{"url":"/sota/temporal-sentence-grounding-on-ego4d-goalstep","task":{"name":"Temporal Sentence Grounding","url":"/task/temporal-sentence-grounding","note":null},"dataset":{"name":"Ego4D-Goalstep","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Temporal sentence grounding (TSG) aims to locate a specific moment from an untrimmed video with a given natural language query. For this task, different levels of supervision are used. 1) Weak supervision: video-level action category set; 2) Semi-weak supervision: video-level action category set, and action annotations at several timestamps; 3) Full supervision: Action category and action interval annotations of all actions in untrimmed videos.","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":["R@1,IoU=0.3","R@1,IoU=0.5","R@5,IoU=0.3","R@5,IoU=0.5"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"R@1,IoU=0.3":"higher","R@1,IoU=0.5":"higher","R@5,IoU=0.3":"higher","R@5,IoU=0.5":"higher"}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DeCafNet-100%","metrics":{"R@1,IoU=0.3":"23.20","R@1,IoU=0.5":"19.40","R@5,IoU=0.3":"51.38","R@5,IoU=0.5":"44.17"},"uses_additional_data":false,"paper_date":"2025-05-22","paper":"/paper/decafnet-delegate-and-conquer-for-efficient","paper_url":"https://arxiv.org/abs/2505.16376v1","paper_title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","code":"https://github.com/zijialewislu/cvpr2025-decafnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DeCafNet-50%","metrics":{"R@1,IoU=0.3":"21.29","R@1,IoU=0.5":"17.46","R@5,IoU=0.3":"47.27","R@5,IoU=0.5":"40.40"},"uses_additional_data":false,"paper_date":"2025-05-22","paper":"/paper/decafnet-delegate-and-conquer-for-efficient","paper_url":"https://arxiv.org/abs/2505.16376v1","paper_title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","code":"https://github.com/zijialewislu/cvpr2025-decafnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"VSLNet","metrics":{"R@1,IoU=0.3":"11.70"},"uses_additional_data":false,"paper_date":"2020-04-29","paper":"/paper/span-based-localizing-network-for-natural","paper_url":"https://arxiv.org/abs/2004.13931v2","paper_title":"Span-based Localizing Network for Natural Language Video Localization","code":"https://github.com/IsaacChanghau/VSLNet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":7,"n_samples":8,"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":1,"n_unverified":7,"n_samples":8,"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"}}}