3D Scene Alignment with Scene Graphs", + "base_url": null, + "title_page": null, + "github": "sayands/sgaligner", + "web_page": "https://sayandebsarkar.com/sgaligner/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sarkar_SGAligner_3D_Scene_Alignment_with_Scene_Graphs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.14880", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Oq89hgocg4Q", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + }, + { + "title": "Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation", + "base_url": null, + "title_page": null, + "github": "jianzongwu/betrayed-by-captions", + "web_page": "https://www.mmlab-ntu.com/project/betrayed_caption/index.html", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Betrayed_by_Captions_Joint_Caption_Grounding_and_Generation_for_Open_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.00805", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "b8WuuvyGp3M", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Scene Analysis and Understanding" + } +] \ No newline at end of file diff --git a/json_data/2023/main/segmentation-grouping-and-shape-analysis.json b/json_data/2023/main/segmentation-grouping-and-shape-analysis.json new file mode 100644 index 0000000..8a8e1d4 --- /dev/null +++ b/json_data/2023/main/segmentation-grouping-and-shape-analysis.json @@ -0,0 +1,1946 @@ +[ + { + "title": "3D Instance Segmentation via Enhanced Spatial and Semantic Supervision", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Al_Khatib_3D_Instance_Segmentation_via_Enhanced_Spatial_and_Semantic_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "thudzj/NeuralEigenfunctionSegmentor", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Deng_Learning_Neural_Eigenfunctions_for_Unsupervised_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02841", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Divide and Conquer: 3D Point Cloud Instance Segmentation with Point-Wise Binarization", + "base_url": null, + "title_page": null, + "github": "weiguangzhao/PBNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Divide_and_Conquer_3D_Point_Cloud_Instance_Segmentation_With_Point-Wise_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2207.11209", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Point2Mask: Point-Supervised Panoptic Segmentation via Optimal Transport", + "base_url": null, + "title_page": null, + "github": "LiWentomng/Point2Mask", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Point2Mask_Point-supervised_Panoptic_Segmentation_via_Optimal_Transport_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.01779", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Handwritten and Printed Text Segmentation: A Signature Case Study", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gholamian_Handwritten_and_Printed_Text_Segmentation_A_Signature_Case_Study_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07887", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Semantic-Aware Implicit Template Learning via Part Deformation Consistency", + "base_url": null, + "title_page": null, + "github": "mlvlab/PDC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Semantic-Aware_Implicit_Template_Learning_via_Part_Deformation_Consistency_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11916", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "LeaF: Learning Frames for 4D Point Cloud Sequence Understanding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_LeaF_Learning_Frames_for_4D_Point_Cloud_Sequence_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "MARS: Model-Agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "shjo-april/MARS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jo_MARS_Model-agnostic_Biased_Object_Removal_without_Additional_Supervision_for_Weakly-Supervised_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.09913", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Peng_USAGE_A_Unified_Seed_Area_Generation_Paradigm_for_Weakly_Supervised_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.07806", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "XMem++: Production-Level Video Segmentation from Few Annotated Frames", + "base_url": null, + "title_page": null, + "github": "max810/XMem2", + "web_page": null, + "github_page": "https://max810.github.io/xmem2-project-page/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bekuzarov_XMem_Production-level_Video_Segmentation_From_Few_Annotated_Frames_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15958", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "3X3TUP4vKcc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "ΣIGMA: Scale-Invariant Global Sparse Shape Matching", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_SIGMA_Scale-Invariant_Global_Sparse_Shape_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08393", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Self-Calibrated Cross Attention Network for Few-Shot Segmentation", + "base_url": null, + "title_page": null, + "github": "Sam1224/SCCAN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Self-Calibrated_Cross_Attention_Network_for_Few-Shot_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09294", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Multi-Granularity Interaction Simulation for Unsupervised Interactive Segmentation", + "base_url": null, + "title_page": null, + "github": "lkhl/MIS", + "web_page": null, + "github_page": "https://lkhl.github.io/MIS/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Multi-granularity_Interaction_Simulation_for_Unsupervised_Interactive_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13399", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Texture Learning Domain Randomization for Domain Generalized Segmentation", + "base_url": null, + "title_page": null, + "github": "ssssshwan/TLDR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Texture_Learning_Domain_Randomization_for_Domain_Generalized_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11546", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Unsupervised Video Object Segmentation with Online Adversarial Self-Tuning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Su_Unsupervised_Video_Object_Segmentation_with_Online_Adversarial_Self-Tuning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Exploring_Open-Vocabulary_Semantic_Segmentation_from_CLIP_Vision_Encoder_Distillation_Only_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.00450", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "RbA: Segmenting Unknown Regions Rejected by All", + "base_url": null, + "title_page": null, + "github": "NazirNayal8/RbA", + "web_page": null, + "github_page": "https://kuis-ai.github.io/RbA/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nayal_RbA_Segmenting_Unknown_Regions_Rejected_by_All_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.14293", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "SEMPART: Self-Supervised Multi-Resolution Partitioning of Image Semantics", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ravindran_SEMPART_Self-supervised_Multi-resolution_Partitioning_of_Image_Semantics_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.10972", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Multi-Object Discovery by Low-Dimensional Object Motion", + "base_url": null, + "title_page": null, + "github": "sadrasafa/multi-object-segmentation", + "web_page": null, + "github_page": "https://kuis-ai.github.io/multi-object-segmentation/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Safadoust_Multi-Object_Discovery_by_Low-Dimensional_Object_Motion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08027", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://waabi.ai/memoryseg/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_MemorySeg_Online_LiDAR_Semantic_Segmentation_with_a_Latent_Memory_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Treating Pseudo-Labels Generation as Image Matting for Weakly Supervised Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Treating_Pseudo-labels_Generation_as_Image_Matting_for_Weakly_Supervised_Semantic_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "BoxSnake: Polygonal Instance Segmentation with Box Supervision", + "base_url": null, + "title_page": null, + "github": "Yangr116/BoxSnake", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_BoxSnake_Polygonal_Instance_Segmentation_with_Box_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11630", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_Dynamic_Token_Pruning_in_Plain_Vision_Transformers_for_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.01045", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Instance Neural Radiance Field", + "base_url": null, + "title_page": null, + "github": "lyclyc52/Instance_NeRF", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Instance_Neural_Radiance_Field_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.04395", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "wW9Bme73coI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Global Knowledge Calibration for Fast Open-Vocabulary Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_Global_Knowledge_Calibration_for_Fast_Open-Vocabulary_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09181", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Peng_Diffusion-based_Image_Translation_with_Label_Guidance_for_Domain_Adaptive_Semantic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12350", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Boosting Semantic Segmentation from the Perspective of Explicit Class Embeddings", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": "https://gitee.com/mindspore/models", + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Boosting_Semantic_Segmentation_from_the_Perspective_of_Explicit_Class_Embeddings_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12894", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "The Making and Breaking of Camouflage", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lamdouar_The_Making_and_Breaking_of_Camouflage_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03899", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation", + "base_url": null, + "title_page": null, + "github": "zkzhang98/CoinSeg", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_CoinSeg_Contrast_Inter-_and_Intra-_Class_Representations_for_Incremental_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation", + "base_url": null, + "title_page": null, + "github": "Meowuu7/few-arti-gen", + "web_page": null, + "github_page": "https://meowuu7.github.io/few-arti-obj-gen/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Few-Shot_Physically-Aware_Articulated_Mesh_Generation_via_Hierarchical_Deformation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10898", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "p8x3GN3VSPE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_HAL3D_Hierarchical_Active_Learning_for_Fine-Grained_3D_Part_Labeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.10460", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation", + "base_url": null, + "title_page": null, + "github": "TY-Shi/FreeCOS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_FreeCOS_Self-Supervised_Learning_from_Fractals_and_Unlabeled_Images_for_Curvilinear_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07245", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "MasQCLIP for Open-Vocabulary Universal Image Segmentation", + "base_url": null, + "title_page": null, + "github": "mlpc-ucsd/MasQCLIP", + "web_page": null, + "github_page": "https://masqclip.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_MasQCLIP_for_Open-Vocabulary_Universal_Image_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "CTVIS: Consistent Training for Online Video Instance Segmentation", + "base_url": null, + "title_page": null, + "github": "KainingYing/CTVIS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ying_CTVIS_Consistent_Training_for_Online_Video_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12616", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "A Generalist Framework for Panoptic Segmentation of Images and Videos", + "base_url": null, + "title_page": null, + "github": "google-research/pix2seq", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_A_Generalist_Framework_for_Panoptic_Segmentation_of_Images_and_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.06366", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Spectrum-Guided Multi-Granularity Referring Video Object Segmentation", + "base_url": null, + "title_page": null, + "github": "bo-miao/SgMg", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Miao_Spectrum-guided_Multi-granularity_Referring_Video_Object_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13537", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "WangChangqi98/CSS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Space_Engage_Collaborative_Space_Supervision_for_Contrastive-Based_Semi-Supervised_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09755", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Adaptive Superpixel for Active Learning in Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Adaptive_Superpixel_for_Active_Learning_in_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16817", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Multimodal Variational Auto-Encoder based Audio-Visual Segmentation", + "base_url": null, + "title_page": null, + "github": "OpenNLPLab/MMVAE-AVS", + "web_page": null, + "github_page": "https://npucvr.github.io/MMVAE-AVS/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mao_Multimodal_Variational_Auto-encoder_based_Audio-Visual_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Isomer: Isomerous Transformer for Zero-Shot Video Object Segmentation", + "base_url": null, + "title_page": null, + "github": "DLUT-yyc/Isomer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yuan_Isomer_Isomerous_Transformer_for_Zero-shot_Video_Object_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06693", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://jimmy15923.github.io/mit_web/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_2D-3D_Interlaced_Transformer_for_Point_Cloud_Segmentation_with_Scene-Level_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "http://vllab.cs.nctu.edu.tw/images/paper/iccv-yang23.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models", + "base_url": null, + "title_page": null, + "github": "MischaD/fobadiffusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dombrowski_Foreground-Background_Separation_through_Concept_Distillation_from_Generative_Image_Foundation_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.14306", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "SegPrompt: Boosting Open-World Segmentation via Category-Level Prompt Learning", + "base_url": null, + "title_page": null, + "github": "aim-uofa/SegPrompt", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_SegPrompt_Boosting_Open-World_Segmentation_via_Category-Level_Prompt_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06531", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection", + "base_url": null, + "title_page": null, + "github": "YeRen123455/SIRST-Single-Point-Supervision", + "web_page": null, + "github_page": "https://yeren123455.github.io/SIRST-Single-Point-Supervision/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Monte_Carlo_Linear_Clustering_with_Single-Point_Supervision_is_Enough_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.04442", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "A Simple Framework for Open-Vocabulary Segmentation and Detection", + "base_url": null, + "title_page": null, + "github": "IDEA-Research/OpenSeeD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_A_Simple_Framework_for_Open-Vocabulary_Segmentation_and_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08131", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "z4gsQw2n7iM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Source-Free Depth for Object Pop-Out", + "base_url": null, + "title_page": null, + "github": "Zongwei97/PopNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/WU_Source-free_Depth_for_Object_Pop-out_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.05370", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "DynaMITe: Dynamic Query Bootstrapping for Multi-Object Interactive Segmentation Transformer", + "base_url": null, + "title_page": null, + "github": "amitrana001/DynaMITe", + "web_page": null, + "github_page": "https://amitrana001.github.io/DynaMITe/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rana_DynaMITe_Dynamic_Query_Bootstrapping_for_Multi-object_Interactive_Segmentation_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06668", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Atmospheric Transmission and Thermal Inertia Induced Blind Road Segmentation with a Large-Scale Dataset TBRSD", + "base_url": null, + "title_page": null, + "github": "chenjzBUAA/TBRSD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Atmospheric_Transmission_and_Thermal_Inertia_Induced_Blind_Road_Segmentation_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Informative_Data_Mining_for_One-Shot_Cross-Domain_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14241", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Homography Guided Temporal Fusion for Road Line and Marking Segmentation", + "base_url": null, + "title_page": null, + "github": "ShanWang-Shan/HomoFusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Homography_Guided_Temporal_Fusion_for_Road_Line_and_Marking_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network", + "base_url": null, + "title_page": null, + "github": "CongHan0808/DeOP", + "web_page": null, + "github_page": "https://conghan0808.github.io/DeOP/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_Open-Vocabulary_Semantic_Segmentation_with_Decoupled_One-Pass_Network_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01198", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "TCOVIS: Temporally Consistent Online Video Instance Segmentation", + "base_url": null, + "title_page": null, + "github": "jun-long-li/TCOVIS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_TCOVIS_Temporally_Consistent_Online_Video_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "FPR: False Positive Rectification for Weakly Supervised Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "mt-cly/FPR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_FPR_False_Positive_Rectification_for_Weakly_Supervised_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "http://www4.comp.polyu.edu.hk/~cslzhang/paper/ICCV23-FPR.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Stochastic Segmentation with Conditional Categorical Diffusion Models", + "base_url": null, + "title_page": null, + "github": "LarsDoorenbos/ccdm-stochastic-segmentation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zbinden_Stochastic_Segmentation_with_Conditional_Categorical_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08888", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "SegGPT: Towards Segmenting Everything In Context", + "base_url": null, + "title_page": null, + "github": "baaivision/Painter", + "web_page": null, + "github_page": "https://github.com/baaivision/Painter/tree/main/SegGPT", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/BAAI/SegGPT", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_SegGPT_Towards_Segmenting_Everything_in_Context_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.03284", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "zxwH0dUBKis", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Open-Vocabulary Panoptic Segmentation with Embedding Modulation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://opsnet-page.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Open-vocabulary_Panoptic_Segmentation_with_Embedding_Modulation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11324", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Residual Pattern Learning for Pixel-Wise Out-of-Distribution Detection in Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "yyliu01/RPL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Residual_Pattern_Learning_for_Pixel-Wise_Out-of-Distribution_Detection_in_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.14512", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Zero-Guidance Segmentation using Zero Segment Labels", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://zero-guide-seg.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rewatbowornwong_Zero-guidance_Segmentation_Using_Zero_Segment_Labels_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13396", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Model Calibration in Dense Classification with Adaptive Label Perturbation", + "base_url": null, + "title_page": null, + "github": "Carlisle-Liu/ASLP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Model_Calibration_in_Dense_Classification_with_Adaptive_Label_Perturbation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13539", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Enhanced Soft Label for Semi-Supervised Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Enhanced_Soft_Label_for_Semi-Supervised_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cai_MixReorg_Cross-Modal_Mixed_Patch_Reorganization_is_a_Good_Mask_Learner_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04829", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "DiffuMask: Synthesizing Images with Pixel-Level Annotations for Semantic Segmentation using Diffusion Models", + "base_url": null, + "title_page": null, + "github": "weijiawu/DiffuMask", + "web_page": null, + "github_page": "https://weijiawu.github.io/DiffusionMask/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_DiffuMask_Synthesizing_Images_with_Pixel-level_Annotations_for_Semantic_Segmentation_Using_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11681", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Alignment Before Aggregation: Trajectory Memory Retrieval Network for Video Object Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Alignment_Before_Aggregation_Trajectory_Memory_Retrieval_Network_for_Video_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Semi-Supervised Semantic Segmentation under Label Noise via Diverse Learning Groups", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Semi-Supervised_Semantic_Segmentation_under_Label_Noise_via_Diverse_Learning_Groups_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets", + "base_url": null, + "title_page": null, + "github": "csimo005/SUMMIT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Simons_SUMMIT_Source-Free_Adaptation_of_Uni-Modal_Models_to_Multi-Modal_Targets_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11880", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "LDlLq9IdoAw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Class-Incremental Continual Learning for Instance Segmentation with Image-Level Weak Supervision", + "base_url": null, + "title_page": null, + "github": "AI-Application-and-Integration-Lab/CL4WSIS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hsieh_Class-incremental_Continual_Learning_for_Instance_Segmentation_with_Image-level_Weak_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Coarse-to-Fine Amodal Segmentation with Shape Prior", + "base_url": null, + "title_page": null, + "github": "JianxGao/C2F-Seg", + "web_page": null, + "github_page": "https://jianxgao.github.io/C2F-Seg/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_Coarse-to-Fine_Amodal_Segmentation_with_Shape_Prior_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16825", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-Centric Representation", + "base_url": null, + "title_page": null, + "github": "kfan21/EoRaS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_Rethinking_Amodal_Video_Segmentation_from_Learning_Supervised_Signals_with_Object-centric_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.13248", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "DVIS: Decoupled Video Instance Segmentation Framework", + "base_url": null, + "title_page": null, + "github": "zhang-tao-whu/DVIS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_DVIS_Decoupled_Video_Instance_Segmentation_Framework_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.03413", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "3D Segmentation of Humans in Point Clouds with Synthetic Data", + "base_url": null, + "title_page": null, + "github": "human-3d/Human3D", + "web_page": null, + "github_page": "https://human-3d.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Takmaz_3D_Segmentation_of_Humans_in_Point_Clouds_with_Synthetic_Data_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.00786", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "WaterMask: Instance Segmentation for Underwater Imagery", + "base_url": null, + "title_page": null, + "github": "LiamLian0727/WaterMask", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lian_WaterMask_Instance_Segmentation_for_Underwater_Imagery_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + }, + { + "title": "Tracking Anything with Decoupled Video Segmentation", + "base_url": null, + "title_page": null, + "github": "hkchengrex/Tracking-Anything-with-DEVA", + "web_page": null, + "github_page": "https://hkchengrex.com/Tracking-Anything-with-DEVA/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_Tracking_Anything_with_Decoupled_Video_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03903", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Segmentation, Grouping and Shape Analysis" + } +] \ No newline at end of file diff --git a/json_data/2023/main/self--semi--and-unsupervised-learning.json b/json_data/2023/main/self--semi--and-unsupervised-learning.json new file mode 100644 index 0000000..366d2ee --- /dev/null +++ b/json_data/2023/main/self--semi--and-unsupervised-learning.json @@ -0,0 +1,326 @@ +[ + { + "title": "Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV", + "base_url": null, + "title_page": null, + "github": "jspenmar/slowtv_monodepth", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Spencer_Kick_Back__Relax_Learning_to_Reconstruct_the_World_by_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10713", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "Novel Scenes & Classes: Towards Adaptive Open-Set Object Detection", + "base_url": null, + "title_page": null, + "github": "CityU-AIM-Group/SOMA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Novel_Scenes__Classes_Towards_Adaptive_Open-set_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "Improving Unsupervised Visual Program Inference with Code Rewriting Families", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://bardofcodes.github.io/coref/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ganeshan_Improving_Unsupervised_Visual_Program_Inference_with_Code_Rewriting_Families_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.14972", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "Denoising Diffusion Autoencoders are Unified Self-Supervised Learners", + "base_url": null, + "title_page": null, + "github": "FutureXiang/ddae", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiang_Denoising_Diffusion_Autoencoders_are_Unified_Self-supervised_Learners_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09769", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "Self-Ordering Point Clouds", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Self-Ordering_Point_Clouds_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.00961", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "MOST: Multiple Object Localization with Self-Supervised Transformers for Object Discovery", + "base_url": null, + "title_page": null, + "github": "rssaketh/MOST", + "web_page": null, + "github_page": "https://rssaketh.github.io/most", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rambhatla_MOST_Multiple_Object_Localization_with_Self-Supervised_Transformers_for_Object_Discovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.05387", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images", + "base_url": null, + "title_page": null, + "github": "jellyheadandrew/CHORUS", + "web_page": null, + "github_page": "https://jellyheadandrew.github.io/projects/chorus/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_CHORUS__Learning_Canonicalized_3D_Human-Object_Spatial_Relations_from_Unbounded_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12288", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "3WwUdKsbqKQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-Identification", + "base_url": null, + "title_page": null, + "github": "dcp15/ISR_ICCV2023_Oral", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dou_Identity-Seeking_Self-Supervised_Representation_Learning_for_Generalizable_Person_Re-Identification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08887", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "Anatomical Invariance Modeling and Semantic Alignment for Self-Supervised Learning in 3D Medical Image