{"url":"/task/zero-shot-action-detection","name":"Zero-Shot Action Detection","slug":"zero-shot-action-detection","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":6,"papers_with_code":5,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":[],"datasets":[{"url":"/dataset/activitynet","name":"ActivityNet","full_name":"","num_papers_in_archive":807},{"url":"/dataset/thumos14-1","name":"THUMOS14","full_name":"","num_papers_in_archive":318}],"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":5,"of":5,"tagged_in_all":6,"items":[{"url":"/paper/scaling-open-vocabulary-action-detection","title":"Scaling Open-Vocabulary Action Detection","date":"2025-04-04","arxiv_id":"2504.03096","repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-temporal-action-localization-1","title":"Open-Vocabulary Action Localization with Iterative Visual Prompting","date":"2024-08-30","arxiv_id":"2408.17422","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/unloc-a-unified-framework-for-video","title":"UnLoc: A Unified Framework for Video Localization Tasks","date":"2023-08-21","arxiv_id":"2308.11062","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-temporal-action-detection-via","title":"Zero-Shot Temporal Action Detection via Vision-Language Prompting","date":"2022-07-17","arxiv_id":"2207.08184","repositories_listed":1,"syntology":null},{"url":"/paper/prompting-visual-language-models-for","title":"Prompting Visual-Language Models for Efficient Video Understanding","date":"2021-12-08","arxiv_id":"2112.04478","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":0}}],"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"}}