{"url":"/sota/egocentric-activity-recognition-on-egtea-1","task":{"name":"Egocentric Activity Recognition","url":"/task/egocentric-activity-recognition","note":null},"dataset":{"name":"EGTEA","url":"/dataset/egtea"},"category":"Computer Vision","categories":["Computer Vision","Robots","Time Series"],"category_note":null,"description":null,"description_from":null,"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":["Average Accuracy","Mean class accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average Accuracy":"higher","Mean class accuracy":"higher"}},"counts":{"rows":6,"rows_with_code":5,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"LaViLa (Finetuned, TimeSformer-L)","metrics":{"Average Accuracy":"81.75","Mean class accuracy":"76"},"uses_additional_data":false,"paper_date":"2022-12-08","paper":"/paper/learning-video-representations-from-large","paper_url":"https://arxiv.org/abs/2212.04501v1","paper_title":"Learning Video Representations from Large Language Models","code":"https://github.com/facebookresearch/lavila","n_code_links":3,"syntology":{"n_ran":13,"n_unverified":7,"n_samples":20,"n_pointer_only_licence":20}},{"rank_in_archive_order":2,"model":"Min et al.","metrics":{"Average Accuracy":"69.58","Mean class accuracy":"62.84"},"uses_additional_data":false,"paper_date":"2020-11-08","paper":"/paper/integrating-human-gaze-into-attention-for","paper_url":"https://arxiv.org/abs/2011.03920v1","paper_title":"Integrating Human Gaze into Attention for Egocentric Activity Recognition","code":"https://github.com/kylemin/Gaze-Attention","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"GC-TSM","metrics":{"Average Accuracy":"65.1"},"uses_additional_data":false,"paper_date":"2022-03-18","paper":"/paper/group-contextualization-for-video-recognition","paper_url":"https://arxiv.org/abs/2203.09694v1","paper_title":"Group Contextualization for Video Recognition","code":"https://github.com/haoyanbin918/group-contextualization","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"SAP","metrics":{"Average Accuracy":"62.7","Mean class accuracy":"-"},"uses_additional_data":false,"paper_date":"2020-02-08","paper":"/paper/symbiotic-attention-with-privileged","paper_url":"https://arxiv.org/abs/2002.03137v1","paper_title":"Symbiotic Attention with Privileged Information for Egocentric Action Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"LSTA","metrics":{"Average Accuracy":"61.9","Mean class accuracy":"-"},"uses_additional_data":false,"paper_date":"2018-11-26","paper":"/paper/lsta-long-short-term-attention-for-egocentric","paper_url":"http://arxiv.org/abs/1811.10698v3","paper_title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","code":"https://github.com/swathikirans/LSTA","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"Ego-RNN","metrics":{"Average Accuracy":"60.8","Mean class accuracy":"-"},"uses_additional_data":false,"paper_date":"2018-07-31","paper":"/paper/attention-is-all-we-need-nailing-down-object","paper_url":"http://arxiv.org/abs/1807.11794v1","paper_title":"Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition","code":"https://github.com/swathikirans/ego-rnn","n_code_links":1,"syntology":null}],"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":18,"n_unverified":7,"n_samples":25,"n_pointer_only_licence":20,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":18,"n_unverified":7,"n_samples":25,"n_pointer_only_licence":20,"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"}}}