Analysis", + "base_url": null, + "title_page": null, + "github": "alibaba-damo-academy/alice", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Anatomical_Invariance_Modeling_and_Semantic_Alignment_for_Self-supervised_Learning_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.05615", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization", + "base_url": null, + "title_page": null, + "github": "nukezil/IOMatch", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_IOMatch_Simplifying_Open-Set_Semi-Supervised_Learning_with_Joint_Inliers_and_Outliers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13168", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning", + "base_url": null, + "title_page": null, + "github": "GuanGui-nju/SAA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gui_Enhancing_Sample_Utilization_through_Sample_Adaptive_Augmentation_in_Semi-Supervised_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03598", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + }, + { + "title": "When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_When_Noisy_Labels_Meet_Long_Tail_Dilemmas_A_Representation_Calibration_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.10955", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, and Unsupervised Learning" + } +] \ No newline at end of file diff --git a/json_data/2023/main/self--semi--meta--unsupervised-learning.json b/json_data/2023/main/self--semi--meta--unsupervised-learning.json new file mode 100644 index 0000000..3e2dd8c --- /dev/null +++ b/json_data/2023/main/self--semi--meta--unsupervised-learning.json @@ -0,0 +1,1811 @@ +[ + { + "title": "Noise2Info: Noisy Image to Information of Noise for Self-Supervised Image Denoising", + "base_url": null, + "title_page": null, + "github": "dominatorX/Noise2Info-code", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Noise2Info_Noisy_Image_to_Information_of_Noise_for_Self-Supervised_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks", + "base_url": null, + "title_page": null, + "github": "eyalgomel/box-based-refinement", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gomel_Box-based_Refinement_for_Weakly_Supervised_and_Unsupervised_Localization_Tasks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03874", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Diverse Cotraining Makes Strong Semi-Supervised Segmentor", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Diverse_Cotraining_Makes_Strong_Semi-Supervised_Segmentor_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09281", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "SSB: Simple but Strong Baseline for Boosting Performance of Open-Set Semi-Supervised Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_SSB_Simple_but_Strong_Baseline_for_Boosting_Performance_of_Open-Set_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Late Stopping: Avoiding Confidently Learning from Mislabeled Examples", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yuan_Late_Stopping_Avoiding_Confidently_Learning_from_Mislabeled_Examples_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13862", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Ponder: Point Cloud Pre-Training via Neural Rendering", + "base_url": null, + "title_page": null, + "github": "OpenGVLab/PonderV2", + "web_page": "https://dihuang.me/ponder/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Ponder_Point_Cloud_Pre-training_via_Neural_Rendering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.00157", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning", + "base_url": null, + "title_page": null, + "github": "skyoux/scfs", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_Semantics-Consistent_Feature_Search_for_Self-Supervised_Visual_Representation_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.06486", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Stable and Causal Inference for Discriminative Self-Supervised Deep Visual Representations", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Stable_and_Causal_Inference_for_Discriminative_Self-supervised_Deep_Visual_Representations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08321", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Towards Semi-Supervised Learning with Non-Random Missing Labels", + "base_url": null, + "title_page": null, + "github": "NJUyued/PRG4SSL-MNAR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Duan_Towards_Semi-supervised_Learning_with_Non-random_Missing_Labels_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08872", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Hallucination Improves the Performance of Unsupervised Visual Representation Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Hallucination_Improves_the_Performance_of_Unsupervised_Visual_Representation_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12168", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Audiovisual Masked Autoencoders", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Georgescu_Audiovisual_Masked_Autoencoders_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.05922", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "PADCLIP: Pseudo-Labeling with Adaptive Debiasing in CLIP for Unsupervised Domain Adaptation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lai_PADCLIP_Pseudo-labeling_with_Adaptive_Debiasing_in_CLIP_for_Unsupervised_Domain_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Removing Anomalies as Noises for Industrial Defect Localization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Removing_Anomalies_as_Noises_for_Industrial_Defect_Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "SparseMAE: Sparse Training Meets Masked Autoencoders", + "base_url": null, + "title_page": null, + "github": "aojunzz/SparseMAE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_SparseMAE_Sparse_Training_Meets_Masked_Autoencoders_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning", + "base_url": null, + "title_page": null, + "github": "LiheYoung/ShrinkMatch", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Shrinking_Class_Space_for_Enhanced_Certainty_in_Semi-Supervised_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06777", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Logic-Induced Diagnostic Reasoning for Semi-Supervised Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_Logic-induced_Diagnostic_Reasoning_for_Semi-supervised_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12595", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "FTT8KhBmPnU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes", + "base_url": null, + "title_page": null, + "github": "zxcqlf/GasMono", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_GasMono_Geometry-Aided_Self-Supervised_Monocular_Depth_Estimation_for_Indoor_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16019", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training", + "base_url": null, + "title_page": null, + "github": "yunyikristy/DualMind", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Is_Imitation_All_You_Need_Generalized_Decision-Making_with_Dual-Phase_Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07909", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy Reduction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Estepa_All4One_Symbiotic_Neighbour_Contrastive_Learning_via_Self-Attention_and_Redundancy_Reduction_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09417", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Weakly Supervised Learning of Semantic Correspondence through Cascaded Online Correspondence Refinement", + "base_url": null, + "title_page": null, + "github": "21210240056/SC-ImageNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Weakly_Supervised_Learning_of_Semantic_Correspondence_through_Cascaded_Online_Correspondence_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Tracking without Label: Unsupervised Multiple Object Tracking via Contrastive Similarity Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Meng_Tracking_without_Label_Unsupervised_Multiple_Object_Tracking_via_Contrastive_Similarity_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.00942", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cabannes_Active_Self-Supervised_Learning_A_Few_Low-Cost_Relationships_Are_All_You_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15256", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Diffusion Models as Masked Autoencoders", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://weichen582.github.io/diffmae.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Diffusion_Models_as_Masked_Autoencoders_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.03283", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Enhanced Meta Label Correction for Coping with Label Corruption", + "base_url": null, + "title_page": null, + "github": "MitchellKT/Enhanced-Meta-Label-Correction", + "web_page": "https://sites.google.com/view/emlc-paper", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Taraday_Enhanced_Meta_Label_Correction_for_Coping_with_Label_Corruption_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.12961", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Randomized Quantization: A Generic Augmentation for Data Agnostic Self-Supervised Learning", + "base_url": null, + "title_page": null, + "github": "microsoft/random_quantize", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Randomized_Quantization_A_Generic_Augmentation_for_Data_Agnostic_Self-supervised_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.08663", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Prototypes-Oriented Transductive Few-Shot Learning with Conditional Transport", + "base_url": null, + "title_page": null, + "github": "RashLog/PUTM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tian_Prototypes-oriented_Transductive_Few-shot_Learning_with_Conditional_Transport_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03047", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Contrastive Learning Relies more on Spatial Inductive Bias than Supervised Learning: An Empirical Study", + "base_url": null, + "title_page": null, + "github": "HaoranTang/cl_spatial_inductive_bias", + "web_page": null, + "github_page": "https://haorantang.github.io/cl_spatial_inductive_bias/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhong_Contrastive_Learning_Relies_More_on_Spatial_Inductive_Bias_Than_Supervised_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Pseudo-Label Alignment for Semi-Supervised Instance Segmentation", + "base_url": null, + "title_page": null, + "github": "hujiecpp/PAIS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_Pseudo-label_Alignment_for_Semi-supervised_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05359", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "CFCG: Semi-Supervised Semantic Segmentation via Cross-Fusion and Contour Guidance Supervision", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_CFCG_Semi-Supervised_Semantic_Segmentation_via_Cross-Fusion_and_Contour_Guidance_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Pixel-Wise Contrastive Distillation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Pixel-Wise_Contrastive_Distillation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.00218", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Rethinking Safe Semi-Supervised Learning: Transferring the Open-Set Problem to a Close-Set One", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Rethinking_Safe_Semi-supervised_Learning_Transferring_the_Open-set_Problem_to_A_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Towards_Open-Set_Test-Time_Adaptation_Utilizing_the_Wisdom_of_Crowds_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06879", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Gradient-based Sampling for Class Imbalanced Semi-Supervised Object Detection", + "base_url": null, + "title_page": null, + "github": "nightkeepers/CI-SSOD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Gradient-based_Sampling_for_Class_Imbalanced_Semi-supervised_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Remembering Normality: Memory-Guided Knowledge Distillation for Unsupervised Anomaly Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gu_Remembering_Normality_Memory-guided_Knowledge_Distillation_for_Unsupervised_Anomaly_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Semi-Supervised Learning via Weight-Aware Distillation under Class Distribution Mismatch", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://github.com/RUC-DWBI-ML/research/tree/main/WAD-master", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Du_Semi-Supervised_Learning_via_Weight-Aware_Distillation_under_Class_Distribution_Mismatch_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11874", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_Label_Shift_Adapter_for_Test-Time_Adaptation_under_Covariate_and_Label_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08810", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "SimMatchV2: Semi-Supervised Learning with Graph Consistency", + "base_url": null, + "title_page": null, + "github": "mingkai-zheng/SimMatchV2", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_SimMatchV2_Semi-Supervised_Learning_with_Graph_Consistency_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06692", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Unsupervised_Accuracy_Estimation_of_Deep_Visual_Models_using_Domain-Adaptive_Adversarial_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10062", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Learning by Sorting: Self-Supervised Learning with Group Ordering Constraints", + "base_url": null, + "title_page": null, + "github": "ninatu/learning_by_sorting", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shvetsova_Learning_by_Sorting_Self-supervised_Learning_with_Group_Ordering_Constraints_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.02009", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "L-DAWA: Layer-Wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Rehman_L-DAWA_Layer-wise_Divergence_Aware_Weight_Aggregation_in_Federated_Self-Supervised_Visual_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07393", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Class-Relation Knowledge Distillation for Novel Class Discovery", + "base_url": null, + "title_page": null, + "github": "kleinzcy/Cr-KD-NCD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gu_Class-relation_Knowledge_Distillation_for_Novel_Class_Discovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09158", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Representation Uncertainty in Self-Supervised Learning as Variational Inference", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nakamura_Representation_Uncertainty_in_Self-Supervised_Learning_as_Variational_Inference_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2203.11437", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Point-TTA: Test-Time Adaptation for Point Cloud Registration using Multitask Meta-Auxiliary Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hatem_Point-TTA_Test-Time_Adaptation_for_Point_Cloud_Registration_Using_Multitask_Meta-Auxiliary_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16481", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning", + "base_url": null, + "title_page": null, + "github": "tileb1/AdaSim", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lebailly_Adaptive_Similarity_Bootstrapping_for_Self-Distillation_Based_Representation_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13606", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sheng_Point_Contrastive_Prediction_with_Semantic_Clustering_for_Self-Supervised_Learning_on_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09247", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "MHCN: A Hyperbolic Neural Network Model for Multi-View Hierarchical Clustering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_MHCN_A_Hyperbolic_Neural_Network_Model_for_Multi-view_Hierarchical_Clustering_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Time does Tell: Self-Supervised Time-Tuning of Dense Image Representations", + "base_url": null, + "title_page": null, + "github": "SMSD75/Timetuning", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Salehi_Time_Does_Tell_Self-Supervised_Time-Tuning_of_Dense_Image_Representations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11796", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "To Adapt or not to Adapt? Real-Time Adaptation for Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "MarcBotet/hamlet", + "web_page": null, + "github_page": "https://marcbotet.github.io/hamlet-web/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Colomer_To_Adapt_or_Not_to_Adapt_Real-Time_Adaptation_for_Semantic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15063", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "zjxPbCphPDE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Simple and Effective Out-of-Distribution Detection via Cosine-based Softmax Loss", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Noh_Simple_and_Effective_Out-of-Distribution_Detection_via_Cosine-based_Softmax_Loss_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "MixBag: Bag-Level Data Augmentation for Learning from Label Proportions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Asanomi_MixBag_Bag-Level_Data_Augmentation_for_Learning_from_Label_Proportions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08822", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Masked Spatio-Temporal Structure Prediction for Self-Supervised Learning on Point Cloud Videos", + "base_url": null, + "title_page": null, + "github": "JohnsonSign/MaST-Pre", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shen_Masked_Spatio-Temporal_Structure_Prediction_for_Self-supervised_Learning_on_Point_Cloud_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09245", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Parametric Classification for Generalized Category Discovery: A Baseline Study", + "base_url": null, + "title_page": null, + "github": "CVMI-Lab/SimGCD", + "web_page": "https://wen-xin.info/simgcd/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wen_Parametric_Classification_for_Generalized_Category_Discovery_A_Baseline_Study_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.11727", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Object-Centric Multiple Object Tracking", + "base_url": null, + "title_page": null, + "github": "amazon-science/object-centric-multiple-object-tracking", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Object-Centric_Multiple_Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.00233", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Locating Noise is Halfway Denoising for Semi-Supervised Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_Locating_Noise_is_Halfway_Denoising_for_Semi-Supervised_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Learning Semi-Supervised Gaussian Mixture Models for Generalized Category Discovery", + "base_url": null, + "title_page": null, + "github": "DTennant/GPC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Learning_Semi-supervised_Gaussian_Mixture_Models_for_Generalized_Category_Discovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.06144", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "LoCUS: Learning Multiscale 3D-Consistent Features from Posed Images", + "base_url": null, + "title_page": null, + "github": "dakloepfer/locus", + "web_page": "https://www.robots.ox.ac.uk/~vgg/research/locus/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kloepfer_LoCUS_Learning_Multiscale_3D-consistent_Features_from_Posed_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Stable Cluster Discrimination for Deep Clustering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qian_Stable_Cluster_Discrimination_for_Deep_Clustering_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Cross-Modal Scalable Hyperbolic Hierarchical Clustering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Long_Cross-modal_Scalable_Hierarchical_Clustering_in_Hyperbolic_space_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-Point Supervision", + "base_url": null, + "title_page": null, + "github": "dsc1126/RWSeg", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Collaborative_Propagation_on_Multiple_Instance_Graphs_for_3D_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.05110", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Semantics Meets Temporal Correspondence: Self-Supervised Object-Centric Learning in Videos", + "base_url": null, + "title_page": null, + "github": "shvdiwnkozbw/SMTC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qian_Semantics_Meets_Temporal_Correspondence_Self-supervised_Object-centric_Learning_in_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09951", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Proxy_Anchor-based_Unsupervised_Learning_for_Continuous_Generalized_Category_Discovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10943", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "DreamTeacher: Pretraining Image Backbones with Deep Generative Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://research.nvidia.com/labs/toronto-ai/DreamTeacher/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_DreamTeacher_Pretraining_Image_Backbones_with_Deep_Generative_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07487", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "MATE: Masked Autoencoders are Online 3D Test-Time Learners", + "base_url": null, + "title_page": null, + "github": "jmiemirza/MATE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mirza_MATE_Masked_Autoencoders_are_Online_3D_Test-Time_Learners_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.11432", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels", + "base_url": null, + "title_page": null, + "github": "CoderHHX/PADDLES", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_PADDLES_Phase-Amplitude_Spectrum_Disentangled_Early_Stopping_for_Learning_with_Noisy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.03462", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Calibrating Uncertainty for Semi-Supervised Crowd Counting", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/LI_Calibrating_Uncertainty_for_Semi-Supervised_Crowd_Counting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09887", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Test Time Adaptation for Blind Image Quality Assessment", + "base_url": null, + "title_page": null, + "github": "subhadeeproy2000/TTA-IQA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Roy_Test_Time_Adaptation_for_Blind_Image_Quality_Assessment_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14735", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + }, + { + "title": "Deep Multiview Clustering by Contrasting Cluster Assignments", + "base_url": null, + "title_page": null, + "github": "chenjie20/CVCL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Deep_Multiview_Clustering_by_Contrasting_Cluster_Assignments_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.10769", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Self-, Semi-, Meta-, Unsupervised Learning" + } +] \ No newline at end of file diff --git a/json_data/2023/main/transfer-low-shot-and-continual-learning.json b/json_data/2023/main/transfer-low-shot-and-continual-learning.json new file mode 100644 index 0000000..ffc9f90 --- /dev/null +++ b/json_data/2023/main/transfer-low-shot-and-continual-learning.json @@ -0,0 +1,326 @@ +[ + { + "title": "Frequency Guidance Matters in Few-Shot Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_Frequency_Guidance_Matters_in_Few-Shot_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning", + "base_url": null, + "title_page": null, + "github": "ziplab/SPT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_Sensitivity-Aware_Visual_Parameter-Efficient_Fine-Tuning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08566", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion", + "base_url": null, + "title_page": null, + "github": "Yushu-Li/OWTTT", + "web_page": null, + "github_page": "https://yushu-li.github.io/owttt-site/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_On_the_Robustness_of_Open-World_Test-Time_Training_Self-Training_with_Dynamic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09942", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "Generating Instance-Level Prompts for Rehearsal-Free Continual Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jung_Generating_Instance-level_Prompts_for_Rehearsal-free_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "Boosting Novel Category Discovery over Domains with Soft Contrastive Learning and all in One Classifier", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zang_Boosting_Novel_Category_Discovery_Over_Domains_with_Soft_Contrastive_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.11262", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "A Soft Nearest-Neighbor Framework for Continual Semi-Supervised Learning", + "base_url": null, + "title_page": null, + "github": "kangzhiq/NNCSL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kang_A_Soft_Nearest-Neighbor_Framework_for_Continual_Semi-Supervised_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.05102", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation", + "base_url": null, + "title_page": null, + "github": "xmed-lab/GraphEcho", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_GraphEcho_Graph-Driven_Unsupervised_Domain_Adaptation_for_Echocardiogram_Video_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11145", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "ViperGPT: Visual Inference via Python Execution for Reasoning", + "base_url": null, + "title_page": null, + "github": "cvlab-columbia/viper", + "web_page": "https://viper.cs.columbia.edu/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Suris_ViperGPT_Visual_Inference_via_Python_Execution_for_Reasoning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08128", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "Improved Visual Fine-Tuning with Natural Language Supervision", + "base_url": null, + "title_page": null, + "github": "idstcv/TeS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Improved_Visual_Fine-tuning_with_Natural_Language_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01489", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "Preparing the Future for Continual Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Preparing_the_Future_for_Continual_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "MAP: Towards Balanced Generalization of IID and OOD through Model-Agnostic Adapters", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_MAP_Towards_Balanced_Generalization_of_IID_and_OOD_through_Model-Agnostic_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + }, + { + "title": "Space-Time Prompting for Video Class-Incremental Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pei_Space-time_Prompting_for_Video_Class-incremental_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, and Continual Learning" + } +] \ No newline at end of file diff --git a/json_data/2023/main/transfer-low-shot-continual-long-tail-learning.json b/json_data/2023/main/transfer-low-shot-continual-long-tail-learning.json new file mode 100644 index 0000000..7884a84 --- /dev/null +++ b/json_data/2023/main/transfer-low-shot-continual-long-tail-learning.json @@ -0,0 +1,2972 @@ +[ + { + "title": "ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition", + "base_url": null, + "title_page": null, + "github": "cool-xuan/Imbalanced_SAM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_ImbSAM_A_Closer_Look_at_Sharpness-Aware_Minimization_in_Class-Imbalanced_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07815", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "LFS-GAN: Lifelong Few-Shot Image Generation", + "base_url": null, + "title_page": null, + "github": "JJuOn/LFS-GAN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Seo_LFS-GAN_Lifelong_Few-Shot_Image_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11917", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection", + "base_url": null, + "title_page": null, + "github": "YuyangSunshine/ABR_IOD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Augmented_Box_Replay_Overcoming_Foreground_Shift_for_Incremental_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12427", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "brdav/cma", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bruggemann_Contrastive_Model_Adaptation_for_Cross-Condition_Robustness_in_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05194", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Towards Effective Instance Discrimination Contrastive Loss for Unsupervised Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "zhyx12/EIDCo", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Towards_Effective_Instance_Discrimination_Contrastive_Loss_for_Unsupervised_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2202.02802", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Adversarial Bayesian Augmentation for Single-Source Domain Generalization", + "base_url": null, + "title_page": null, + "github": "shengcheng/ABA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_Adversarial_Bayesian_Augmentation_for_Single-Source_Domain_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09520", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Measuring Asymmetric Gradient Discrepancy in Parallel Continual Learning", + "base_url": null, + "title_page": null, + "github": "fanlyu/maxdo", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lyu_Measuring_Asymmetric_Gradient_Discrepancy_in_Parallel_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_CSDA_Learning_Category-Scale_Joint_Feature_for_Domain_Adaptive_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Distilling from Similar Tasks for Transfer Learning on a