{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 <subject, predicate, object> 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\n<span class=\"description-source\">Source: [ImageNet-VidVRD Video Visual Relation Dataset](https://xdshang.github.io/docs/imagenet-vidvrd.html)</span>","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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":15,"of":15,"of_with_code":9,"tagged_in_all":15,"counts":{"archive_papers_tagged":15,"with_a_code_link":9,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":15,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/spatial-temporal-transformer-for-dynamic","slug":"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":13,"n_constructed":4,"n_ran_checked":12,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/spatial-temporal-transformer-for-dynamic#ran","syntology_url":"https://syntology.ai/paper/2107.12309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12309"}},"official":{"repos":["yrcong/sttran"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/vrdone-one-stage-video-visual-relation","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/compositional-prompt-tuning-with-motion-cues#ran","syntology_url":"https://syntology.ai/paper/2302.00268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00268"}},"official":{"repos":["dawn-lx/openvoc-vidvrd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video-relation-detection-via-tracklet-based","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":null,"slug":"openvidvrd-open-vocabulary-video-visual","title":"OpenVidVRD: Open-Vocabulary Video Visual Relation Detection via Prompt-Driven Semantic Space Alignment","date":"2025-03-12","arxiv_id":"2503.09416","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-defense-of-clip-based-video-relation","title":"In Defense of Clip-based Video Relation Detection","date":"2023-07-18","arxiv_id":"2307.08984","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-spatio-temporal-debiasing-for-video","title":"Meta Spatio-Temporal Debiasing for Video Scene Graph Generation","date":"2022-07-23","arxiv_id":"2207.11441","repositories_listed":0,"syntology":null},{"url":null,"slug":"vrdformer-end-to-end-video-visual-relation","title":"VRDFormer: End-to-End Video Visual Relation Detection With Transformers","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-relation-detection-with-trajectory","title":"Video Relation Detection with Trajectory-aware Multi-modal Features","date":"2021-01-20","arxiv_id":"2101.08165","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-short-term-snippet-video-relation","title":"Beyond Short-Term Snippet: Video Relation Detection With Spatio-Temporal Global Context","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/task/video-visual-relation-detection/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/video-visual-relation-detection/papers/ran/1","json":"/task/video-visual-relation-detection/papers/ran/1.json","rows":2}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"ab8ce199af6e779d12b96b56129e9a3c68f936ef8478fb14ca3644c058a590b8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}