{"url":"/task/long-video-retrieval-background-removed","name":"Long Video Retrieval (Background Removed)","slug":"long-video-retrieval-background-removed","description_markdown":"Retrieve the long videos given all subtitles.","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":6,"papers_with_code":6,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/long-video-retrieval-background-removed-on","slug":"long-video-retrieval-background-removed-on","dataset":"YouCook2","dataset_url":"/dataset/youcook2","rows_in_archive":6,"metrics":["Cap. Avg. R@1","Cap. Avg. R@5","Cap. Avg. R@10","DTW R@1","DTW R@5","DTW R@10","OTAM R@1","OTAM R@5","OTAM R@10"],"first_row_in_archive_order":{"model":"Norton","paper_title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","paper_url":"/paper/multi-granularity-correspondence-learning-1","paper_date":"2024-01-30","arxiv_id":"2401.16702","code_links":[{"title":"XLearning-SCU/2024-ICLR-Norton","url":"https://github.com/XLearning-SCU/2024-ICLR-Norton"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/youcook2","name":"YouCook2","full_name":"","num_papers_in_archive":198}],"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":6,"of":6,"tagged_in_all":6,"items":[{"url":"/paper/end-to-end-learning-of-visual-representations","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","date":"2019-12-13","arxiv_id":"1912.06430","repositories_listed":4,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/howto100m-learning-a-text-video-embedding-by","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","date":"2019-06-07","arxiv_id":"1906.03327","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/videoclip-contrastive-pre-training-for-zero","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","date":"2021-09-28","arxiv_id":"2109.14084","repositories_listed":2,"syntology":null},{"url":"/paper/multi-granularity-correspondence-learning-1","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","date":"2024-01-30","arxiv_id":"2401.16702","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/tempclr-temporal-alignment-representation","title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","date":"2022-12-28","arxiv_id":"2212.13738","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/multimodal-clustering-networks-for-self","title":"Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos","date":"2021-04-26","arxiv_id":"2104.12671","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}],"syntology_records":5,"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"}}