Budget", + "base_url": null, + "title_page": null, + "github": "Kennethborup/DistillWeighted", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Borup_Distilling_from_Similar_Tasks_for_Transfer_Learning_on_a_Budget_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.12314", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cho_Complementary_Domain_Adaptation_and_Generalization_for_Unsupervised_Continual_Domain_Shift_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15833", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-Identification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://cvlab.yonsei.ac.kr/projects/CaCL/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Camera-Driven_Representation_Learning_for_Unsupervised_Domain_Adaptive_Person_Re-identification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11901", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Introducing Language Guidance in Prompt-based Continual Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Khan_Introducing_Language_Guidance_in_Prompt-based_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.15827", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Fast and Accurate Transferability Measurement by Evaluating Intra-Class Feature Variance", + "base_url": null, + "title_page": null, + "github": "snudatalab/TMI", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Fast_and_Accurate_Transferability_Measurement_by_Evaluating_Intra-class_Feature_Variance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05986", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "A Unified Continual Learning Framework with General Parameter-Efficient Tuning", + "base_url": null, + "title_page": null, + "github": "gqk/LAE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_A_Unified_Continual_Learning_Framework_with_General_Parameter-Efficient_Tuning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10070", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysis", + "base_url": null, + "title_page": null, + "github": "nkdinsdale/SFHarmony", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dinsdale_SFHarmony_Source_Free_Domain_Adaptation_for_Distributed_Neuroimaging_Analysis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15965", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Towards Realistic Evaluation of Industrial Continual Learning Scenarios with an Emphasis on Energy Consumption and Computational Footprint", + "base_url": null, + "title_page": null, + "github": "Vivek9Chavan/RECIL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chavan_Towards_Realistic_Evaluation_of_Industrial_Continual_Learning_Scenarios_with_an_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "TsWfYqz8qbk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "CDAC: Cross-Domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "wangkaihong/CDAC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_CDAC_Cross-domain_Attention_Consistency_in_Transformer_for_Domain_Adaptive_Semantic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.14703", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-Label", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Park_PC-Adapter_Topology-Aware_Adapter_for_Efficient_Domain_Adaption_on_Point_Clouds_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.16936", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "DETA: Denoised Task Adaptation for Few-Shot Learning", + "base_url": null, + "title_page": null, + "github": "JimZAI/DETA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_DETA_Denoised_Task_Adaptation_for_Few-Shot_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06315", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Activate and Reject: Towards Safe Domain Generalization under Category Shift", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Activate_and_Reject_Towards_Safe_Domain_Generalization_under_Category_Shift_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization", + "base_url": null, + "title_page": null, + "github": "zzwdx/MEDIC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Generalizable_Decision_Boundaries_Dualistic_Meta-Learning_for_Open_Set_Domain_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09391", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Continual Zero-Shot Learning through Semantically Guided Generative Random Walks", + "base_url": null, + "title_page": null, + "github": "wx-zhang/IGCZSL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Continual_Zero-Shot_Learning_through_Semantically_Guided_Generative_Random_Walks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12366", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis", + "base_url": null, + "title_page": null, + "github": "leolyj/3DPC-GZSL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Zero-Shot_Point_Cloud_Segmentation_by_Semantic-Visual_Aware_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "MDCS: More Diverse Experts with Consistency Self-Distillation for Long-Tailed Recognition", + "base_url": null, + "title_page": null, + "github": "fistyee/MDCS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_MDCS_More_Diverse_Experts_with_Consistency_Self-distillation_for_Long-tailed_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09922", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Building a Winning Team: Selecting Source Model Ensembles using a Submodular Transferability Estimation Approach", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/B_Building_a_Winning_Team_Selecting_Source_Model_Ensembles_using_a_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02429", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Confidence-based Visual Dispersal for Few-Shot Unsupervised Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "Bostoncake/C-VisDiT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiong_Confidence-based_Visual_Dispersal_for_Few-shot_Unsupervised_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.15575", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_BEV-DG_Cross-Modal_Learning_under_Birds-Eye_View_for_Domain_Generalization_of_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06530", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "CDFSL-V: Cross-Domain Few-Shot Learning for Videos", + "base_url": null, + "title_page": null, + "github": "Sarinda251/CDFSL-V", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Samarasinghe_CDFSL-V_Cross-Domain_Few-Shot_Learning_for_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03989", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Herath_Energy-based_Self-Training_and_Normalization_for_Unsupervised_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-Trained Vision-Language Models", + "base_url": null, + "title_page": null, + "github": "wuw2019/R-AMT", + "web_page": null, + "github_page": "https://wuw2019.github.io/R-AMT/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Regularized_Mask_Tuning_Uncovering_Hidden_Knowledge_in_Pre-Trained_Vision-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15049", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "NAPA-VQ: Neighborhood-Aware Prototype Augmentation with Vector Quantization for Continual Learning", + "base_url": null, + "title_page": null, + "github": "TamashaM/NAPA-VQ", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Malepathirana_NAPA-VQ_Neighborhood-Aware_Prototype_Augmentation_with_Vector_Quantization_for_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09297", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance", + "base_url": null, + "title_page": null, + "github": "OoDBag/RISE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_A_Sentence_Speaks_a_Thousand_Images_Domain_Generalization_through_Distilling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.12530", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "ViM: Vision Middleware for Unified Downstream Transferring", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_ViM_Vision_Middleware_for_Unified_Downstream_Transferring_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06911", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Learning to Learn: How to Continuously Teach Humans and Machines", + "base_url": null, + "title_page": null, + "github": "ZhangLab-DeepNeuroCogLab/Learning2Learn", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Singh_Learning_to_Learn_How_to_Continuously_Teach_Humans_and_Machines_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.15470", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "xz1TSRAQCN4", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://vlislab22.github.io/CTCL/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_A_Good_Student_is_Cooperative_and_Reliable_CNN-Transformer_Collaborative_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12574", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning", + "base_url": null, + "title_page": null, + "github": "moonjunyyy/Si-Blurry", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Moon_Online_Class_Incremental_Learning_on_Stochastic_Blurry_Task_Boundary_via_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09303", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Heterogeneous Forgetting Compensation for Class-Incremental Learning", + "base_url": null, + "title_page": null, + "github": "JiahuaDong/HFC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Heterogeneous_Forgetting_Compensation_for_Class-Incremental_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03374", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Disposable Transfer Learning for Selective Source Task Unlearning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Koh_Disposable_Transfer_Learning_for_Selective_Source_Task_Unlearning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09971", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Online Continual Learning on Hierarchical Label Expansion", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Online_Continual_Learning_on_Hierarchical_Label_Expansion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14374", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Black-Box Unsupervised Domain Adaptation with Bi-Directional Atkinson-Shiffrin Memory", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Black-Box_Unsupervised_Domain_Adaptation_with_Bi-Directional_Atkinson-Shiffrin_Memory_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13236", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Local and Global Logit Adjustments for Long-Tailed Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tao_Local_and_Global_Logit_Adjustments_for_Long-Tailed_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "FS-DETR: Few-Shot DEtection TRansformer with Prompting and without Re-Training", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bulat_FS-DETR_Few-Shot_DEtection_TRansformer_with_Prompting_and_without_Re-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.04845", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Tuning Pre-Trained Model via Moment Probing", + "base_url": null, + "title_page": null, + "github": "mingzeG/Moment-Probing", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_Tuning_Pre-trained_Model_via_Moment_Probing_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11342", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Benchmarking Low-Shot Robustness to Natural Distribution Shifts", + "base_url": null, + "title_page": null, + "github": "Aaditya-Singh/Low-Shot-Robustness", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Singh_Benchmarking_Low-Shot_Robustness_to_Natural_Distribution_Shifts_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.11263", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Label-Guided Knowledge Distillation for Continual Semantic Segmentation on 2D Images and 3D Point Clouds", + "base_url": null, + "title_page": null, + "github": "Ze-Yang/LGKD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Label-Guided_Knowledge_Distillation_for_Continual_Semantic_Segmentation_on_2D_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "ETran: Energy-based Transferability Estimation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gholami_ETran_Energy-Based_Transferability_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.02027", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "PØDA: Prompt-Driven Zero-Shot Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "astra-vision/PODA", + "web_page": null, + "github_page": "https://astra-vision.github.io/PODA/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fahes_PODA_Prompt-driven_Zero-shot_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.03241", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "kataxQoPuSE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Local Context-Aware Active Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "tsun/LADA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Local_Context-Aware_Active_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.12856", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition", + "base_url": null, + "title_page": null, + "github": "simplify23/MRN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_MRN_Multiplexed_Routing_Network_for_Incremental_Multilingual_Text_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.14758", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Few-Shot Dataset Distillation via Translative Pre-Training", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Few-Shot_Dataset_Distillation_via_Translative_Pre-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Wasserstein Expansible Variational Autoencoder for Discriminative and Generative Continual Learning", + "base_url": null, + "title_page": null, + "github": "dtuzi123/WEVAE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_Wasserstein_Expansible_Variational_Autoencoder_for_Discriminative_and_Generative_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Tangent Model Composition for Ensembling and Continual Fine-Tuning", + "base_url": null, + "title_page": null, + "github": "tianyu139/tangent-model-composition", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Tangent_Model_Composition_for_Ensembling_and_Continual_Fine-tuning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08114", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Look at the Neighbor: Distortion-Aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "zhengxuJosh/DATR", + "web_page": null, + "github_page": "https://vlislab22.github.io/DATR/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Look_at_the_Neighbor_Distortion-aware_Unsupervised_Domain_Adaptation_for_Panoramic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.05493", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Homeomorphism Alignment for Unsupervised Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "buerzlh/HMA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Homeomorphism_Alignment_for_Unsupervised_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Knowledge Restore and Transfer for Multi-Label Class-Incremental Learning", + "base_url": null, + "title_page": null, + "github": "witdsl/KRT-MLCIL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dong_Knowledge_Restore_and_Transfer_for_Multi-Label_Class-Incremental_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.13334", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Unsupervised Domain Adaptation for Training Event-based Networks using Contrastive Learning and Uncorrelated Conditioning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jian_Unsupervised_Domain_Adaptation_for_Training_Event-Based_Networks_Using_Contrastive_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12424", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "A Simple Recipe to Meta-Learn Forward and Backward Transfer", + "base_url": null, + "title_page": null, + "github": "Aladoro/SimpleMetaLearner4ContinualLearning", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cetin_A_Simple_Recipe_to_Meta-Learn_Forward_and_Backward_Transfer_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Dynamic Residual Classifier for Class Incremental Learning", + "base_url": null, + "title_page": null, + "github": "chen-xw/DRC-CIL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Dynamic_Residual_Classifier_for_Class_Incremental_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.13305", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Concept-Wise Fine-Tuning Matters in Preventing Negative Transfer", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Concept-wise_Fine-tuning_Matters_in_Preventing_Negative_Transfer_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Online Prototype Learning for Online Continual Learning", + "base_url": null, + "title_page": null, + "github": "weilllllls/OnPro", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Online_Prototype_Learning_for_Online_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.00301", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Bidirectional Alignment for Domain Adaptive Detection with Transformers", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_Bidirectional_Alignment_for_Domain_Adaptive_Detection_with_Transformers_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Borrowing Knowledge from Pre-Trained Language Model: A New Data-Efficient Visual Learning Paradigm", + "base_url": null, + "title_page": null, + "github": "BIT-DA/BorLan", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Borrowing_Knowledge_From_Pre-trained_Language_Model_A_New_Data-efficient_Visual_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "CLR: Channel-Wise Lightweight Reprogramming for Continual Learning", + "base_url": null, + "title_page": null, + "github": "gyhandy/Channel-wise-Lightweight-Reprogramming", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ge_CLR_Channel-wise_Lightweight_Reprogramming_for_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11386", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "hmOtuNC1ANU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://sites.google.com/view/mmcotta", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Multi-Modal_Continual_Test-Time_Adaptation_for_3D_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10457", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Panos_First_Session_Adaptation_A_Strong_Replay-Free_Baseline_for_Class-Incremental_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13199", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Domain Adaptive Few-Shot Open-Set Learning", + "base_url": null, + "title_page": null, + "github": "DebabrataPal7/DAFOSNET", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pal_Domain_Adaptive_Few-Shot_Open-Set_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.12814", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Rethinking_the_Role_of_Pre-Trained_Networks_in_Source-Free_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.07585", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Rapid Adaptation in Online Continual Learning: Are we Evaluating it Right?", + "base_url": null, + "title_page": null, + "github": "drimpossible/EvalOCL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Al_Kader_Hammoud_Rapid_Adaptation_in_Online_Continual_Learning_Are_We_Evaluating_It_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.09275", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "H8Cyh-7xltg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Multi-Grained Temporal Prototype Learning for Few-Shot Video Object Segmentation", + "base_url": null, + "title_page": null, + "github": "nankepan/VIPMT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Multi-grained_Temporal_Prototype_Learning_for_Few-shot_Video_Object_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11160", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "A Low-Shot Object Counting Network with Iterative Prototype Adaptation", + "base_url": null, + "title_page": null, + "github": "djukicn/loca", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Dukic_A_Low-Shot_Object_Counting_Network_With_Iterative_Prototype_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.08217", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Towards Better Robustness against Common Corruptions for Unsupervised Domain Adaptation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gao_Towards_Better_Robustness_against_Common_Corruptions_for_Unsupervised_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Alleviating Catastrophic Forgetting of Incremental Object Detection via Within-Class and Between-Class Knowledge Distillation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kang_Alleviating_Catastrophic_Forgetting_of_Incremental_Object_Detection_via_Within-Class_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Class-Aware Patch Embedding Adaptation for Few-Shot Image Classification", + "base_url": null, + "title_page": null, + "github": "FushengHao/CPEA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hao_Class-Aware_Patch_Embedding_Adaptation_for_Few-Shot_Image_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Order-Preserving Consistency Regularization for Domain Adaptation and Generalization", + "base_url": null, + "title_page": null, + "github": "TL-UESTC/OCR_MindSpore", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jing_Order-preserving_Consistency_Regularization_for_Domain_Adaptation_and_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.13258", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "val-iisc/DSiT-SFDA", + "web_page": "https://val.cds.iisc.ac.in/DSiT-SFDA/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sanyal_Domain-Specificity_Inducing_Transformers_for_Source-Free_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14023", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Diffusion Model as Representation Learner", + "base_url": null, + "title_page": null, + "github": "Adamdad/Repfusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Diffusion_Model_as_Representation_Learner_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10916", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "σ-Adaptive Decoupled Prototype for Few-Shot Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Du_s-Adaptive_Decoupled_Prototype_for_Few-Shot_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Growing a Brain with Sparsity-Inducing Generation for Continual Learning", + "base_url": null, + "title_page": null, + "github": "Jin0316/GrowBrain", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jin_Growing_a_Brain_with_Sparsity-Inducing_Generation_for_Continual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "DomainAdaptor: A Novel Approach to Test-Time Adaptation", + "base_url": null, + "title_page": null, + "github": "koncle/DomainAdaptor", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_DomainAdaptor_A_Novel_Approach_to_Test-time_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10297", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Reconciling Object-Level and Global-Level Objectives for Long-Tail Detection", + "base_url": null, + "title_page": null, + "github": "EricZsy/ROG", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Reconciling_Object-Level_and_Global-Level_Objectives_for_Long-Tail_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Domain Generalization via Balancing Training Difficulty and Model Capability", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Domain_Generalization_via_Balancing_Training_Difficulty_and_Model_Capability_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.00844", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Understanding Hessian Alignment for Domain Generalization", + "base_url": null, + "title_page": null, + "github": "huawei-noah/Federated-Learning", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hemati_Understanding_Hessian_Alignment_for_Domain_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11778", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Vision Transformer Adapters for Generalizable Multitask Learning", + "base_url": null, + "title_page": null, + "github": "IVRL/VTAGML", + "web_page": null, + "github_page": "https://ivrl.github.io/VTAGML/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bhattacharjee_Vision_Transformer_Adapters_for_Generalizable_Multitask_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12372", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "MED5nbn9ACM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Focus on Your Target: A Dual Teacher-Student Framework for Domain-Adaptive Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "xinyuehuo/DTS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huo_Focus_on_Your_Target_A_Dual_Teacher-Student_Framework_for_Domain-Adaptive_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09083", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Masked Retraining Teacher-Student Framework for Domain Adaptive Object Detection", + "base_url": null, + "title_page": null, + "github": "JeremyZhao1998/MRT-release", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Masked_Retraining_Teacher-Student_Framework_for_Domain_Adaptive_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "GGhBn6akViU", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "DandelionNet: Domain Composition with Instance Adaptive Classification for Domain Generalization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_DandelionNet_Domain_Composition_with_Instance_Adaptive_Classification_for_Domain_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "CAFA: Class-Aware Feature Alignment for Test-Time Adaptation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jung_CAFA_Class-Aware_Feature_Alignment_for_Test-Time_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.00205", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Image-Free Classifier Injection for Zero-Shot Classification", + "base_url": null, + "title_page": null, + "github": "ExplainableML/ImageFreeZSL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Christensen_Image-Free_Classifier_Injection_for_Zero-Shot_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10599", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "CBA: Improving Online Continual Learning via Continual Bias Adaptor", + "base_url": null, + "title_page": null, + "github": "wqza/CBA-online-CL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_CBA_Improving_Online_Continual_Learning_via_Continual_Bias_Adaptor_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06925", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Masked Autoencoders are Efficient Class Incremental Learners", + "base_url": null, + "title_page": null, + "github": "scok30/MAE-CIL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhai_Masked_Autoencoders_are_Efficient_Class_Incremental_Learners_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12510", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization", + "base_url": null, + "title_page": null, + "github": "lingeringlight/DomainDrop", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_DomainDrop_Suppressing_Domain-Sensitive_Channels_for_Domain_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10285", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models", + "base_url": null, + "title_page": null, + "github": "Thunderbeee/ZSCL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zheng_Preventing_Zero-Shot_Transfer_Degradation_in_Continual_Learning_of_Vision-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06628", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Incremental Generalized Category Discovery", + "base_url": null, + "title_page": null, + "github": "DTennant/Incremental-Generalized-Category-Discovery", + "web_page": "https://bzhao.me/iNatIGCD/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Incremental_Generalized_Category_Discovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.14310", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-Trained Model", + "base_url": null, + "title_page": null, + "github": "GengDavid/SLCA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_SLCA_Slow_Learner_with_Classifier_Alignment_for_Continual_Learning_on_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05118", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Efficient_Model_Personalization_in_Federated_Learning_via_Client-Specific_Prompt_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.15367", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "iDAG: Invariant DAG Searching for Domain Generalization", + "base_url": null, + "title_page": null, + "github": "lccurious/iDAG", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_iDAG_Invariant_DAG_Searching_for_Domain_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "SSDA: Secure Source-Free Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "ML-Security-Research-LAB/SSDA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ahmed_SSDA_Secure_Source-Free_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Learning Pseudo-Relations for Cross-Domain Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "DZhaoXd/RTea", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Learning_Pseudo-Relations_for_Cross-domain_Semantic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Self-Organizing_Pathway_Expansion_for_Non-Exemplar_Class-Incremental_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Improved Knowledge Transfer for Semi-Supervised Domain Adaptation via Trico Training Strategy", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ngo_Improved_Knowledge_Transfer_for_Semi-Supervised_Domain_Adaptation_via_Trico_Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Few-Shot Continual Infomax Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gu_Few-shot_Continual_Infomax_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation", + "base_url": null, + "title_page": null, + "github": "susaha/edaps", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Saha_EDAPS_Enhanced_Domain-Adaptive_Panoptic_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.14291", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Label-Efficient Online Continual Object Detection in Streaming Video", + "base_url": null, + "title_page": null, + "github": "showlab/Efficient-CLS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Label-Efficient_Online_Continual_Object_Detection_in_Streaming_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.00309", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Prototypical Kernel Learning and Open-Set Foreground Perception for Generalized Few-Shot Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Prototypical_Kernel_Learning_and_Open-set_Foreground_Perception_for_Generalized_Few-shot_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04952", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "MSI: Maximize Support-Set Information for Few-Shot Segmentation", + "base_url": null, + "title_page": null, + "github": "moonsh/MSI-Maximize-Support-Set-Information-ICCV2023", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Moon_MSI_Maximize_Support-Set_Information_for_Few-Shot_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.04673", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "AREA: Adaptive Reweighting via Effective Area for Long-Tailed Classification", + "base_url": null, + "title_page": null, + "github": "xiaohua-chen/AREA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_AREA_Adaptive_Reweighting_via_Effective_Area_for_Long-Tailed_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization", + "base_url": null, + "title_page": null, + "github": "prithv1/PASTA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chattopadhyay_PASTA_Proportional_Amplitude_Spectrum_Training_Augmentation_for_Syn-to-Real_Domain_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.00979", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Personalized Semantics Excitation for Federated Image Classification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xia_Personalized_Semantics_Excitation_for_Federated_Image_Classification_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Few-Shot Video Classification via Representation Fusion and Promotion Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xia_Few-Shot_Video_Classification_via_Representation_Fusion_and_Promotion_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + }, + { + "title": "Segmenting known Objects and Unseen Unknowns without Prior Knowledge", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://holisticseg.