{"url":"/sota/temporal-action-localization-on-muses","task":{"name":"Temporal Action Localization","url":"/task/action-recognition","note":null},"dataset":{"name":"MUSES","url":"/dataset/muses"},"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":["mAP","mAP@0.3","mAP@0.4","mAP@0.5","mAP@0.6","mAP@0.7"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mAP":"higher","mAP@0.3":"higher","mAP@0.4":"higher","mAP@0.5":"higher","mAP@0.6":"higher","mAP@0.7":"higher"}},"counts":{"rows":2,"rows_with_code":2,"rows_with_paper_page":2,"rows_dated":2,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"TemporalMaxer","metrics":{"mAP":"27.2","mAP@0.3":"36.7","mAP@0.4":"33.2","mAP@0.5":"27.8 ","mAP@0.6":"21.9","mAP@0.7":"16.2"},"uses_additional_data":false,"paper_date":"2023-03-16","paper":"/paper/temporalmaxer-maximize-temporal-context-with","paper_url":"https://arxiv.org/abs/2303.09055v1","paper_title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","code":"https://github.com/tuantng/temporalmaxer","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"MUSES","metrics":{"mAP":"18.6","mAP@0.3":"25.9","mAP@0.4":"22.6","mAP@0.5":"18.9","mAP@0.6":"15.0","mAP@0.7":"10.6"},"uses_additional_data":false,"paper_date":"2020-12-17","paper":"/paper/multi-shot-temporal-event-localization-a","paper_url":"https://arxiv.org/abs/2012.09434v2","paper_title":"Multi-shot Temporal Event Localization: a Benchmark","code":"https://github.com/xlliu7/muses","n_code_links":1,"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":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"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"}}}