{"url":"/task/video-scene-graph-generation","name":"Video scene graph generation","slug":"video-scene-graph-generation","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":16,"papers_with_code":7,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":0},"benchmarks":[{"leaderboard":"/sota/video-scene-graph-generation-on-imagenet","slug":"video-scene-graph-generation-on-imagenet","dataset":"ImageNet-VidVRD","dataset_url":"/dataset/imagenet-vidvrd","rows_in_archive":1,"metrics":["Recall@50"],"first_row_in_archive_order":{"model":"DLL","paper_title":"Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learning","paper_url":"/paper/taking-a-closer-look-at-visual-relation","paper_date":"2023-03-23","arxiv_id":"2303.13209","code_links":[{"title":"Wq23333/DLL","url":"https://github.com/Wq23333/DLL"}],"syntology":null}}],"datasets":[{"url":"/dataset/situated-reasoning-star","name":"STAR Benchmark","full_name":"Situated Reasoning","num_papers_in_archive":17},{"url":"/dataset/imagenet-vidvrd","name":"ImageNet-VidVRD","full_name":"","num_papers_in_archive":10}],"subtasks":[],"parent_tasks":[],"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":7,"of":7,"tagged_in_all":16,"items":[{"url":"/paper/panoptic-video-scene-graph-generation-1","title":"Panoptic Video Scene Graph Generation","date":"2023-11-28","arxiv_id":"2311.17058","repositories_listed":3,"syntology":{"n":11,"n_ran":11,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/diffvsgg-diffusion-driven-online-video-scene","title":"DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation","date":"2025-03-18","arxiv_id":"2503.13957","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-video-scene-graph","title":"Weakly Supervised Video Scene Graph Generation via Natural Language Supervision","date":"2025-02-21","arxiv_id":"2502.15370","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"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/spatial-temporal-knowledge-embedded","title":"Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation","date":"2023-09-23","arxiv_id":"2309.13237","repositories_listed":1,"syntology":null},{"url":"/paper/taking-a-closer-look-at-visual-relation","title":"Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learning","date":"2023-03-23","arxiv_id":"2303.13209","repositories_listed":1,"syntology":null},{"url":"/paper/target-adaptive-context-aggregation-for-video","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","date":"2021-08-18","arxiv_id":"2108.08121","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"}}