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gasperini_Segmenting_Known_Objects_and_Unseen_Unknowns_without_Prior_Knowledge_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2209.05407", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Transfer, Low-Shot, Continual, Long-Tail Learning" + } +] \ No newline at end of file diff --git a/json_data/2023/main/video-analysis-and-understanding.json b/json_data/2023/main/video-analysis-and-understanding.json new file mode 100644 index 0000000..0542cf5 --- /dev/null +++ b/json_data/2023/main/video-analysis-and-understanding.json @@ -0,0 +1,1379 @@ +[ + { + "title": "Long-Range Multimodal Pretraining for Movie Understanding", + "base_url": null, + "title_page": null, + "github": "dawitmureja/LMP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Argaw_Long-range_Multimodal_Pretraining_for_Movie_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09775.pdf", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Cross-View Semantic Alignment for Livestreaming Product Recognition", + "base_url": null, + "title_page": null, + "github": "adxcreative/RICE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Cross-view_Semantic_Alignment_for_Livestreaming_Product_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04912", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "HTML: Hybrid Temporal-Scale Multimodal Learning Framework for Referring Video Object Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://mingfei.info/HTML/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_HTML_Hybrid_Temporal-scale_Multimodal_Learning_Framework_for_Referring_Video_Object_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "DyGait: Exploiting Dynamic Representations for High-Performance Gait Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_DyGait_Exploiting_Dynamic_Representations_for_High-performance_Gait_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14953", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Identity-Consistent Aggregation for Video Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Deng_Identity-Consistent_Aggregation_for_Video_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07737", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "xuyu0010/SSA2lign", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_Augmenting_and_Aligning_Snippets_for_Few-Shot_Video_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.10451", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Action Sensitivity Learning for Temporal Action Localization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shao_Action_Sensitivity_Learning_for_Temporal_Action_Localization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.15701", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "SwinLSTM: Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM", + "base_url": null, + "title_page": null, + "github": "SongTang-x/SwinLSTM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_SwinLSTM_Improving_Spatiotemporal_Prediction_Accuracy_using_Swin_Transformer_and_LSTM_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09891", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "LVOS: A Benchmark for Long-Term Video Object Segmentation", + "base_url": null, + "title_page": null, + "github": "LingyiHongfd/LVOS", + "web_page": null, + "github_page": "https://lingyihongfd.github.io/lvos.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hong_LVOS_A_Benchmark_for_Long-term_Video_Object_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.10181", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "MGMAE: Motion Guided Masking for Video Masked Autoencoding", + "base_url": null, + "title_page": null, + "github": "MCG-NJU/MGMAE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_MGMAE_Motion_Guided_Masking_for_Video_Masked_Autoencoding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10794", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Markov Game Video Augmentation for Action Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Aziere_Markov_Game_Video_Augmentation_for_Action_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec", + "base_url": null, + "title_page": null, + "github": "Orange-OpenSource/Cool-Chic", + "web_page": null, + "github_page": "https://orange-opensource.github.io/Cool-Chic/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ladune_COOL-CHIC_Coordinate-based_Low_Complexity_Hierarchical_Image_Codec_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "ReGen: A Good Generative Zero-Shot Video Classifier Should be Rewarded", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bulat_ReGen_A_good_Generative_Zero-Shot_Video_Classifier_Should_be_Rewarded_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Task Agnostic Restoration of Natural Video Dynamics", + "base_url": null, + "title_page": null, + "github": "MKashifAli/TARONVD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ali_Task_Agnostic_Restoration_of_Natural_Video_Dynamics_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2206.03753", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Normalizing Flows for Human Pose Anomaly Detection", + "base_url": null, + "title_page": null, + "github": "orhir/STG-NF", + "web_page": null, + "github_page": "https://orhir.github.io/STG_NF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hirschorn_Normalizing_Flows_for_Human_Pose_Anomaly_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.10946", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Movement Enhancement toward Multi-Scale Video Feature Representation for Temporal Action Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Movement_Enhancement_toward_Multi-Scale_Video_Feature_Representation_for_Temporal_Action_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Event-Guided Procedure Planning from Instructional Videos with Text Supervision", + "base_url": null, + "title_page": null, + "github": "AlanWang0o0/ISEE-E3P", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Event-Guided_Procedure_Planning_from_Instructional_Videos_with_Text_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08885", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yoon_SCANet_Scene_Complexity_Aware_Network_for_Weakly-Supervised_Video_Moment_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.05241", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Spatio-Temporal Prompting Network for Robust Video Feature Extraction", + "base_url": null, + "title_page": null, + "github": "guanxiongsun/STPN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Spatio-temporal_Prompting_Network_for_Robust_Video_Feature_Extraction_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "TeD-SPAD: Temporal Distinctiveness for Self-Supervised Privacy-Preservation for Video Anomaly Detection", + "base_url": null, + "title_page": null, + "github": "UCF-CRCV/TeD-SPAD", + "web_page": null, + "github_page": "https://joefioresi718.github.io/TeD-SPAD_webpage/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fioresi_TeD-SPAD_Temporal_Distinctiveness_for_Self-Supervised_Privacy-Preservation_for_Video_Anomaly_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11072", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Non-Semantics Suppressed Mask Learning for Unsupervised Video Semantic Compression", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tian_Non-Semantics_Suppressed_Mask_Learning_for_Unsupervised_Video_Semantic_Compression_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "UnLoc: A Unified Framework for Video Localization Tasks", + "base_url": null, + "title_page": null, + "github": "google-research/scenic", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_UnLoc_A_Unified_Framework_for_Video_Localization_Tasks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11062", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "B7-mnHj5jno", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "SkeleTR: Towards Skeleton-based Action Recognition in the Wild", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Duan_SkeleTR_Towards_Skeleton-based_Action_Recognition_in_the_Wild_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "AutoAD II: The Sequel - Who, When, and What in Movie Audio Description", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://www.robots.ox.ac.uk/~vgg/research/autoad/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_AutoAD_II_The_Sequel_-_Who_When_and_What_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.06838", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "gMQSoib6lSI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "What can a Cook in Italy Teach a Mechanic in India? Action Recognition Generalisation over Scenarios and Locations", + "base_url": null, + "title_page": null, + "github": "Chiaraplizz/ARGO1M-What-can-a-cook", + "web_page": null, + "github_page": "https://chiaraplizz.github.io/what-can-a-cook/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Plizzari_What_Can_a_Cook_in_Italy_Teach_a_Mechanic_in_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.08713", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "C507QYUItTs", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Localizing Moments in Long Video via Multimodal Guidance", + "base_url": null, + "title_page": null, + "github": "waybarrios/guidance-based-video-grounding", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Barrios_Localizing_Moments_in_Long_Video_Via_Multimodal_Guidance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.13372", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "LAC - Latent Action Composition for Skeleton-based Action Segmentation", + "base_url": null, + "title_page": null, + "github": "walker1126/Latent_Action_Composition", + "web_page": null, + "github_page": "https://walker1126.github.io/LAC/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_LAC_-_Latent_Action_Composition_for_Skeleton-based_Action_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.14500", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "RIGID: Recurrent GAN Inversion and Editing of Real Face Videos", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://cnnlstm.github.io/RIGID/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_RIGID_Recurrent_GAN_Inversion_and_Editing_of_Real_Face_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06097", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "x_bUe6HxDeo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Uncertainty-Aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting", + "base_url": null, + "title_page": null, + "github": "oppo-us-research/USST", + "web_page": null, + "github_page": "https://actionlab-cv.github.io/EgoHandTrajPred/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bao_Uncertainty-aware_State_Space_Transformer_for_Egocentric_3D_Hand_Trajectory_Forecasting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08243", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "MYY6GmqZSJA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "What can Simple Arithmetic Operations do for Temporal Modeling?", + "base_url": null, + "title_page": null, + "github": "whwu95/ATM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_What_Can_Simple_Arithmetic_Operations_Do_for_Temporal_Modeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08908", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "UATVR: Uncertainty-Adaptive Text-Video Retrieval", + "base_url": null, + "title_page": null, + "github": "bofang98/UATVR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_UATVR_Uncertainty-Adaptive_Text-Video_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.06309", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation", + "base_url": null, + "title_page": null, + "github": "solicucu/D3G", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_D3G_Exploring_Gaussian_Prior_for_Temporal_Sentence_Grounding_with_Glance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04197", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Unsupervised Open-Vocabulary Object Localization in Videos", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_Unsupervised_Open-Vocabulary_Object_Localization_in_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.09858", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "HiVLP: Hierarchical Interactive Video-Language Pre-Training", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shao_HiVLP_Hierarchical_Interactive_Video-Language_Pre-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Scanning Only Once: An End-to-End Framework for Fast Temporal Grounding in Long Videos", + "base_url": null, + "title_page": null, + "github": "afcedf/SOONet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pan_Scanning_Only_Once_An_End-to-end_Framework_for_Fast_Temporal_Grounding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08345", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition", + "base_url": null, + "title_page": null, + "github": "TalalWasim/Video-FocalNets", + "web_page": null, + "github_page": "https://talalwasim.github.io/Video-FocalNets/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wasim_Video-FocalNets_Spatio-Temporal_Focal_Modulation_for_Video_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Djilali_Lip2Vec_Efficient_and_Robust_Visual_Speech_Recognition_via_Latent-to-Latent_Visual_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06112", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Video OWL-ViT: Temporally-Consistent Open-World Localization in Video", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Heigold_Video_OWL-ViT_Temporally-consistent_Open-world_Localization_in_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization", + "base_url": null, + "title_page": null, + "github": "fmthoker/tubelet-contrast", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Thoker_Tubelet-Contrastive_Self-Supervision_for_Video-Efficient_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11003", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Memory-and-Anticipation Transformer for Online Action Understanding", + "base_url": null, + "title_page": null, + "github": "Echo0125/Memory-and-Anticipation-Transformer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Memory-and-Anticipation_Transformer_for_Online_Action_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07893", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Video Action Segmentation via Contextually Refined Temporal Keypoints", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_Video_Action_Segmentation_via_Contextually_Refined_Temporal_Keypoints_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Knowing where to Focus: Event-Aware Transformer for Video Grounding", + "base_url": null, + "title_page": null, + "github": "jinhyunj/EaTR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jang_Knowing_Where_to_Focus_Event-aware_Transformer_for_Video_Grounding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06947", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "MPI-Flow: Learning Realistic Optical Flow with Multiplane Images", + "base_url": null, + "title_page": null, + "github": "Sharpiless/MPI-Flow", + "web_page": "https://sites.google.com/view/mpi-flow", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_MPI-Flow_Learning_Realistic_Optical_Flow_with_Multiplane_Images_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.06714", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Discovering Spatio-Temporal Rationales for Video Question Answering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Discovering_Spatio-Temporal_Rationales_for_Video_Question_Answering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12058", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Scalable Video Object Segmentation with Simplified Framework", + "base_url": null, + "title_page": null, + "github": "jimmy-dq/SimVOS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Scalable_Video_Object_Segmentation_with_Simplified_Framework_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09903", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Root Pose Decomposition Towards Generic Non-Rigid 3D Reconstruction with Monocular Videos", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://rpd-share.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Root_Pose_Decomposition_Towards_Generic_Non-rigid_3D_Reconstruction_with_Monocular_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10089", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "CkGnYxNZv70", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Helping Hands: An Object-Aware Ego-Centric Video Recognition Model", + "base_url": null, + "title_page": null, + "github": "Chuhanxx/helping_hand_for_egocentric_videos", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Helping_Hands_An_Object-Aware_Ego-Centric_Video_Recognition_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07918", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Modeling the Relative Visual Tempo for Self-Supervised Skeleton-based Action Recognition", + "base_url": null, + "title_page": null, + "github": "Zhuysheng/RVTCLR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Modeling_the_Relative_Visual_Tempo_for_Self-supervised_Skeleton-based_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation", + "base_url": null, + "title_page": null, + "github": "lxtGH/Tube-Link", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Tube-Link_A_Flexible_Cross_Tube_Framework_for_Universal_Video_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12782", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning", + "base_url": null, + "title_page": null, + "github": "alibaba-mmai-research/DiST", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qing_Disentangling_Spatial_and_Temporal_Learning_for_Efficient_Image-to-Video_Transfer_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.07911", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + }, + { + "title": "Tem-Adapter: Adapting Image-Text Pretraining for Video Question Answer", + "base_url": null, + "title_page": null, + "github": "XLiu443/Tem-adapter", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Tem-Adapter_Adapting_Image-Text_Pretraining_for_Video_Question_Answer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08414", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Video Analysis and Understanding" + } +] \ No newline at end of file diff --git a/json_data/2023/main/vision-and-audio.json b/json_data/2023/main/vision-and-audio.json new file mode 100644 index 0000000..abcd27a --- /dev/null +++ b/json_data/2023/main/vision-and-audio.json @@ -0,0 +1,326 @@ +[ + { + "title": "Sound Source Localization is All About Cross-Modal Alignment", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Senocak_Sound_Source_Localization_is_All_about_Cross-Modal_Alignment_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.10724", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "Class-Incremental Grouping Network for Continual Audio-Visual Learning", + "base_url": null, + "title_page": null, + "github": "stoneMo/CIGN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mo_Class-Incremental_Grouping_Network_for_Continual_Audio-Visual_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05281", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "Audio-Visual Class-Incremental Learning", + "base_url": null, + "title_page": null, + "github": "weiguoPian/AV-CIL_ICCV2023", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pian_Audio-Visual_Class-Incremental_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11073", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-Guided Speaker Embedding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Choi_DiffV2S_Diffusion-Based_Video-to-Speech_Synthesis_with_Vision-Guided_Speaker_Embedding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07787", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion", + "base_url": null, + "title_page": null, + "github": "ku-vai/TPoS", + "web_page": null, + "github_page": "https://ku-vai.github.io/TPoS/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jeong_The_Power_of_Sound_TPoS_Audio_Reactive_Video_Generation_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.04509", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "SIDGAN: High-Resolution Dubbed Video Generation via Shift-Invariant Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Muaz_SIDGAN_High-Resolution_Dubbed_Video_Generation_via_Shift-Invariant_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": "https://www.amazon.science/publications/sidgan-high-resolution-dubbed-video-generation-via-shift-invariant-learning", + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "On the Audio-Visual Synchronization for Lip-to-Speech Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Niu_On_the_Audio-visual_Synchronization_for_Lip-to-Speech_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.00502", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "Be Everywhere - Hear Everything (BEE): Audio Scene Reconstruction by Sparse Audio-Visual Samples", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Be_Everywhere_-_Hear_Everything_BEE_Audio_Scene_Reconstruction_by_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation", + "base_url": null, + "title_page": null, + "github": "HS-YN/DAPS", + "web_page": null, + "github_page": "https://hs-yn.github.io/DAPS/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yun_Dense_2D-3D_Indoor_Prediction_with_Sound_via_Aligned_Cross-Modal_Distillation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.11081", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "Hyperbolic Audio-Visual Zero-Shot Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hong_Hyperbolic_Audio-visual_Zero-shot_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12558", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "AdVerb: Visually Guided Audio Dereverberation", + "base_url": null, + "title_page": null, + "github": "Sreyan88/AdVerb-dereverb", + "web_page": null, + "github_page": "https://schowdhury671.github.io/adverb/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chowdhury_AdVerb_Visually_Guided_Audio_Dereverberation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12370", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "dZuR-pZ9uM0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + }, + { + "title": "Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation", + "base_url": null, + "title_page": null, + "github": "IFICL/SLfM", + "web_page": null, + "github_page": "https://ificl.github.io/SLfM/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Sound_Localization_from_Motion_Jointly_Learning_Sound_Direction_and_Camera_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11329", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Audio" + } +] \ No newline at end of file diff --git a/json_data/2023/main/vision-and-graphics.json b/json_data/2023/main/vision-and-graphics.json new file mode 100644 index 0000000..ffd26cd --- /dev/null +++ b/json_data/2023/main/vision-and-graphics.json @@ -0,0 +1,596 @@ +[ + { + "title": "Efficient Neural Supersampling on a Novel Gaming Dataset", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mercier_Efficient_Neural_Supersampling_on_a_Novel_Gaming_Dataset_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.01483", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "Locally Stylized Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": "hkust-vgd/nerfstyle", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pang_Locally_Stylized_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.10684", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://ivrl.github.io/NEMTO/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_NEMTO_Neural_Environment_Matting_for_Novel_View_and_Relighting_Synthesis_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.11963", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders", + "base_url": null, + "title_page": null, + "github": "piddnad/DDColor", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": "https://www.modelscope.cn/models/damo/cv_ddcolor_image-colorization/summary", + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kang_DDColor_Towards_Photo-Realistic_Image_Colorization_via_Dual_Decoders_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.11613", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis", + "base_url": null, + "title_page": null, + "github": "zju3dv/IntrinsicNeRF", + "web_page": null, + "github_page": "https://zju3dv.github.io/intrinsic_nerf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_IntrinsicNeRF_Learning_Intrinsic_Neural_Radiance_Fields_for_Editable_Novel_View_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.00647", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "PARIS: Part-Level Reconstruction and Motion Analysis for Articulated Objects", + "base_url": null, + "title_page": null, + "github": "3dlg-hcvc/paris", + "web_page": null, + "github_page": "https://3dlg-hcvc.github.io/paris/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_PARIS_Part-level_Reconstruction_and_Motion_Analysis_for_Articulated_Objects_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07391", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "tDSrROPCgUc", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model", + "base_url": null, + "title_page": null, + "github": "mingyuan-zhang/ReMoDiffuse", + "web_page": null, + "github_page": "https://mingyuan-zhang.github.io/projects/ReMoDiffuse.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_ReMoDiffuse_Retrieval-Augmented_Motion_Diffusion_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01116", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "wSddrIA_2p8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion", + "base_url": null, + "title_page": null, + "github": "tmaham/DS-Fusion", + "web_page": null, + "github_page": "https://ds-fusion.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/spaces/tmaham/DS-Fusion-Express", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tanveer_DS-Fusion_Artistic_Typography_via_Discriminated_and_Stylized_Diffusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09604", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "Dynamic Mesh-Aware Radiance Fields", + "base_url": null, + "title_page": null, + "github": "YilingQiao/DMRF", + "web_page": null, + "github_page": "https://mesh-aware-rf.