{"url":"/sota/temporal-action-localization-on-crosstask","task":{"name":"Temporal Action Localization","url":"/task/action-recognition","note":null},"dataset":{"name":"CrossTask","url":"/dataset/crosstask"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Temporal Action Localization aims to detect activities in the video stream and  output beginning and end timestamps. It is closely related to  Temporal Action Proposal Generation.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Recall"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Recall":"higher"}},"counts":{"rows":7,"rows_with_code":5,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":3},"rows":[{"rank_in_archive_order":1,"model":"VideoCLIP","metrics":{"Recall":"47.3"},"uses_additional_data":true,"paper_date":"2021-09-28","paper":"/paper/videoclip-contrastive-pre-training-for-zero","paper_url":"https://arxiv.org/abs/2109.14084v2","paper_title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","code":"https://github.com/facebookresearch/fairseq","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"VLM","metrics":{"Recall":"46.5"},"uses_additional_data":true,"paper_date":"2021-05-20","paper":"/paper/vlm-task-agnostic-video-language-model-pre","paper_url":"https://arxiv.org/abs/2105.09996v3","paper_title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","code":"https://github.com/pytorch/fairseq","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"TACo","metrics":{"Recall":"42.5"},"uses_additional_data":true,"paper_date":"2021-08-23","paper":"/paper/taco-token-aware-cascade-contrastive-learning","paper_url":"https://arxiv.org/abs/2108.09980v1","paper_title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"Text-Video Embedding","metrics":{"Recall":"33.6"},"uses_additional_data":false,"paper_date":"2019-06-07","paper":"/paper/howto100m-learning-a-text-video-embedding-by","paper_url":"https://arxiv.org/abs/1906.03327v2","paper_title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","code":"https://github.com/antoine77340/MIL-NCE_HowTo100M","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":5,"model":"Fully-supervised upper-bound","metrics":{"Recall":"31.6"},"uses_additional_data":false,"paper_date":"2019-03-19","paper":"/paper/cross-task-weakly-supervised-learning-from","paper_url":"http://arxiv.org/abs/1903.08225v2","paper_title":"Cross-task weakly supervised learning from instructional videos","code":"https://github.com/DmZhukov/CrossTask","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"Zhukov","metrics":{"Recall":"22.4"},"uses_additional_data":false,"paper_date":"2019-03-19","paper":"/paper/cross-task-weakly-supervised-learning-from","paper_url":"http://arxiv.org/abs/1903.08225v2","paper_title":"Cross-task weakly supervised learning from instructional videos","code":"https://github.com/DmZhukov/CrossTask","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"Alayrac","metrics":{"Recall":"13.3"},"uses_additional_data":false,"paper_date":"2015-06-30","paper":"/paper/unsupervised-learning-from-narrated","paper_url":"http://arxiv.org/abs/1506.09215v4","paper_title":"Unsupervised Learning from Narrated Instruction Videos","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}