{"url":"/task/video-visual-relation-detection","name":"Video Visual Relation Detection","slug":"video-visual-relation-detection","description_markdown":"**Video Visual Relation Detection (VidVRD)** aims to detect instances of visual relations of interest in a video, where a visual relation instance is represented by a relation triplet with the trajectories of the subject and object. As compared to still images, videos provide a more natural set of features for detecting visual relations, such as the dynamic relations like “A-follow-B” and “A-towards-B”, and temporally changing relations like “A-chase-B” followed by “A-hold-B”. Yet, VidVRD is technically more challenging than ImgVRD due to the difficulties in accurate object tracking and diverse relation appearances in the video domain.\r\n\r\nSource: [ImageNet-VidVRD Video Visual Relation Dataset](https://xdshang.github.io/docs/imagenet-vidvrd.html)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":15,"papers_with_code":9,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-visual-relation-detection-on-imagenet","slug":"video-visual-relation-detection-on-imagenet","dataset":"ImageNet-VidVRD","dataset_url":"/dataset/imagenet-vidvrd","rows_in_archive":2,"metrics":["Recall@100","Recall@50","mAP"],"first_row_in_archive_order":{"model":"Social Fabric","paper_title":"Social Fabric: Tubelet Compositions for Video Relation Detection","paper_url":"/paper/social-fabric-tubelet-compositions-for-video","paper_date":"2021-08-18","arxiv_id":"2108.08363","code_links":[{"title":"shanshuo/social-fabric","url":"https://github.com/shanshuo/social-fabric"}],"syntology":null}},{"leaderboard":"/sota/video-visual-relation-detection-on-vidor","slug":"video-visual-relation-detection-on-vidor","dataset":"VidOR","dataset_url":"/dataset/vidor","rows_in_archive":2,"metrics":["Recall@100","Recall@50","mAP"],"first_row_in_archive_order":{"model":"Social Fabric","paper_title":"Social Fabric: Tubelet Compositions for Video Relation Detection","paper_url":"/paper/social-fabric-tubelet-compositions-for-video","paper_date":"2021-08-18","arxiv_id":"2108.08363","code_links":[{"title":"shanshuo/social-fabric","url":"https://github.com/shanshuo/social-fabric"}],"syntology":null}}],"datasets":[{"url":"/dataset/imagenet-vidvrd","name":"ImageNet-VidVRD","full_name":"","num_papers_in_archive":10},{"url":"/dataset/vidor","name":"VidOR","full_name":"","num_papers_in_archive":5}],"subtasks":[],"parent_tasks":[{"url":"/task/visual-relationship-detection","name":"Visual Relationship Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":9,"of":9,"tagged_in_all":15,"items":[{"url":"/paper/spatial-temporal-transformer-for-dynamic","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","date":"2021-07-26","arxiv_id":"2107.12309","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":5}},{"url":"/paper/vrdone-one-stage-video-visual-relation","title":"VrdONE: One-stage Video Visual Relation Detection","date":"2024-08-18","arxiv_id":"2408.09408","repositories_listed":1,"syntology":null},{"url":"/paper/sportshhi-a-dataset-for-human-human","title":"SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos","date":"2024-04-06","arxiv_id":"2404.04565","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-prompt-tuning-with-motion-cues","title":"Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection","date":"2023-02-01","arxiv_id":"2302.00268","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/video-relation-detection-via-tracklet-based","title":"Video Relation Detection via Tracklet based Visual Transformer","date":"2021-08-19","arxiv_id":"2108.08669","repositories_listed":1,"syntology":null},{"url":"/paper/social-fabric-tubelet-compositions-for-video","title":"Social Fabric: Tubelet Compositions for Video Relation Detection","date":"2021-08-18","arxiv_id":"2108.08363","repositories_listed":1,"syntology":null},{"url":"/paper/what-and-when-to-look-temporal-span-proposal","title":"What and When to Look?: Temporal Span Proposal Network for Video Relation Detection","date":"2021-07-15","arxiv_id":"2107.07154","repositories_listed":1,"syntology":null},{"url":"/paper/lighten-learning-interactions-with-graph-and","title":"LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos","date":"2020-12-17","arxiv_id":"2012.09402","repositories_listed":1,"syntology":null},{"url":"/paper/video-relationship-reasoning-using-gated","title":"Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph","date":"2019-03-25","arxiv_id":"1903.10547","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}