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qiao_Dynamic_Mesh-Aware_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://drive.google.com/file/d/1uXg76v0CNVxgrQfBHPR5SbxIMXyPLFfQ/view", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "Neural Reconstruction of Relightable Human Model from Monocular Video", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Neural_Reconstruction_of_Relightable_Human_Model_from_Monocular_Video_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "Neural Microfacet Fields for Inverse Rendering", + "base_url": null, + "title_page": null, + "github": "half-potato/nmf", + "web_page": null, + "github_page": "https://half-potato.gitlab.io/posts/nmf/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mai_Neural_Microfacet_Fields_for_Inverse_Rendering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.17806", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "A Theory of Topological Derivatives for Inverse Rendering of Geometry", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://ishit.github.io/td/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mehta_A_Theory_of_Topological_Derivatives_for_Inverse_Rendering_of_Geometry_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09865", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "Vox-E: Text-Guided Voxel Editing of 3D Objects", + "base_url": null, + "title_page": null, + "github": "TAU-VAILab/Vox-E", + "web_page": null, + "github_page": "https://tau-vailab.github.io/Vox-E/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sella_Vox-E_Text-Guided_Voxel_Editing_of_3D_Objects_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.12048", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "StegaNeRF: Embedding Invisible Information within Neural Radiance Fields", + "base_url": null, + "title_page": null, + "github": "XGGNet/StegaNeRF", + "web_page": null, + "github_page": "https://xggnet.github.io/StegaNeRF/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_StegaNeRF_Embedding_Invisible_Information_within_Neural_Radiance_Fields_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.01602", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "GlobalMapper: Arbitrary-Shaped Urban Layout Generation", + "base_url": null, + "title_page": null, + "github": "Arking1995/GlobalMapper", + "web_page": null, + "github_page": "https://arking1995.github.io/GlobalMapper/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_GlobalMapper_Arbitrary-Shaped_Urban_Layout_Generation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09693", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "T_Zp91FCoFw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "Urban Radiance Field Representation with Deformable Neural Mesh Primitives", + "base_url": null, + "title_page": null, + "github": "DNMP/DNMP", + "web_page": null, + "github_page": "https://dnmp.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Urban_Radiance_Field_Representation_with_Deformable_Neural_Mesh_Primitives_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.10776", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "JABhlaVq4VA", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "End2End Multi-View Feature Matching with Differentiable Pose Optimization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://barbararoessle.github.io/e2e_multi_view_matching/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Roessle_End2End_Multi-View_Feature_Matching_with_Differentiable_Pose_Optimization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2205.01694", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "5bFIIDOHRZY", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "Tree-Structured Shading Decomposition", + "base_url": null, + "title_page": null, + "github": "gcgeng/inv-shade-trees", + "web_page": null, + "github_page": "https://chen-geng.com/inv-shade-trees/index.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Geng_Tree-Structured_Shading_Decomposition_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://chen-geng.com/files/inv-shade-trees.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "L7zD9zM_zcg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "Lens Parameter Estimation for Realistic Depth of Field Modeling", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://lvsn.github.io/inversedof/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Piche-Meunier_Lens_Parameter_Estimation_for_Realistic_Depth_of_Field_Modeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "vv06dr0p7oo", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism", + "base_url": null, + "title_page": null, + "github": "ZcyMonkey/AttT2M", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhong_AttT2M_Text-Driven_Human_Motion_Generation_with_Multi-Perspective_Attention_Mechanism_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.00796", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "Cross-Modal Latent Space Alignment for Image to Avatar Translation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/de_Guevara_Cross-modal_Latent_Space_Alignment_for_Image_to_Avatar_Translation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + }, + { + "title": "Computationally-Efficient Neural Image Compression with Shallow Decoders", + "base_url": null, + "title_page": null, + "github": "mandt-lab/shallow-ntc", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Computationally-Efficient_Neural_Image_Compression_with_Shallow_Decoders_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06244", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Graphics" + } +] \ No newline at end of file diff --git a/json_data/2023/main/vision-and-language.json b/json_data/2023/main/vision-and-language.json new file mode 100644 index 0000000..9e1c07d --- /dev/null +++ b/json_data/2023/main/vision-and-language.json @@ -0,0 +1,3431 @@ +[ + { + "title": "SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-Training", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_SMAUG_Sparse_Masked_Autoencoder_for_Efficient_Video-Language_Pre-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.11446", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "DiffusionRet: Generative Text-Video Retrieval with Diffusion Model", + "base_url": null, + "title_page": null, + "github": "jpthu17/DiffusionRet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jin_DiffusionRet_Generative_Text-Video_Retrieval_with_Diffusion_Model_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09867", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Explore and Tell: Embodied Visual Captioning in 3D Environments", + "base_url": null, + "title_page": null, + "github": "HAWLYQ/ET-Cap", + "web_page": null, + "github_page": "https://aim3-ruc.github.io/ExploreAndTell/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_Explore_and_Tell_Embodied_Visual_Captioning_in_3D_Environments_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10447", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Distilling Large Vision-Language Model with Out-of-Distribution Generalizability", + "base_url": null, + "title_page": null, + "github": "xuanlinli17/large_vlm_distillation_ood", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Distilling_Large_Vision-Language_Model_with_Out-of-Distribution_Generalizability_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.03135", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Learning Trajectory-Word Alignments for Video-Language Tasks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Learning_Trajectory-Word_Alignments_for_Video-Language_Tasks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.01953", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Variational Causal Inference Network for Explanatory Visual Question Answering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xue_Variational_Causal_Inference_Network_for_Explanatory_Visual_Question_Answering_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "TextManiA: Enriching Visual Feature by Text-Driven Manifold Augmentation", + "base_url": null, + "title_page": null, + "github": "postech-ami/TextManiA", + "web_page": null, + "github_page": "https://textmania.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye-Bin_TextManiA_Enriching_Visual_Feature_by_Text-driven_Manifold_Augmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14611", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Segment Every Reference Object in Spatial and Temporal Spaces", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Segment_Every_Reference_Object_in_Spatial_and_Temporal_Spaces_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Gradient-Regulated_Meta-Prompt_Learning_for_Generalizable_Vision-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.06571", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pre-Training", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Misalign_Contrast_then_Distill_Rethinking_Misalignments_in_Language-Image_Pre-training_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Toward Multi-Granularity Decision-Making: Explicit Visual Reasoning with Hierarchical Knowledge", + "base_url": null, + "title_page": null, + "github": "SuperJohnZhang/HCNMN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Toward_Multi-Granularity_Decision-Making_Explicit_Visual_Reasoning_with_Hierarchical_Knowledge_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bi_VL-Match_Enhancing_Vision-Language_Pretraining_with_Token-Level_and_Instance-Level_Matching_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Moment Detection in Long Tutorial Videos", + "base_url": null, + "title_page": null, + "github": "ioanacroi/longmoment-detr", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Croitoru_Moment_Detection_in_Long_Tutorial_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Not All Features Matter: Enhancing Few-Shot CLIP with Adaptive Prior Refinement", + "base_url": null, + "title_page": null, + "github": "yangyangyang127/APE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Not_All_Features_Matter_Enhancing_Few-shot_CLIP_with_Adaptive_Prior_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01195", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://whoops-benchmark.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Bitton-Guetta_Breaking_Common_Sense_WHOOPS_A_Vision-and-Language_Benchmark_of_Synthetic_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.07274", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Advancing Referring Expression Segmentation Beyond Single Image", + "base_url": null, + "title_page": null, + "github": "shikras/d-cube", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Advancing_Referring_Expression_Segmentation_Beyond_Single_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.12452", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-World Learning", + "base_url": null, + "title_page": null, + "github": "yangyangyang127/PointCLIP_V2", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_PointCLIP_V2_Prompting_CLIP_and_GPT_for_Powerful_3D_Open-world_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.11682", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Unsupervised Prompt Tuning for Text-Driven Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/He_Unsupervised_Prompt_Tuning_for_Text-Driven_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding", + "base_url": null, + "title_page": null, + "github": "ZzZZCHS/WS-3DVG", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Distilling_Coarse-to-Fine_Semantic_Matching_Knowledge_for_Weakly_Supervised_3D_Visual_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09267", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "I can't Believe there's no Images! Learning Visual Tasks using Only Language Supervision", + "base_url": null, + "title_page": null, + "github": "allenai/close", + "web_page": "https://prior.allenai.org/projects/close", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gu_I_Cant_Believe_Theres_No_Images_Learning_Visual_Tasks_Using_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.09778", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples", + "base_url": null, + "title_page": null, + "github": "hengliusky/Few_shot_RVOS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Learning_Cross-Modal_Affinity_for_Referring_Video_Object_Segmentation_Targeting_Limited_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.02041", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "MeViS: A Large-Scale Benchmark for Video Segmentation with Motion Expressions", + "base_url": null, + "title_page": null, + "github": "henghuiding/MeViS", + "web_page": null, + "github_page": "https://henghuiding.github.io/MeViS/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ding_MeViS_A_Large-scale_Benchmark_for_Video_Segmentation_with_Motion_Expressions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08544", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Diverse Data Augmentation with Diffusions for Effective Test-Time Prompt Tuning", + "base_url": null, + "title_page": null, + "github": "chunmeifeng/DiffTPT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_Diverse_Data_Augmentation_with_Diffusions_for_Effective_Test-time_Prompt_Tuning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06038", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "ShapeScaffolder: Structure-Aware 3D Shape Generation from Text", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tian_ShapeScaffolder_Structure-Aware_3D_Shape_Generation_from_Text_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://www.yongliangyang.net/docs/shapescaffolder_iccv23.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "SuS-X: Training-Free Name-Only Transfer of Vision-Language Models", + "base_url": null, + "title_page": null, + "github": "vishaal27/SuS-X", + "web_page": null, + "github_page": "https://vishaal27.github.io/SuS-X-webpage/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Udandarao_SuS-X_Training-Free_Name-Only_Transfer_of_Vision-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.16198", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "X-Mesh: Towards Fast and Accurate Text-Driven 3D Stylization via Dynamic Textual Guidance", + "base_url": null, + "title_page": null, + "github": "xmu-xiaoma666/X-Mesh", + "web_page": null, + "github_page": "https://xmu-xiaoma666.github.io/Projects/X-Mesh/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_X-Mesh_Towards_Fast_and_Accurate_Text-driven_3D_Stylization_via_Dynamic_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15764", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation", + "base_url": null, + "title_page": null, + "github": "wudongming97/OnlineRefer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_OnlineRefer_A_Simple_Online_Baseline_for_Referring_Video_Object_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09356", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Attentive Mask CLIP", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Attentive_Mask_CLIP_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.08653", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Knowledge Proxy Intervention for Deconfounded Video Question Answering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Knowledge_Proxy_Intervention_for_Deconfounded_Video_Question_Answering_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "UniVTG: Towards Unified Video-Language Temporal Grounding", + "base_url": null, + "title_page": null, + "github": "showlab/UniVTG", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_UniVTG_Towards_Unified_Video-Language_Temporal_Grounding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16715", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Self-Supervised Cross-View Representation Reconstruction for Change Captioning", + "base_url": null, + "title_page": null, + "github": "tuyunbin/SCORER", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tu_Self-supervised_Cross-view_Representation_Reconstruction_for_Change_Captioning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Unified Coarse-to-Fine Alignment for Video-Text Retrieval", + "base_url": null, + "title_page": null, + "github": "Ziyang412/UCoFiA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Unified_Coarse-to-Fine_Alignment_for_Video-Text_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.10091", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Confidence-Aware Pseudo-Label Learning for Weakly Supervised Visual Grounding", + "base_url": null, + "title_page": null, + "github": "zjh31/CPL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Confidence-aware_Pseudo-label_Learning_for_Weakly_Supervised_Visual_Grounding_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "TextPSG: Panoptic Scene Graph Generation from Textual Descriptions", + "base_url": null, + "title_page": null, + "github": "chengyzhao/TextPSG", + "web_page": "https://vis-www.cs.umass.edu/TextPSG/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_TextPSG_Panoptic_Scene_Graph_Generation_from_Textual_Descriptions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.07056", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "_ZjMXMKjm58", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge", + "base_url": null, + "title_page": null, + "github": "wlin-at/MAXI", + "web_page": null, + "github_page": "https://wlin-at.github.io/maxi", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_MAtch_eXpand_and_Improve_Unsupervised_Finetuning_for_Zero-Shot_Action_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08914", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Unify_Align_and_Refine_Multi-Level_Semantic_Alignment_for_Radiology_Report_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15932", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "CLIPTrans: Transferring Visual Knowledge with Pre-Trained Models for Multimodal Machine Translation", + "base_url": null, + "title_page": null, + "github": "devaansh100/CLIPTrans", + "web_page": null, + "github_page": "https://devaansh100.github.io/projects/cliptrans/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gupta_CLIPTrans_Transferring_Visual_Knowledge_with_Pre-trained_Models_for_Multimodal_Machine_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.15226", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Learning Human-Human Interactions in Images from Weak Textual Supervision", + "base_url": null, + "title_page": null, + "github": "TAU-VAILab/learning-interactions", + "web_page": null, + "github_page": "https://tau-vailab.github.io/learning-interactions/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Alper_Learning_Human-Human_Interactions_in_Images_from_Weak_Textual_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.14104", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Jiang_BUS_Efficient_and_Effective_Vision-Language_Pre-Training_with_Bottom-Up_Patch_Summarization._ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.08504", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "3D-VisTA: Pre-Trained Transformer for 3D Vision and Text Alignment", + "base_url": null, + "title_page": null, + "github": "3d-vista/3D-VisTA", + "web_page": null, + "github_page": "https://3d-vista.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_3D-VisTA_Pre-trained_Transformer_for_3D_Vision_and_Text_Alignment_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.04352", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "uUtMaoif8DQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "ALIP: Adaptive Language-Image Pre-Training with Synthetic Caption", + "base_url": null, + "title_page": null, + "github": "deepglint/ALIP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_ALIP_Adaptive_Language-Image_Pre-Training_with_Synthetic_Caption_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.08428", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "LoGoPrompt: Synthetic Text Images can be Good Visual Prompts for Vision-Language Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://chengshiest.github.io/logo/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_LoGoPrompt_Synthetic_Text_Images_Can_Be_Good_Visual_Prompts_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01155", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Noise-Aware Learning from Web-Crawled Image-Text Data for Image Captioning", + "base_url": null, + "title_page": null, + "github": "kakaobrain/noc", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kang_Noise-Aware_Learning_from_Web-Crawled_Image-Text_Data_for_Image_Captioning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.13563", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qian_Decouple_Before_Interact_Multi-Modal_Prompt_Learning_for_Continual_Visual_Question_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3", + "base_url": null, + "title_page": null, + "github": "Yushi-Hu/PromptCap", + "web_page": null, + "github_page": "https://yushi-hu.github.io/promptcap_demo/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_PromptCap_Prompt-Guided_Image_Captioning_for_VQA_with_GPT-3_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.09699", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Grounded Image Text Matching with Mismatched Relation Reasoning", + "base_url": null, + "title_page": null, + "github": "SHTUPLUS/GITM-MR", + "web_page": null, + "github_page": "https://weiyana.github.io/pages/dataset.html", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Grounded_Image_Text_Matching_with_Mismatched_Relation_Reasoning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.01236", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "eHXm2LrSSqE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "GePSAn: Generative Procedure Step Anticipation in Cooking Videos", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Abdelsalam_GePSAn_Generative_Procedure_Step_Anticipation_in_Cooking_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models", + "base_url": null, + "title_page": null, + "github": "OSU-NLP-Group/LLM-Planner", + "web_page": null, + "github_page": "https://dki-lab.github.io/LLM-Planner/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Song_LLM-Planner_Few-Shot_Grounded_Planning_for_Embodied_Agents_with_Large_Language_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.04088", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control", + "base_url": null, + "title_page": null, + "github": "HenryHZY/VL-PET", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_VL-PET_Vision-and-Language_Parameter-Efficient_Tuning_via_Granularity_Control_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09804", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "With a Little Help from Your own Past: Prototypical Memory Networks for Image Captioning", + "base_url": null, + "title_page": null, + "github": "aimagelab/PMA-Net", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Barraco_With_a_Little_Help_from_Your_Own_Past_Prototypical_Memory_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12383", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models", + "base_url": null, + "title_page": null, + "github": "j-min/DallEval", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cho_DALL-Eval_Probing_the_Reasoning_Skills_and_Social_Biases_of_Text-to-Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2202.04053", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Learning Navigational Visual Representations with Semantic Map Supervision", + "base_url": null, + "title_page": null, + "github": "YicongHong/Ego2Map-NaViT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hong_Learning_Navigational_Visual_Representations_with_Semantic_Map_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12335", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://toneyaya.github.io/cotdet/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_CoTDet_Affordance_Knowledge_Prompting_for_Task_Driven_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01093", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Open Set Video HOI detection from Action-Centric Chain-of-Look Prompting", + "base_url": null, + "title_page": null, + "github": "southnx/ACoLP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xi_Open_Set_Video_HOI_detection_from_Action-Centric_Chain-of-Look_Prompting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Learning Concise and Descriptive Attributes for Visual Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yan_Learning_Concise_and_Descriptive_Attributes_for_Visual_Recognition_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.03685", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Open-Vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models", + "base_url": null, + "title_page": null, + "github": "mlvlab/OVQA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ko_Open-vocabulary_Video_Question_Answering_A_New_Benchmark_for_Evaluating_the_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09363", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Encyclopedic VQA: Visual Questions About Detailed Properties of Fine-Grained Categories", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://github.com/google-research/google-research/tree/master/encyclopedic_vqa", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mensink_Encyclopedic_VQA_Visual_Questions_About_Detailed_Properties_of_Fine-Grained_Categories_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.09224", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Story Visualization by Online Text Augmentation with Context Memory", + "base_url": null, + "title_page": null, + "github": "yonseivnl/cmota", + "web_page": null, + "github_page": "https://dcahn12.github.io/projects/CMOTA/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ahn_Story_Visualization_by_Online_Text_Augmentation_with_Context_Memory_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07575", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Transferable Decoding with Visual Entities for Zero-Shot Image Captioning", + "base_url": null, + "title_page": null, + "github": "FeiElysia/ViECap", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fei_Transferable_Decoding_with_Visual_Entities_for_Zero-Shot_Image_Captioning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16525", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Too Large; Data Reduction for Vision-Language Pre-Training", + "base_url": null, + "title_page": null, + "github": "showlab/datacentric.vlp", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Too_Large_Data_Reduction_for_Vision-Language_Pre-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.20087", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "ViLTA: Enhancing Vision-Language Pre-Training through Textual Augmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_ViLTA_Enhancing_Vision-Language_Pre-training_through_Textual_Augmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16689", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Zero-Shot Composed Image Retrieval with Textual Inversion", + "base_url": null, + "title_page": null, + "github": "miccunifi/SEARLE", + "web_page": "https://circo.micc.unifi.it/demo", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Baldrati_Zero-Shot_Composed_Image_Retrieval_with_Textual_Inversion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15247", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "SATR: Zero-Shot Semantic Segmentation of 3D Shapes", + "base_url": null, + "title_page": null, + "github": "Samir55/SATR", + "web_page": null, + "github_page": "https://samir55.github.io/SATR/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Abdelreheem_SATR_Zero-Shot_Semantic_Segmentation_of_3D_Shapes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.04909", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "CiT: Curation in Training for Effective Vision-Language Data", + "base_url": null, + "title_page": null, + "github": "facebookresearch/CiT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_CiT_Curation_in_Training_for_Effective_Vision-Language_Data_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2301.02241", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Self-Regulating Prompts: Foundational Model Adaptation without Forgetting", + "base_url": null, + "title_page": null, + "github": "muzairkhattak/PromptSRC", + "web_page": null, + "github_page": "https://muzairkhattak.github.io/PromptSRC/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Khattak_Self-regulating_Prompts_Foundational_Model_Adaptation_without_Forgetting_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.06948", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "VVLwL57UBDg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Learning to Ground Instructional Articles in Videos through Narrations", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mavroudi_Learning_to_Ground_Instructional_Articles_in_Videos_through_Narrations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.03802", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kurita_RefEgo_Referring_Expression_Comprehension_Dataset_from_First-Person_Perception_of_Ego4D_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12035", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Multi3DRefer: Grounding Text Description to Multiple 3D Objects", + "base_url": null, + "title_page": null, + "github": "3dlg-hcvc/M3DRef-CLIP", + "web_page": null, + "github_page": "https://3dlg-hcvc.github.io/multi3drefer/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Multi3DRefer_Grounding_Text_Description_to_Multiple_3D_Objects_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.05251", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Bayesian Prompt Learning for Image-Language Model Generalization", + "base_url": null, + "title_page": null, + "github": "saic-fi/Bayesian-Prompt-Learning", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Derakhshani_Bayesian_Prompt_Learning_for_Image-Language_Model_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2210.02390", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Who are You Referring to? Coreference Resolution in Image Narrations", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Goel_Who_Are_You_Referring_To_Coreference_Resolution_In_Image_Narrations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.14563", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Guiding Image Captioning Models Toward more Specific Captions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kornblith_Guiding_Image_Captioning_Models_Toward_More_Specific_Captions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.16686", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "PreSTU: Pre-Training for Scene-Text Understanding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kil_PreSTU_Pre-Training_for_Scene-Text_Understanding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2209.05534", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Exploring Group Video Captioning with Efficient Relational Approximation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Exploring_Group_Video_Captioning_with_Efficient_Relational_Approximation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "VLSlice: Interactive Vision-and-Language Slice Discovery", + "base_url": null, + "title_page": null, + "github": "slymane/vlslice", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Slyman_VLSlice_Interactive_Vision-and-Language_Slice_Discovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.06703", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": "https://drive.google.com/file/d/1JkbVXnCds6rOErUx-YWZmp3mQ3IDJuhi/view", + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Pretrained Language Models as Visual Planners for Human Assistance", + "base_url": null, + "title_page": null, + "github": "facebookresearch/vlamp", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Patel_Pretrained_Language_Models_as_Visual_Planners_for_Human_Assistance_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.09179", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "VQA Therapy: Exploring Answer Differences by Visually Grounding Answers", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://vizwiz.org/tasks-and-datasets/vqa-answer-therapy/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_VQA_Therapy_Exploring_Answer_Differences_by_Visually_Grounding_Answers_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11662", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation using only Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Towards_High-Fidelity_Text-Guided_3D_Face_Generation_and_Manipulation_Using_only_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.16758", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Zero-Shot Composed Image Retrieval with Textual Inversion", + "base_url": null, + "title_page": null, + "github": "miccunifi/SEARLE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Baldrati_Zero-Shot_Composed_Image_Retrieval_with_Textual_Inversion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15247", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "qxpNb9qxDQI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_PatchCT_Aligning_Patch_Set_and_Label_Set_with_Conditional_Transport_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.09066", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Lip Reading for Low-Resource Languages by Learning and Combining General Speech Knowledge and Language-Specific Knowledge", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Lip_Reading_for_Low-resource_Languages_by_Learning_and_Combining_General_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09311", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "ViewRefer: Grasp the Multi-View Knowledge for 3D Visual Grounding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_ViewRefer_Grasp_the_Multi-view_Knowledge_for_3D_Visual_Grounding_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16894", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "AerialVLN: Vision-and-Language Navigation for UAVs", + "base_url": null, + "title_page": null, + "github": "AirVLN/AirVLN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_AerialVLN_Vision-and-Language_Navigation_for_UAVs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06735", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Linear Spaces of Meanings: Compositional Structures in Vision-Language Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Trager_Linear_Spaces_of_Meanings_Compositional_Structures_in_Vision-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.14383", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "HiTeA: Hierarchical Temporal-Aware Video-Language Pre-Training", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ye_HiTeA_Hierarchical_Temporal-Aware_Video-Language_Pre-training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.14546", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "EgoTV: Egocentric Task Verification from Natural Language Task Descriptions", + "base_url": null, + "title_page": null, + "github": "facebookresearch/EgoTV", + "web_page": null, + "github_page": "https://rishihazra.github.io/EgoTV/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hazra_EgoTV_Egocentric_Task_Verification_from_Natural_Language_Task_Descriptions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.16975", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "SINC: Self-Supervised in-Context Learning for Vision-Language Tasks", + "base_url": null, + "title_page": null, + "github": "YiSyuanChen/SINC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_SINC_Self-Supervised_In-Context_Learning_for_Vision-Language_Tasks_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.07742", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation", + "base_url": null, + "title_page": null, + "github": "YanyuanQiao/VLN-PETL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qiao_VLN-PETL_Parameter-Efficient_Transfer_Learning_for_Vision-and-Language_Navigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10172", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Going Denser with Open-Vocabulary Part Segmentation", + "base_url": null, + "title_page": null, + "github": "facebookresearch/VLPart", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_Going_Denser_with_Open-Vocabulary_Part_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2305.11173", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Temporal Collection and Distribution for Referring Video Object Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://toneyaya.github.io/tempcd/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_Temporal_Collection_and_Distribution_for_Referring_Video_Object_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.03473", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Inverse Compositional Learning for Weakly-Supervised Relation Grounding", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Inverse_Compositional_Learning_for_Weakly-supervised_Relation_Grounding_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Why is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?", + "base_url": null, + "title_page": null, + "github": "CEWu/PTNL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Why_Is_Prompt_Tuning_for_Vision-Language_Models_Robust_to_Noisy_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11978", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "CHAMPAGNE: Learning Real-World Conversation from Large-Scale Web Videos", + "base_url": null, + "title_page": null, + "github": "wade3han/champagne", + "web_page": "https://seungjuhan.me/champagne/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Han_CHAMPAGNE_Learning_Real-world_Conversation_from_Large-Scale_Web_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09713", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "RCA-NOC: Relative Contrastive Alignment for Novel Object Captioning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fan_RCA-NOC_Relative_Contrastive_Alignment_for_Novel_Object_Captioning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "DIME-FM: DIstilling Multimodal and Efficient Foundation Models", + "base_url": null, + "title_page": null, + "github": "sunxm2357/DIME-FM", + "web_page": "https://cs-people.bu.edu/sunxm/DIME-FM/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sun_DIME-FM__DIstilling_Multimodal_and_Efficient_Foundation_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.18232", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Black Box Few-Shot Adaptation for Vision-Language Models", + "base_url": null, + "title_page": null, + "github": "saic-fi/LFA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ouali_Black_Box_Few-Shot_Adaptation_for_Vision-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.01752", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Shatter and Gather: Learning Referring Image Segmentation with Text Supervision", + "base_url": null, + "title_page": null, + "github": "kdwonn/SaG", + "web_page": null, + "github_page": "https://southflame.github.io/sag/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Shatter_and_Gather_Learning_Referring_Image_Segmentation_with_Text_Supervision_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.15512", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Accurate and Fast Compressed Video Captioning", + "base_url": null, + "title_page": null, + "github": "acherstyx/CoCap", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shen_Accurate_and_Fast_Compressed_Video_Captioning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.12867", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Exploring Temporal Concurrency for Video-Language Representation Learning", + "base_url": null, + "title_page": null, + "github": "hengRUC/TCP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Exploring_Temporal_Concurrency_for_Video-Language_Representation_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Verbs in Action: Improving Verb Understanding in Video-Language Models", + "base_url": null, + "title_page": null, + "github": "google-research/scenic", + "web_page": null, + "github_page": "https://github.com/google-research/scenic/tree/main/scenic/projects/verbs_in_action", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Momeni_Verbs_in_Action_Improving_Verb_Understanding_in_Video-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06708", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Sign Language Translation with Iterative Prototype", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yao_Sign_Language_Translation_with_Iterative_Prototype_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12191", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Contrastive Feature Masking Open-Vocabulary Vision Transformer", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kim_Contrastive_Feature_Masking_Open-Vocabulary_Vision_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.00775", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "9dH4LpStK-0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Toward Unsupervised Realistic Visual Question Answering", + "base_url": null, + "title_page": null, + "github": "chihhuiho/RGQA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Toward_Unsupervised_Realistic_Visual_Question_Answering_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05068", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "APPK_9DzpXE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "GridMM: Grid Memory Map for Vision-and-Language Navigation", + "base_url": null, + "title_page": null, + "github": "MrZihan/GridMM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_GridMM_Grid_Memory_Map_for_Vision-and-Language_Navigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12907", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Video Background Music Generation: Dataset, Method and Evaluation", + "base_url": null, + "title_page": null, + "github": "zhuole1025/SymMV", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhuo_Video_Background_Music_Generation_Dataset_Method_and_Evaluation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.11248", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval", + "base_url": null, + "title_page": null, + "github": "bladewaltz1/PromptSwitch", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Deng_Prompt_Switch_Efficient_CLIP_Adaptation_for_Text-Video_Retrieval_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.07648", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Prompt-Aligned Gradient for Prompt Tuning", + "base_url": null, + "title_page": null, + "github": "BeierZhu/Prompt-align", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhu_Prompt-aligned_Gradient_for_Prompt_Tuning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2205.14865", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kan_Knowledge-Aware_Prompt_Tuning_for_Generalizable_Vision-Language_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11186", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Order-Prompted Tag Sequence Generation for Video Tagging", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ma_Order-Prompted_Tag_Sequence_Generation_for_Video_Tagging_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "What does a Platypus Look Like? Generating Customized Prompts for Zero-Shot Image Classification", + "base_url": null, + "title_page": null, + "github": "sarahpratt/CuPL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Pratt_What_Does_a_Platypus_Look_Like_Generating_Customized_Prompts_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2209.03320", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "PromptStyler: Prompt-Driven Style Generation for Source-Free Domain Generalization", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://promptstyler.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cho_PromptStyler_Prompt-driven_Style_Generation_for_Source-free_Domain_Generalization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15199", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "0PsU4pbW0mQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_DiffDis_Empowering_Generative_Diffusion_Model_with_Cross-Modal_Discrimination_Capability_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.09306", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "EdaDet: Open-Vocabulary Object Detection using Early Dense Alignment", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://chengshiest.github.io/edadet/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_EdaDet_Open-Vocabulary_Object_Detection_Using_Early_Dense_Alignment_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01151", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition", + "base_url": null, + "title_page": null, + "github": "Exgc/AVMuST-TED", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cheng_MixSpeech_Cross-Modality_Self-Learning_with_Audio-Visual_Stream_Mixup_for_Visual_Speech_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05309", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Waffling Around for Performance: Visual Classification with Random Words and Broad Concepts", + "base_url": null, + "title_page": null, + "github": "ExplainableML/WaffleCLIP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Roth_Waffling_Around_for_Performance_Visual_Classification_with_Random_Words_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.07282", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "March in Chat: Interactive Prompting for Remote Embodied Referring Expression", + "base_url": null, + "title_page": null, + "github": "YanyuanQiao/MiC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Qiao_March_in_Chat_Interactive_Prompting_for_Remote_Embodied_Referring_Expression_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10141", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Chinese Text Recognition with a Pre-Trained CLIP-Like Model through Image-IDS Aligning", + "base_url": null, + "title_page": null, + "github": "FudanVI/FudanOCR", + "web_page": null, + "github_page": "https://github.com/FudanVI/FudanOCR/tree/main/image-ids-CTR", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yu_Chinese_Text_Recognition_with_A_Pre-Trained_CLIP-Like_Model_Through_Image-IDS_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.01083", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "OmniLabel: A Challenging Benchmark for Language-based Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://www.omnilabel.org/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Schulter_OmniLabel_A_Challenging_Benchmark_for_Language-Based_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.11463", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "IntentQA: Context-Aware Video Intent Reasoning", + "base_url": null, + "title_page": null, + "github": "JoseponLee/IntentQA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_IntentQA_Context-aware_Video_Intent_Reasoning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Sigmoid Loss for Language Image Pre-Training", + "base_url": null, + "title_page": null, + "github": "google-research/big_vision", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhai_Sigmoid_Loss_for_Language_Image_Pre-Training_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.15343", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "H4yPlDPomrI", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "What does CLIP Know About a Red Circle? Visual Prompt Engineering for VLMs", + "base_url": null, + "title_page": null, + "github": "suny-sht/clip-red-circle", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shtedritski_What_does_CLIP_know_about_a_red_circle_Visual_prompt_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.06712", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Equivariant Similarity for Vision-Language Foundation Models", + "base_url": null, + "title_page": null, + "github": "Wangt-CN/EqBen", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Equivariant_Similarity_for_Vision-Language_Foundation_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.14465", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Scaling Data Generation in Vision-and-Language Navigation", + "base_url": null, + "title_page": null, + "github": "wz0919/ScaleVLN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Scaling_Data_Generation_in_Vision-and-Language_Navigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.15644", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "QCGWSM_okfM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Name Your Colour for the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer", + "base_url": null, + "title_page": null, + "github": "ryeocthiv/CQFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Su_Name_Your_Colour_For_the_Task_Artificially_Discover_Colour_Naming_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.03434", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_G2L_Semantically_Aligned_and_Uniform_Video_Grounding_via_Geodesic_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14277", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Grounded Entity-Landmark Adaptive Pre-Training for Vision-and-Language Navigation", + "base_url": null, + "title_page": null, + "github": "CSir1996/VLN-GELA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cui_Grounded_Entity-Landmark_Adaptive_Pre-Training_for_Vision-and-Language_Navigation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12587", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Ibrahimi_Audio-Enhanced_Text-to-Video_Retrieval_using_Text-Conditioned_Feature_Alignment_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12964", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + }, + { + "title": "Open-Domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities", + "base_url": null, + "title_page": null, + "github": "edchengg/oven_eval", + "web_page": null, + "github_page": "https://open-vision-language.github.io/oven/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hu_Open-domain_Visual_Entity_Recognition_Towards_Recognizing_Millions_of_Wikipedia_Entities_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.11154", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Language" + } +] \ No newline at end of file diff --git a/json_data/2023/main/vision-and-robotics.json b/json_data/2023/main/vision-and-robotics.json new file mode 100644 index 0000000..4412b4e --- /dev/null +++ b/json_data/2023/main/vision-and-robotics.json @@ -0,0 +1,299 @@ +[ + { + "title": "Simoun: Synergizing Interactive Motion-Appearance Understanding for Vision-based Reinforcement Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Simoun_Synergizing_Interactive_Motion-appearance_Understanding_for_Vision-based_Reinforcement_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + }, + { + "title": "Among Us: Adversarially Robust Collaborative Perception by Consensus", + "base_url": null, + "title_page": null, + "github": "coperception/ROBOSAC", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Among_Us_Adversarially_Robust_Collaborative_Perception_by_Consensus_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.09495", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + }, + { + "title": "Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "saltoricristiano/LiDOG", + "web_page": null, + "github_page": "https://saltoricristiano.github.io/lidog/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Saltori_Walking_Your_LiDOG_A_Journey_Through_Multiple_Domains_for_LiDAR_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.11705", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + }, + { + "title": "Stabilizing Visual Reinforcement Learning via Asymmetric Interactive Cooperation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhai_Stabilizing_Visual_Reinforcement_Learning_via_Asymmetric_Interactive_Cooperation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + }, + { + "title": "MAAL: Multimodality-Aware Autoencoder-based Affordance Learning for 3D Articulated Objects", + "base_url": null, + "title_page": null, + "github": "akira-l/MAAL", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liang_MAAL_Multimodality-Aware_Autoencoder-Based_Affordance_Learning_for_3D_Articulated_Objects_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + }, + { + "title": "Rethinking Range View Representation for LiDAR Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Kong_Rethinking_Range_View_Representation_for_LiDAR_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05367", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + }, + { + "title": "PourIt!: Weakly-Supervised Liquid Perception from a Single Image for Visual Closed-Loop Robotic Pouring", + "base_url": null, + "title_page": null, + "github": "hetolin/PourIt", + "web_page": null, + "github_page": "https://hetolin.github.io/PourIt/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_PourIt_Weakly-Supervised_Liquid_Perception_from_a_Single_Image_for_Visual_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11299", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "R5SpiV0658Q", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + }, + { + "title": "CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Moreau_CROSSFIRE_Camera_Relocalization_On_Self-Supervised_Features_from_an_Implicit_Representation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.04869", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + }, + { + "title": "Environment Agnostic Representation for Visual Reinforcement Learning", + "base_url": null, + "title_page": null, + "github": "doihye/EAR", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Choi_Environment_Agnostic_Representation_for_Visual_Reinforcement_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + }, + { + "title": "Test-Time Personalizable Forecasting of 3D Human Poses", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://sites.google.com/view/hp-ttp", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cui_Test-time_Personalizable_Forecasting_of_3D_Human_Poses_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "bnqwjhPyvTM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + }, + { + "title": "HM-ViT: Hetero-Modal Vehicle-to-Vehicle Cooperative Perception with Vision Transformer", + "base_url": null, + "title_page": null, + "github": "XHwind/HM-ViT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xiang_HM-ViT_Hetero-Modal_Vehicle-to-Vehicle_Cooperative_Perception_with_Vision_Transformer_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.10628", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision and Robotics" + } +] \ No newline at end of file diff --git a/json_data/2023/main/vision-applications-and-systems.json b/json_data/2023/main/vision-applications-and-systems.json new file mode 100644 index 0000000..26d78c1 --- /dev/null +++ b/json_data/2023/main/vision-applications-and-systems.json @@ -0,0 +1,974 @@ +[ + { + "title": "Democratising 2D Sketch to 3D Shape Retrieval through Pivoting", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chowdhury_Democratising_2D_Sketch_to_3D_Shape_Retrieval_Through_Pivoting_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "iM1A81QEhfw", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Towards Instance-Adaptive Inference for Federated Learning", + "base_url": null, + "title_page": null, + "github": "chunmeifeng/FedIns", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_Towards_Instance-adaptive_Inference_for_Federated_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.06051", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_TransTIC_Transferring_Transformer-based_Image_Compression_from_Human_Perception_to_Machine_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.05085", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Counting Crowds in Bad Weather", + "base_url": null, + "title_page": null, + "github": "awccnet/AWCC-Net", + "web_page": null, + "github_page": "https://awccnet.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_Counting_Crowds_in_Bad_Weather_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2306.01209", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection", + "base_url": null, + "title_page": null, + "github": "facebookresearch/NeRF-Det", + "web_page": null, + "github_page": "https://chenfengxu714.github.io/nerfdet/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_NeRF-Det_Learning_Geometry-Aware_Volumetric_Representation_for_Multi-View_3D_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.14620", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "MEGA: Multimodal Alignment Aggregation and Distillation for Cinematic Video Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Sadoughi_MEGA_Multimodal_Alignment_Aggregation_and_Distillation_For_Cinematic_Video_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.11185", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Bring Clipart to Life", + "base_url": null, + "title_page": null, + "github": "dangsq/ClipFaceShop", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Bring_Clipart_to_Life_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "UpCycling: Semi-Supervised 3D Object Detection without Sharing Raw-Level Unlabeled Scenes", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Hwang_UpCycling_Semi-supervised_3D_Object_Detection_without_Sharing_Raw-level_Unlabeled_Scenes_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2211.11950", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Graph Matching with Bi-Level Noisy Correspondence", + "base_url": null, + "title_page": null, + "github": "XLearning-SCU/2023-ICCV-COMMON", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Graph_Matching_with_Bi-level_Noisy_Correspondence_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.04085", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Anomaly Detection using Score-based Perturbation Resilience", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Shin_Anomaly_Detection_using_Score-based_Perturbation_Resilience_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception", + "base_url": null, + "title_page": null, + "github": "starfdu1418/SCOPE", + "web_page": null, + "github_page": "https://ydk122024.github.io/SCOPE/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Spatio-Temporal_Domain_Awareness_for_Multi-Agent_Collaborative_Perception_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13929", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing", + "base_url": null, + "title_page": null, + "github": "aimagelab/multimodal-garment-designer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Baldrati_Multimodal_Garment_Designer_Human-Centric_Latent_Diffusion_Models_for_Fashion_Image_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.02051", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Towards Unifying Medical Vision-and-Language Pre-Training via Soft Prompts", + "base_url": null, + "title_page": null, + "github": "zhjohnchan/ptunifier", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Towards_Unifying_Medical_Vision-and-Language_Pre-Training_via_Soft_Prompts_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.08958", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "MAS: Towards Resource-Efficient Federated Multiple-Task Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhuang_MAS_Towards_Resource-Efficient_Federated_Multiple-Task_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.11285", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Hierarchical Visual Categories Modeling: A Joint Representation Learning and Density Estimation Framework for Out-of-Distribution Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_Hierarchical_Visual_Categories_Modeling_A_Joint_Representation_Learning_and_Density_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Improving Generalization in Visual Reinforcement Learning via Conflict-Aware Gradient Agreement Augmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_Improving_Generalization_in_Visual_Reinforcement_Learning_via_Conflict-aware_Gradient_Agreement_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.01194", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Tiny Updater: Towards Efficient Neural Network-Driven Software Updating", + "base_url": null, + "title_page": null, + "github": "ArchipLab-LinfengZhang/TinyUpdater", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Tiny_Updater_Towards_Efficient_Neural_Network-Driven_Software_Updating_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Multiple Planar Object Tracking", + "base_url": null, + "title_page": null, + "github": "nku-zhichengzhang/MPOT", + "web_page": "https://zzcheng.top/MPOT/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Multiple_Planar_Object_Tracking_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "1kE_VJgM4u8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "OmnimatteRF: Robust Omnimatte with 3D Background Modeling", + "base_url": null, + "title_page": null, + "github": "facebookresearch/OmnimatteRF", + "web_page": null, + "github_page": "https://omnimatte-rf.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_OmnimatteRF_Robust_Omnimatte_with_3D_Background_Modeling_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.07749", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Ordinal Label Distribution Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://downdric23.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wen_Ordinal_Label_Distribution_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Re-Mine, Learn and Reason: Exploring the Cross-Modal Semantic Correlations for Language-Guided HOI Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Re-mine_Learn_and_Reason_Exploring_the_Cross-modal_Semantic_Correlations_for_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.13529", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "MUVA: A New Large-Scale Benchmark for Multi-View Amodal Instance Segmentation in the Shopping Scenario", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://zhixuanli.github.io/project_2023_ICCV_MUVA/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Li_MUVA_A_New_Large-Scale_Benchmark_for_Multi-View_Amodal_Instance_Segmentation_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Editable Image Geometric Abstraction via Neural Primitive Assembly", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Editable_Image_Geometric_Abstraction_via_Neural_Primitive_Assembly_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "One-Shot Recognition of any Material Anywhere using Contrastive Learning with Physics-based Rendering", + "base_url": null, + "title_page": null, + "github": "ZuseZ4/MatSim-Dataset-Generator-Scripts-And-Neural-net", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Drehwald_One-Shot_Recognition_of_Any_Material_Anywhere_Using_Contrastive_Learning_with_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2212.00648", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "sXN3jmqv2SM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Fast Full-Frame Video Stabilization with Iterative Optimization", + "base_url": null, + "title_page": null, + "github": "zwyking/Fast-Stab", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_Fast_Full-frame_Video_Stabilization_with_Iterative_Optimization_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2307.12774", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers", + "base_url": null, + "title_page": null, + "github": "NevSNev/UniST", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Gu_Two_Birds_One_Stone_A_Unified_Framework_for_Joint_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.11335", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Multi-Modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion", + "base_url": null, + "title_page": null, + "github": "SunYM2020/MoE-Fusion", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Multi-Modal_Gated_Mixture_of_Local-to-Global_Experts_for_Dynamic_Image_Fusion_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.01392", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection", + "base_url": null, + "title_page": null, + "github": "SamWilso/SAFE_Official", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wilson_SAFE_Sensitivity-Aware_Features_for_Out-of-Distribution_Object_Detection_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2208.13930", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "GeT: Generative Target Structure Debiasing for Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "lulusindazc/Get", + "web_page": null, + "github_page": "https://lulusindazc.github.io/getproject/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_GeT_Generative_Target_Structure_Debiasing_for_Domain_Adaptation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10205", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending", + "base_url": null, + "title_page": null, + "github": "wty-ustc/HairCLIPv2", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_HairCLIPv2_Unifying_Hair_Editing_via_Proxy_Feature_Blending_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2310.10651", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation", + "base_url": null, + "title_page": null, + "github": "fuqichen1998/Deformer", + "web_page": null, + "github_page": "https://fuqichen1998.github.io/Deformer/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Fu_Deformer_Dynamic_Fusion_Transformer_for_Robust_Hand_Pose_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.04991", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Improving Continuous Sign Language Recognition with Cross-Lingual Signs", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wei_Improving_Continuous_Sign_Language_Recognition_with_Cross-Lingual_Signs_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.10809", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "A Parse-then-Place Approach for Generating Graphic Layouts from Textual Descriptions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_A_Parse-Then-Place_Approach_for_Generating_Graphic_Layouts_from_Textual_Descriptions_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2308.12700", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "DISeR: Designing Imaging Systems with Reinforcement Learning", + "base_url": null, + "title_page": null, + "github": "tzofi/diser", + "web_page": null, + "github_page": "https://tzofi.github.io/diser/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Klinghoffer_DISeR_Designing_Imaging_Systems_with_Reinforcement_Learning_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.13851", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Lm80OZh5eDg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Segmentation of Tubular Structures using Iterative Training with Tailored Samples", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Liao_Segmentation_of_Tubular_Structures_Using_Iterative_Training_with_Tailored_Samples_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2309.08727", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + }, + { + "title": "Time-to-Contact Map by Joint Estimation of Up-to-Scale Inverse Depth and Global Motion using a Single Event Camera", + "base_url": null, + "title_page": null, + "github": "neuromorphic-paris/ETTCM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Nunes_Time-to-Contact_Map_by_Joint_Estimation_of_Up-to-Scale_Inverse_Depth_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision Applications and Systems" + } +] \ No newline at end of file diff --git a/json_data/2023/main/vision-graphics-and-robotics.json b/json_data/2023/main/vision-graphics-and-robotics.json new file mode 100644 index 0000000..54520e0 --- /dev/null +++ b/json_data/2023/main/vision-graphics-and-robotics.json @@ -0,0 +1,218 @@ +[ + { + "title": "Adding Conditional Control to Text-to-Image Diffusion Models", + "base_url": null, + "title_page": null, + "github": "lllyasviel/ControlNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Adding_Conditional_Control_to_Text-to-Image_Diffusion_Models_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2302.05543", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision, Graphics, and Robotics" + }, + { + "title": "Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation", + "base_url": null, + "title_page": null, + "github": "lwwu2/fipt", + "web_page": null, + "github_page": "https://jerrypiglet.github.io/fipt-ucsd/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wu_Factorized_Inverse_Path_Tracing_for_Efficient_and_Accurate_Material-Lighting_Estimation_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.05669", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision, Graphics, and Robotics" + }, + { + "title": "Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations", + "base_url": null, + "title_page": null, + "github": "AGI-Labs/manipulate-by-seeing", + "web_page": null, + "github_page": "https://agi-labs.github.io/manipulate-by-seeing/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wang_Manipulate_by_Seeing_Creating_Manipulation_Controllers_from_Pre-Trained_Representations_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.08135", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision, Graphics, and Robotics" + }, + { + "title": "3D Implicit Transporter for Temporally Consistent Keypoint Discovery", + "base_url": null, + "title_page": null, + "github": "zhongcl-thu/3D-Implicit-Transporter", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Zhong_3D_Implicit_Transporter_for_Temporally_Consistent_Keypoint_Discovery_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": "https://www.researchgate.net/publication/373328882_3D_Implicit_Transporter_for_Temporally_Consistent_Keypoint_Discovery", + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision, Graphics, and Robotics" + }, + { + "title": "Chordal Averaging on Flag Manifolds and its Applications", + "base_url": null, + "title_page": null, + "github": "nmank/FlagAveraging", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Mankovich_Chordal_Averaging_on_Flag_Manifolds_and_Its_Applications_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.13501", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision, Graphics, and Robotics" + }, + { + "title": "UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-Aware Curriculum and Iterative Generalist-Specialist Learning", + "base_url": null, + "title_page": null, + "github": "PKU-EPIC/UniDexGrasp2", + "web_page": null, + "github_page": "https://pku-epic.github.io/UniDexGrasp++/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Wan_UniDexGrasp_Improving_Dexterous_Grasping_Policy_Learning_via_Geometry-Aware_Curriculum_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2304.00464", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision, Graphics, and Robotics" + }, + { + "title": "GameFormer: Game-Theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving", + "base_url": null, + "title_page": null, + "github": "MCZhi/GameFormer", + "web_page": null, + "github_page": "https://mczhi.github.io/GameFormer/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Huang_GameFormer_Game-theoretic_Modeling_and_Learning_of_Transformer-based_Interactive_Prediction_and_ICCV_2023_paper.pdf", + "paper_arxiv_id": "2303.05760", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision, Graphics, and Robotics" + }, + { + "title": "PPR: Physically Plausible Reconstruction from Monocular Videos", + "base_url": null, + "title_page": null, + "github": "gengshan-y/ppr", + "web_page": null, + "github_page": "https://gengshan-y.github.io/ppr/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_PPR_Physically_Plausible_Reconstruction_from_Monocular_Videos_ICCV_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": "https://gengshan-y.github.io/ppr/PPR.pdf", + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Vision, Graphics, and Robotics" + } +] \ No newline at end of file diff --git a/json_data/2023/workshops/visual-inductive-priors-for-data-efficient-dl-w.json b/json_data/2023/workshops/visual-inductive-priors-for-data-efficient-dl-w.json new file mode 100644 index 0000000..7b99061 --- /dev/null +++ b/json_data/2023/workshops/visual-inductive-priors-for-data-efficient-dl-w.json @@ -0,0 +1,461 @@ +[ + { + "title": "Using and Abusing Equivariance", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Edixhoven_Using_and_Abusing_Equivariance_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.11316", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "Video BagNet: Short Temporal Receptive Fields Increase Robustness in Long-Term Action Recognition", + "base_url": null, + "title_page": null, + "github": "ombretta/videobagnet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Strafforello_Video_BagNet_Short_Temporal_Receptive_Fields_Increase_Robustness_in_Long-Term_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.11249", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "COSE: A Consistency-Sensitivity Metric for Saliency on Image Classification", + "base_url": null, + "title_page": null, + "github": "cvl-umass/COSE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Daroya_COSE_A_Consistency-Sensitivity_Metric_for_Saliency_on_Image_Classification_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.10989", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning", + "base_url": null, + "title_page": null, + "github": "nis-research/dfmX-augmentation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Wang_DFM-X_Augmentation_by_Leveraging_Prior_Knowledge_of_Shortcut_Learning_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.06622", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "Good Fences Make Good Neighbours", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Estepa_Good_Fences_Make_Good_Neighbours_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "Data Efficient Single Image Dehazing via Adversarial Auto-Augmentation and Extended Atmospheric Scattering Model", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Shyam_Data_Efficient_Single_Image_Dehazing_via_Adversarial_Auto-Augmentation_and_Extended_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "Distilling Part-Whole Hierarchical Knowledge from a Huge Pretrained Class Agnostic Segmentation Framework", + "base_url": null, + "title_page": null, + "github": "AhmedMostafaSoliman/distill-part-whole", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Radwan_Distilling_Part-Whole_Hierarchical_Knowledge_from_a_Huge_Pretrained_Class_Agnostic_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "Padding Aware Neurons", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Garcia-Gasulla_Padding_Aware_Neurons_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.08048", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "Logarithm-Transform Aided Gaussian Sampling for Few-Shot Learning", + "base_url": null, + "title_page": null, + "github": "ganatra-v/gaussian-sampling-fsl", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Ganatra_Logarithm-Transform_Aided_Gaussian_Sampling_for_Few-Shot_Learning_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.16337", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "DeepVAT: A Self-Supervised Technique for Cluster Assessment in Image Datasets", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Mazumder_DeepVAT_A_Self-Supervised_Technique_for_Cluster_Assessment_in_Image_Datasets_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2306.00011", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasets", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Brigato_No_Data_Augmentation_Alternative_Regularizations_for_Effective_Training_on_Small_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.01694", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "RV-VAE: Integrating Random Variable Algebra into Variational Autoencoders", + "base_url": null, + "title_page": null, + "github": "VassilisCN/RV-VAE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Nicodemou_RV-VAE_Integrating_Random_Variable_Algebra_into_Variational_Autoencoders_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "PARTICLE: Part Discovery and Contrastive Learning for Fine-Grained Recognition", + "base_url": null, + "title_page": null, + "github": "cvl-umass/PARTICLE", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Saha_PARTICLE_Part_Discovery_and_Contrastive_Learning_for_Fine-Grained_Recognition_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.13822", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "Self-Supervised Learning of Contextualized Local Visual Embeddings", + "base_url": null, + "title_page": null, + "github": "sthalles/CLoVE", + "web_page": null, + "github_page": "https://sthalles.github.io/CLoVE/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Silva_Self-Supervised_Learning_of_Contextualized_Local_Visual_Embeddings_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2310.00527", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "InterAug: A Tuning-Free Augmentation Policy for Data-Efficient and Robust Object Detection", + "base_url": null, + "title_page": null, + "github": "kowshikthopalli/InterAug", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Thopalli_InterAug_A_Tuning-Free_Augmentation_Policy_for_Data-Efficient_and_Robust_Object_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "Geometric Superpixel Representations for Efficient Image Classification with Graph Neural Networks", + "base_url": null, + "title_page": null, + "github": "lukasknobel/ShapeGNN", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Cosma_Geometric_Superpixel_Representations_for_Efficient_Image_Classification_with_Graph_Neural_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + }, + { + "title": "Geometric Contrastive Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/VIPriors/papers/Koishekenov_Geometric_Contrastive_Learning_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop" + } +] \ No newline at end of file diff --git a/json_data/2023/workshops/w-and-challenge-on-deepfake-analysis-and-detection.json b/json_data/2023/workshops/w-and-challenge-on-deepfake-analysis-and-detection.json new file mode 100644 index 0000000..199a7b8 --- /dev/null +++ b/json_data/2023/workshops/w-and-challenge-on-deepfake-analysis-and-detection.json @@ -0,0 +1,326 @@ +[ + { + "title": "Detecting Images Generated by Deep Diffusion Models using Their Local Intrinsic Dimensionality", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Lorenz_Detecting_Images_Generated_by_Deep_Diffusion_Models_Using_Their_Local_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "Attending Generalizability in Course of Deep Fake Detection by Exploring Multi-Task Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Balaji_Attending_Generalizability_in_Course_of_Deep_Fake_Detection_by_Exploring_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.13503", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localization", + "base_url": null, + "title_page": null, + "github": "vimal-isi-edu/TrainFors", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Nandi_TrainFors_A_Large_Benchmark_Training_Dataset_for_Image_Manipulation_Detection_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.05264", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "FIVA: Facial Image and Video Anonymization and Anonymization Defense", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Rosberg_FIVA_Facial_Image_and_Video_Anonymization_and_Anonymization_Defense_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.04228", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "Interpretable-through-Prototypes Deepfake Detection for Diffusion Models", + "base_url": null, + "title_page": null, + "github": "lira-centre/DeepfakeDetection", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Aghasanli_Interpretable-Through-Prototypes_Deepfake_Detection_for_Diffusion_Models_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "Learning Interpretable Forensic Representations via Local Window Modulation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Das_Learning_Interpretable_Forensic_Representations_via_Local_Window_Modulation_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "Revisiting Generalizability in Deepfake Detection: Improving Metrics and Stabilizing Transfer", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Kamat_Revisiting_Generalizability_in_Deepfake_Detection_Improving_Metrics_and_Stabilizing_Transfer_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "WaterLo: Protect Images from Deepfakes using Localized Semi-Fragile Watermark", + "base_url": null, + "title_page": null, + "github": "beuve/waterlo", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Beuve_WaterLo_Protect_Images_from_Deepfakes_Using_Localized_Semi-Fragile_Watermark_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "Online Detection of AI-Generated Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Epstein_Online_Detection_of_AI-Generated_Images__ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2310.15150", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "A Comprehensive Framework for Evaluating Deepfake Generators: Dataset, Metrics Performance, and Comparative Analysis", + "base_url": null, + "title_page": null, + "github": "SaharHusseini/deepfake_evaluation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Husseini_A_Comprehensive_Framework_for_Evaluating_Deepfake_Generators_Dataset_Metrics_Performance_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "Undercover Deepfakes: Detecting Fake Segments in Videos", + "base_url": null, + "title_page": null, + "github": "rgb91/temporal-deepfake-segmentation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Saha_Undercover_Deepfakes_Detecting_Fake_Segments_in_Videos_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2305.06564", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + }, + { + "title": "Deepfakes Signatures Detection in the Handcrafted Features Space", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Hamadene_Deepfakes_Signatures_Detection_in_the_Handcrafted_Features_Space_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop and Challenge on DeepFake Analysis and Detection" + } +] \ No newline at end of file diff --git a/json_data/2023/workshops/w-on-cv-in-plant-phenotyping-and-agriculture.json b/json_data/2023/workshops/w-on-cv-in-plant-phenotyping-and-agriculture.json new file mode 100644 index 0000000..31090e3 --- /dev/null +++ b/json_data/2023/workshops/w-on-cv-in-plant-phenotyping-and-agriculture.json @@ -0,0 +1,677 @@ +[ + { + "title": "Analyzing the Behavior of Cauliflower Harvest-Readiness Models by Investigating Feature Relevances", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Penzel_Analyzing_the_Behavior_of_Cauliflower_Harvest-Readiness_Models_by_Investigating_Feature_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Towards Automated Regulation of Jacobaea Vulgaris in Grassland using Deep Neural Networks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Schauer_Towards_Automated_Regulation_of_Jacobaea_Vulgaris_in_Grassland_Using_Deep_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Estimation of Crop Production by Fusing Images and Crop Features", + "base_url": null, + "title_page": null, + "github": "joheras/yield-prediction", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Casado-Garcia_Estimation_of_Crop_Production_by_Fusing_Images_and_Crop_Features_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "An Interpretable Framework to Characterize Compound Treatments on Filamentous Fungi using Cell Painting and Deep Metric Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Lejeune_An_Interpretable_Framework_to_Characterize_Compound_Treatments_on_Filamentous_Fungi_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Rapid Tomato DUS Trait Analysis using an Optimized Mobile-based Coarse-to-Fine Instance Segmentation Algorithm", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Rustia_Rapid_Tomato_DUS_Trait_Analysis_Using_an_Optimized_Mobile-Based_Coarse-to-Fine_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Non-Destructive Infield Quality Estimation of Strawberries using Deep Architectures", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Jol_Non-Destructive_Infield_Quality_Estimation_of_Strawberries_Using_Deep_Architectures_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Reinforcement Learning with Space Carving for Plant Scanning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Villalpando_Reinforcement_Learning_with_Space_Carving_for_Plant_Scanning_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Deep Learning based 3d Reconstruction for Phenotyping of Wheat Seeds: A Dataset, Challenge, and Baseline Method", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Cherepashkin_Deep_Learning_Based_3d_Reconstruction_for_Phenotyping_of_Wheat_Seeds_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Semantic Segmentation of Crops and Weeds with Probabilistic Modeling and Uncertainty Quantification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Celikkan_Semantic_Segmentation_of_Crops_andWeeds_with_Probabilistic_Modeling_and_Uncertainty_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "A New Large Dataset and a Transfer Learning Methodology for Plant Phenotyping in Vertical Farms", + "base_url": null, + "title_page": null, + "github": "deepplants/AGM_plant_phenotyping", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": "https://huggingface.co/datasets/deep-plants/AGM_HS", + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Sama_A_new_Large_Dataset_and_a_Transfer_Learning_Methodology_for_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Pollinators as Data Collectors: Estimating Floral Diversity with Bees and Computer Vision", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Tausch_Pollinators_as_Data_Collectors_Estimating_Floral_Diversity_with_Bees_and_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Inductive Conformal Prediction for Harvest-Readiness Classification of Cauliflower Plants: A Comparative Study of Uncertainty Quantification Methods", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Farag_Inductive_Conformal_Prediction_for_Harvest-Readiness_Classification_of_Cauliflower_Plants_A_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Group-Conditional Conformal Prediction via Quantile Regression Calibration for Crop and Weed Classification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Melki_Group-Conditional_Conformal_Prediction_via_Quantile_Regression_Calibration_for_Crop_and_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.15094", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Vision-based Monitoring of the Short-Term Dynamic Behaviour of Plants for Automated Phenotyping", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Wagner_Vision-Based_Monitoring_of_the_Short-Term_Dynamic_Behaviour_of_Plants_for_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Improving Deep Learning on Hyperspectral Images of Grain by Incorporating Domain Knowledge from Chemometrics", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Engstrom_Improving_Deep_Learning_on_Hyperspectral_Images_of_Grain_by_Incorporating_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Adapting Vision Foundation Models for Plant Phenotyping", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Chen_Adapting_Vision_Foundation_Models_for_Plant_Phenotyping_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Embedded Plant Recognition: A Benchmark for Low Footprint Deep Neural Networks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Amine_Embedded_Plant_Recognition_A_Benchmark_for_low_Footprint_Deep_Neural_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Deep Learning for Apple Fruit Quality Inspection using X-Ray Imaging", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Tempelaere_Deep_Learning_for_Apple_Fruit_Quality_Inspection_Using_X-Ray_Imaging_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Detection of Fusarium Damaged Kernels in Wheat using Deep Semi-Supervised Learning on a Novel WheatSeedBelt Dataset", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Najafian_Detection_of_Fusarium_Damaged_Kernels_in_Wheat_Using_Deep_Semi-Supervised_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Unified Automatic Plant Cover and Phenology Prediction", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Korschens_Unified_Automatic_Plant_Cover_and_Phenology_Prediction_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Weed Mapping with Convolutional Neural Networks on High Resolution Whole-Field Images", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Wang_Weed_Mapping_with_Convolutional_Neural_Networks_on_High_Resolution_Whole-Field_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Unlocking Comparative Plant Scoring with Siamese Neural Networks and Pairwise Pseudo Labelling", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Hartley_Unlocking_Comparative_Plant_Scoring_with_Siamese_Neural_Networks_and_Pairwise_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Class-Incremental Learning of Plant and Disease Detection: Growing Branches with Knowledge Distillation", + "base_url": null, + "title_page": null, + "github": "DynYKD/Continual-Plant-Detection", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Page-Fortin_Class-Incremental_Learning_of_Plant_and_Disease_Detection_Growing_Branches_with_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2304.06619", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Efficient Grapevine Structure Estimation in Vineyards Conditions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Gentilhomme_Efficient_Grapevine_Structure_Estimation_in_Vineyards_Conditions_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + }, + { + "title": "Plant Root Occlusion Inpainting with Generative Adversarial Network", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Song_Plant_Root_Occlusion_Inpainting_with_Generative_Adversarial_Network_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "8th Workshop on Computer Vision in Plant Phenotyping and Agriculture" + } +] \ No newline at end of file diff --git a/json_data/2023/workshops/w-on-new-ideas-in-vision-transformers.json b/json_data/2023/workshops/w-on-new-ideas-in-vision-transformers.json new file mode 100644 index 0000000..1223072 --- /dev/null +++ b/json_data/2023/workshops/w-on-new-ideas-in-vision-transformers.json @@ -0,0 +1,488 @@ +[ + { + "title": "Explaining Through Transformer Input Sampling", + "base_url": null, + "title_page": null, + "github": "aenglebert/Transformer_Input_Sampling", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Englebert_Explaining_Through_Transformer_Input_Sampling_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "Actor-Agnostic Multi-Label Action Recognition with Multi-Modal Query", + "base_url": null, + "title_page": null, + "github": "mondalanindya/MSQNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Mondal_Actor-Agnostic_Multi-Label_Action_Recognition_with_Multi-Modal_Query_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2307.10763", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "bafoEVdQYJg", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "All-Pairs Consistency Learning forWeakly Supervised Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Sun_All-pairs_Consistency_Learning_forWeakly_Supervised_Semantic_Segmentation_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "Dual-Contrastive Dual-Consistency Dual-Transformer: A Semi-Supervised Approach to Medical Image Segmentation", + "base_url": null, + "title_page": null, + "github": "ziyangwang007/CV-SSL-MIS", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Wang_Dual-Contrastive_Dual-Consistency_Dual-Transformer_A_Semi-Supervised_Approach_to_Medical_Image_Segmentation_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "JU9koBE83co", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "A Hybrid Visual Transformer for Efficient Deep Human Activity Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Djenouri_A_Hybrid_Visual_Transformer_for_Efficient_Deep_Human_Activity_Recognition_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "Which Tokens to Use? Investigating Token Reduction in Vision Transformers", + "base_url": null, + "title_page": null, + "github": "JoakimHaurum/TokenReduction", + "web_page": "https://vap.aau.dk/tokens/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Haurum_Which_Tokens_to_Use_Investigating_Token_Reduction_in_Vision_Transformers_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.04657", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "Hierarchical Spatiotemporal Transformers for Video Object Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Yoo_Hierarchical_Spatiotemporal_Transformers_for_Video_Object_Segmentation_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2307.08263", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "JV9TyazM38Y", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "IDTransformer: Transformer for Intrinsic Image Decomposition", + "base_url": null, + "title_page": null, + "github": "ParthaDasWeb/IDTransformer.web", + "web_page": null, + "github_page": "https://morpheus3000.github.io/IDTransformer.web/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Das_IDTransformer_Transformer_for_Intrinsic_Image_Decomposition_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers", + "base_url": null, + "title_page": null, + "github": "Qualcomm-AI-research/batchshaping", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Havtorn_MSViT_Dynamic_Mixed-Scale_Tokenization_for_Vision_Transformers_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2307.02321", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "1H7LJ7-v58w", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "Template-Guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction", + "base_url": null, + "title_page": null, + "github": "FelixHertlein/illtrtemplate-model", + "web_page": null, + "github_page": "https://felixhertlein.github.io/illtrtemplate/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Hertlein_Template-Guided_Illumination_Correction_for_Document_Images_with_Imperfect_Geometric_Reconstruction_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "CWrMHbvScSM", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "Spatio-Temporal Convolution-Attention Video Network", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Diba_Spatio-Temporal_Convolution-Attention_Video_Network_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "TSOSVNet: Teacher-Student Collaborative Knowledge Distillation for Online Signature Verification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Sekhar_TSOSVNet_Teacher-Student_Collaborative_Knowledge_Distillation_for_Online_Signature_Verification_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "y0akK9vZ4xE", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "SeMask: Semantically Masked Transformers for Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "Picsart-AI-Research/SeMask-Segmentation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Jain_SeMask_Semantically_Masked_Transformers_for_Semantic_Segmentation_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2112.12782", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "eLg2rmFWiGs", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "TransInpaint: Transformer-based Image Inpainting with Context Adaptation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Shamsolmoali_TransInpaint_Transformer-Based_Image_Inpainting_with_Context_Adaptation_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "ynEg6y4si_8", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "Interactive Image Segmentation with Cross-Modality Vision Transformers", + "base_url": null, + "title_page": null, + "github": "lik1996/iCMFormer", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Li_Interactive_Image_Segmentation_with_Cross-Modality_Vision_Transformers_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2307.02280", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "MOSAIC: Multi-Object Segmented Arbitrary Stylization using CLIP", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Ganugula_MOSAIC_Multi-Object_Segmented_Arbitrary_Stylization_Using_CLIP_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.13716", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "On Moving Object Segmentation from Monocular Video with Transformers", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Homeyer_On_Moving_Object_Segmentation_from_Monocular_Video_with_Transformers_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "5kuGvSJmitQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + }, + { + "title": "SCSC: Spatial Cross-Scale Convolution Module to Strengthen Both CNNs and Transformers", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/NIVT/papers/Wang_SCSC_Spatial_Cross-Scale_Convolution_Module_to_Strengthen_Both_CNNs_and_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.07110", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "LE6ncJVvJMQ", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Workshop on New Ideas in Vision Transformers" + } +] \ No newline at end of file diff --git a/json_data/2023/workshops/w-representation-learning-with-very-limited-images.json b/json_data/2023/workshops/w-representation-learning-with-very-limited-images.json new file mode 100644 index 0000000..fe14b65 --- /dev/null +++ b/json_data/2023/workshops/w-representation-learning-with-very-limited-images.json @@ -0,0 +1,542 @@ +[ + { + "title": "Image Guided Inpainting with Parameter Efficient Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Lim_Image_Guided_Inpainting_with_Parameter_Efficient_Learning_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Augmenting Features via Contrastive Learning-based Generative Model for Long-Tailed Classification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Park_Augmenting_Features_via_Contrastive_Learning-Based_Generative_Model_for_Long-Tailed_Classification_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "G2L: A High-Dimensional Geometric Approach for Automatic Generation of Highly Accurate Pseudo-Labels", + "base_url": null, + "title_page": null, + "github": "Hmic1102/Auto-generated-pseudo-label", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Kender_G2L_A_High-Dimensional_Geometric_Approach_for_Automatic_Generation_of_Highly_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Self-Supervised Hypergraphs for Learning Multiple World Interpretations", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Marcu_Self-Supervised_Hypergraphs_for_Learning_Multiple_World_Interpretations_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.07615", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Deep Generative Networks for Heterogeneous Augmentation of Cranial Defects", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Kwarciak_Deep_Generative_Networks_for_Heterogeneous_Augmentation_of_Cranial_Defects_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.04883", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "360° from a Single Camera: A Few-Shot Approach for LiDAR Segmentation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Reichardt_360deg_from_a_Single_Camera_A_Few-Shot_Approach_for_LiDAR_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Adaptive Self-Training for Object Detection", + "base_url": null, + "title_page": null, + "github": "rvandeghen/ASTOD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Vandeghen_Adaptive_Self-Training_for_Object_Detection_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2212.05911", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "FedLID: Self-Supervised Federated Learning for Leveraging Limited Image Data", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Psaltis_FedLID_Self-Supervised_Federated_Learning_for_Leveraging_Limited_Image_Data_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "A Horse with no Labels: Self-Supervised Horse Pose Estimation from Unlabelled Images and Synthetic Prior", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Sosa_A_Horse_with_no_Labels_Self-Supervised_Horse_Pose_Estimation_from_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.03411", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Boosting Semi-Supervised Learning by Bridging High and Low-Confidence Predictions", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Nguyen_Boosting_Semi-Supervised_Learning_by_Bridging_high_and_low-Confidence_Predictions_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.07509", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation", + "base_url": null, + "title_page": null, + "github": "Yussef93/SelectNAdaptICCVW", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Dawoud_SelectNAdapt_Support_Set_Selection_for_Few-Shot_Domain_Adaptation_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.04946", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://miad-2022.github.io/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Bao_MIAD_A_Maintenance_Inspection_Dataset_for_Unsupervised_Anomaly_Detection_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2211.13968", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Enhancing Classification Accuracy on Limited Data via Unconditional GAN", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Hong_Enhancing_Classification_Accuracy_on_Limited_Data_via_Unconditional_GAN_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Self-Training and Multi-Task Learning for Limited Data: Evaluation Study on Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": "https://lhoangan.github.io/multas/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Le_Self-Training_and_Multi-Task_Learning_for_Limited_Data_Evaluation_Study_on_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.06288", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "73we1N0azNk", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Bicsi_JEDI_Joint_Expert_Distillation_in_a_Semi-Supervised_Multi-Dataset_Student-Teacher_Scenario_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.04934", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Semantic RGB-D Image Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Li_Semantic_RGB-D_Image_Synthesis_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.11356", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Learning Universal Semantic Correspondences with No Supervision and Automatic Data Curation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Shtedritski_Learning_Universal_Semantic_Correspondences_with_No_Supervision_and_Automatic_Data_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Guiding Video Prediction with Explicit Procedural Knowledge", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Takenaka_Guiding_Video_Prediction_with_Explicit_Procedural_Knowledge_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Frequency-Aware Self-Supervised Long-Tailed Learning", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Lin_Frequency-Aware_Self-Supervised_Long-Tailed_Learning_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.04723", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + }, + { + "title": "Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/LIMIT/papers/Sharma_Tensor_Factorization_for_Leveraging_Cross-Modal_Knowledge_in_Data-Constrained_Infrared_Object_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.16592", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Representation Learning with very Limited Images: The Potential of Self-, Synthetic- and Formula-Supervision" + } +] \ No newline at end of file diff --git a/json_data/2023/workshops/w-scene-graphs-and-graph-representation-learning.json b/json_data/2023/workshops/w-scene-graphs-and-graph-representation-learning.json new file mode 100644 index 0000000..1ed3051 --- /dev/null +++ b/json_data/2023/workshops/w-scene-graphs-and-graph-representation-learning.json @@ -0,0 +1,272 @@ +[ + { + "title": "DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering", + "base_url": null, + "title_page": null, + "github": "SAMPL-Weizmann/DeepCut", + "web_page": null, + "github_page": "https://sampl-weizmann.github.io/DeepCut/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/SG2RL/papers/Aflalo_DeepCut_Unsupervised_Segmentation_Using_Graph_Neural_Networks_Clustering_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2212.05853", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "1st Workshop on Scene Graphs and Graph Representation Learning" + }, + { + "title": "Relational Prior Knowledge Graphs for Detection and Instance Segmentation", + "base_url": null, + "title_page": null, + "github": "ozzyou/RP-FEM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/SG2RL/papers/Ulger_Relational_Prior_Knowledge_Graphs_for_Detection_and_Instance_Segmentation_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2310.07573", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "1st Workshop on Scene Graphs and Graph Representation Learning" + }, + { + "title": "Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation", + "base_url": null, + "title_page": null, + "github": "Maelic/VG_curated", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/SG2RL/papers/Neau_Fine-Grained_is_Too_Coarse_A_Novel_Data-Centric_Approach_for_Efficient_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2305.18668", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "1st Workshop on Scene Graphs and Graph Representation Learning" + }, + { + "title": "Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes", + "base_url": null, + "title_page": null, + "github": "DavidGillsjo/polygon-HGT", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/SG2RL/papers/Gillsjo_Polygon_Detection_for_Room_Layout_Estimation_using_Heterogeneous_Graphs_andWireframes_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2306.12203", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "1st Workshop on Scene Graphs and Graph Representation Learning" + }, + { + "title": "SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/SG2RL/papers/Farshad_SceneGenie_Scene_Graph_Guided_Diffusion_Models_for_Image_Synthesis_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2304.14573", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "1st Workshop on Scene Graphs and Graph Representation Learning" + }, + { + "title": "Knowledge Informed Sequential Scene Graph Verification using VQA", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/SG2RL/papers/Thauvin_Knowledge_Informed_Sequential_Scene_Graph_Verification_Using_VQA_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "1st Workshop on Scene Graphs and Graph Representation Learning" + }, + { + "title": "Dynamic Scene Graph Representation for Surgical Video", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/SG2RL/papers/Holm_Dynamic_Scene_Graph_Representation_for_Surgical_Video_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.14538", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "1st Workshop on Scene Graphs and Graph Representation Learning" + }, + { + "title": "Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classes", + "base_url": null, + "title_page": null, + "github": "lorjul/haystack", + "web_page": null, + "github_page": "https://lorjul.github.io/haystack/", + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/SG2RL/papers/Lorenz_Haystack_A_Panoptic_Scene_Graph_Dataset_to_Evaluate_Rare_Predicate_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.02286", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "1st Workshop on Scene Graphs and Graph Representation Learning" + }, + { + "title": "nuScenes Knowledge Graph - A Comprehensive Semantic Representation of Traffic Scenes for Trajectory Prediction", + "base_url": null, + "title_page": null, + "github": "boschresearch/nuScenes_Knowledge_Graph", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/SG2RL/papers/Mlodzian_nuScenes_Knowledge_Graph_-_A_Comprehensive_Semantic_Representation_of_Traffic_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2312.09676", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "1st Workshop on Scene Graphs and Graph Representation Learning" + }, + { + "title": "Exploring the Road Graph in Trajectory Forecasting for Autonomous Driving", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/SG2RL/papers/Sun_Exploring_the_Road_Graph_in_Trajectory_Forecasting_for_Autonomous_Driving_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "1st Workshop on Scene Graphs and Graph Representation Learning" + } +] \ No newline at end of file diff --git a/json_data/2023/workshops/w-to-nerf-or-not-to-nerf.json b/json_data/2023/workshops/w-to-nerf-or-not-to-nerf.json new file mode 100644 index 0000000..cf3ecc6 --- /dev/null +++ b/json_data/2023/workshops/w-to-nerf-or-not-to-nerf.json @@ -0,0 +1,56 @@ +[ + { + "title": "ILSH: The Imperial Light-Stage Head Dataset for Human Head View Synthesis", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/RHWC/papers/Zheng_ILSH_The_Imperial_Light-Stage_Head_Dataset_for_Human_Head_View_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2310.03952", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "To NeRF or not to NeRF: A View Synthesis Challenge for Human Heads" + }, + { + "title": "VSCHH 2023: A Benchmark for the View Synthesis Challenge of Human Heads", + "base_url": null, + "title_page": null, + "github": null, + "web_page": "https://sites.google.com/view/vschh/", + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/RHWC/papers/Jang_VSCHH_2023_A_Benchmark_for_the_View_Synthesis_Challenge_of_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "To NeRF or not to NeRF: A View Synthesis Challenge for Human Heads" + } +] \ No newline at end of file diff --git a/json_data/2023/workshops/w-uncertainty-estimation-for-cv.json b/json_data/2023/workshops/w-uncertainty-estimation-for-cv.json new file mode 100644 index 0000000..e68f50b --- /dev/null +++ b/json_data/2023/workshops/w-uncertainty-estimation-for-cv.json @@ -0,0 +1,380 @@ +[ + { + "title": "A Simple and Explainable Method for Uncertainty Estimation using Attribute Prototype Networks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Zelenka_A_Simple_and_Explainable_Method_for_Uncertainty_Estimation_Using_Attribute_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "A Unified Approach to Learning with Label Noise and Unsupervised Confidence Approximation", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Rabbani_Unsupervised_Confidence_Approximation_Trustworthy_Learning_from_Noisy_Labelled_Data_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Adversarial Attacks Against Uncertainty Quantification", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Ledda_Adversarial_Attacks_Against_Uncertainty_Quantification_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2309.10586", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Biased Class Disagreement: Detection of Out of Distribution Instances by using Differently Biased Semantic Segmentation Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Alcover-Couso_Biased_Class_disagreement_detection_of_out_of_distribution_instances_by_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Calibrated Out-of-Distribution Detection with a Generic Representation", + "base_url": null, + "title_page": null, + "github": "vojirt/GROOD", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Vojir_Calibrated_Out-of-Distribution_Detection_with_a_Generic_Representation_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2303.13148", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Ali_DELO_Deep_Evidential_LiDAR_Odometry_Using_Partial_Optimal_Transport_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.07153", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Distance Matters for Improving Performance Estimation Under Covariate Shift", + "base_url": null, + "title_page": null, + "github": "melanibe/distance_matters_performance_estimation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Roschewitz_Distance_Matters_For_Improving_Performance_Estimation_Under_Covariate_Shift_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.07223", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Dual-Level Interaction for Domain Adaptive Semantic Segmentation", + "base_url": null, + "title_page": null, + "github": "RainJamesY/DIDA", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Yao_Dual-Level_Interaction_for_Domain_Adaptive_Semantic_Segmentation_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2307.07972", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Exploring Inlier and Outlier Specification for Improved Medical OOD Detection", + "base_url": null, + "title_page": null, + "github": "LLNL/OODmedic", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Narayanaswamy_Exploring_Inlier_and_Outlier_Specification_for_Improved_Medical_OOD_Detection_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Far Away in the Deep Space: Dense Nearest-Neighbor-based Out-of-Distribution Detection", + "base_url": null, + "title_page": null, + "github": "silviogalesso/dense-ood-knns", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Galesso_Far_Away_in_the_Deep_Space_Dense_Nearest-Neighbor-Based_Out-of-Distribution_Detection_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2211.06660", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Gaussian Latent Representations for Uncertainty Estimation using Mahalanobis Distance in Deep Classifiers", + "base_url": null, + "title_page": null, + "github": "vaishwarya96/MAPLE-uncertainty-estimation", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Venkataramanan_Gaussian_Latent_Representations_for_Uncertainty_Estimation_Using_Mahalanobis_Distance_in_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2305.13849", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Identifying Out-of-Domain Objects with Dirichlet Deep Neural Networks", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Hammam_Identifying_Out-of-Domain_Objects_with_Dirichlet_Deep_Neural_Networks_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Probabilistic MIMO U-Net: Efficient and Accurate Uncertainty Estimation for Pixel-Wise Regression", + "base_url": null, + "title_page": null, + "github": "antonbaumann/MIMO-Unet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Baumann_Probabilistic_MIMO_U-Net_Efficient_and_Accurate_Uncertainty_Estimation_for_Pixel-Wise_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.07477", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + }, + { + "title": "Uncle-SLAM: Uncertainty Learning for Dense Neural SLAM", + "base_url": null, + "title_page": null, + "github": "kev-in-ta/UncLe-SLAM", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/UnCV/papers/Sandstrom_UncLe-SLAM_Uncertainty_Learning_for_Dense_Neural_SLAM_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2306.11048", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "Uncertainty Estimation for Computer Vision" + } +] \ No newline at end of file diff --git a/json_data/2023/workshops/w-what-is-next-in-multimodal-foundation-models.json b/json_data/2023/workshops/w-what-is-next-in-multimodal-foundation-models.json new file mode 100644 index 0000000..90b69dd --- /dev/null +++ b/json_data/2023/workshops/w-what-is-next-in-multimodal-foundation-models.json @@ -0,0 +1,245 @@ +[ + { + "title": "Coarse to Fine Frame Selection for Online Open-Ended Video Question Answering", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/MMFM/papers/Nuthalapati_Coarse_to_Fine_Frame_Selection_for_Online_Open-Ended_Video_Question_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": "Qw81xaGh-O0", + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "What is Next in Multimodal Foundation Models?" + }, + { + "title": "Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/MMFM/papers/Pan_Retrieving-to-Answer_Zero-Shot_Video_Question_Answering_with_Frozen_Large_Language_Models_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2306.11732", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "What is Next in Multimodal Foundation Models?" + }, + { + "title": "Video-and-Language (VidL) Models and their Cognitive Relevance", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/MMFM/papers/Zonneveld_Video-and-Language_VidL_models_and_their_cognitive_relevance_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "What is Next in Multimodal Foundation Models?" + }, + { + "title": "Video Attribute Prototype Network: A New Perspective for Zero-Shot Video Classification", + "base_url": null, + "title_page": null, + "github": "bobo199830/VAPNet", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/MMFM/papers/Wang_Video_Attribute_Prototype_Network_A_New_Perspective_for_Zero-Shot_Video_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "What is Next in Multimodal Foundation Models?" + }, + { + "title": "Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection", + "base_url": null, + "title_page": null, + "github": "webber2933/iCLIP", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/MMFM/papers/Huang_Interaction-Aware_Prompting_for_Zero-Shot_Spatio-Temporal_Action_Detection_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2304.04688", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "What is Next in Multimodal Foundation Models?" + }, + { + "title": "ClipCrop: Conditioned Cropping Driven by Vision-Language Model", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/MMFM/papers/Zhong_ClipCrop_Conditioned_Cropping_Driven_by_Vision-Language_Model_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2211.11492", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "What is Next in Multimodal Foundation Models?" + }, + { + "title": "Towards an Exhaustive Evaluation of Vision-Language Foundation Models", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/MMFM/papers/Salin_Towards_an_Exhaustive_Evaluation_of_Vision-Language_Foundation_Models_ICCVW_2023_paper.pdf", + "paper_arxiv_id": null, + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "What is Next in Multimodal Foundation Models?" + }, + { + "title": "Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts", + "base_url": null, + "title_page": null, + "github": "mayug/VDT-Adapter", + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/MMFM/papers/Maniparambil_Enhancing_CLIP_with_GPT-4_Harnessing_Visual_Descriptions_as_Prompts_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2307.11661", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "What is Next in Multimodal Foundation Models?" + }, + { + "title": "Painter: Teaching Auto-Regressive Language Models to Draw Sketches", + "base_url": null, + "title_page": null, + "github": null, + "web_page": null, + "github_page": null, + "colab": null, + "modelscope": null, + "gitee": null, + "gitlab": null, + "zenodo": null, + "kaggle": null, + "demo_page": null, + "paper_thecvf": "https://openaccess.thecvf.com/content/ICCV2023W/MMFM/papers/Pourreza_Painter_Teaching_Auto-Regressive_Language_Models_to_Draw_Sketches_ICCVW_2023_paper.pdf", + "paper_arxiv_id": "2308.08520", + "paper_pdf": null, + "paper_hal_science": null, + "paper_researchgate": null, + "paper_amazon": null, + "youtube_id": null, + "drive_google": null, + "dropbox": null, + "onedrive": null, + "loom": null, + "section": "What is Next in Multimodal Foundation Models?" + } +] \ No newline at end of file