{"url":"/sota/3d-action-recognition-on-assembly101","task":{"name":"3D Action Recognition","url":"/task/3d-human-action-recognition","note":null},"dataset":{"name":"Assembly101","url":"/dataset/assembly101"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"Image: [Rahmani et al](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Rahmani_3D_Action_Recognition_CVPR_2016_paper.pdf)","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":["Actions Top-1","Verbs Top-1","Object Top-1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Actions Top-1":"higher","Verbs Top-1":"higher","Object Top-1":"higher"}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"HandFormer-B/21","metrics":{"Actions Top-1":"41.06","Object Top-1":"51.17","Verbs Top-1":"69.23"},"uses_additional_data":false,"paper_date":"2024-03-14","paper":"/paper/on-the-utility-of-3d-hand-poses-for-action","paper_url":"https://arxiv.org/abs/2403.09805v2","paper_title":"On the Utility of 3D Hand Poses for Action Recognition","code":"https://github.com/s-shamil/HandFormer","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"TSM","metrics":{"Actions Top-1":"35.27","Object Top-1":"47.45","Verbs Top-1":"58.27"},"uses_additional_data":false,"paper_date":"2018-11-20","paper":"/paper/temporal-shift-module-for-efficient-video","paper_url":"https://arxiv.org/abs/1811.08383v3","paper_title":"TSM: Temporal Shift Module for Efficient Video Understanding","code":"https://github.com/open-mmlab/mmaction2","n_code_links":13,"syntology":{"n_ran":6,"n_unverified":10,"n_samples":16,"n_pointer_only_licence":4}},{"rank_in_archive_order":3,"model":"RGBPoseConv3D","metrics":{"Actions Top-1":"33.61","Object Top-1":"42.90","Verbs Top-1":"61.99"},"uses_additional_data":false,"paper_date":"2021-04-28","paper":"/paper/revisiting-skeleton-based-action-recognition","paper_url":"https://arxiv.org/abs/2104.13586v2","paper_title":"Revisiting Skeleton-based Action Recognition","code":"https://github.com/open-mmlab/mmaction2","n_code_links":4,"syntology":null},{"rank_in_archive_order":4,"model":"MS-G3D","metrics":{"Actions Top-1":"28.7","Object Top-1":"36.3","Verbs Top-1":"65.7"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/disentangling-and-unifying-graph-convolutions","paper_url":"https://arxiv.org/abs/2003.14111v2","paper_title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","code":"https://github.com/kennymckormick/pyskl","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"ISTA-Net","metrics":{"Actions Top-1":"28.07","Object Top-1":"31.69","Verbs Top-1":"62.66"},"uses_additional_data":false,"paper_date":"2023-07-14","paper":"/paper/interactive-spatiotemporal-token-attention","paper_url":"https://arxiv.org/abs/2307.07469v1","paper_title":"Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition","code":"https://github.com/Necolizer/ISTA-Net","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"CHASE(CTR-GCN)","metrics":{"Actions Top-1":"28.03"},"uses_additional_data":false,"paper_date":"2024-10-09","paper":"/paper/chase-learning-convex-hull-adaptive-shift-for","paper_url":"https://arxiv.org/abs/2410.07153v2","paper_title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","code":"https://github.com/Necolizer/CHASE","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"2s-AGCN","metrics":{"Actions Top-1":"26.7","Object Top-1":"33.8","Verbs Top-1":"64.4"},"uses_additional_data":false,"paper_date":"2018-05-20","paper":"/paper/non-local-graph-convolutional-networks-for","paper_url":"https://arxiv.org/abs/1805.07694v3","paper_title":"Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition","code":"https://github.com/benedekrozemberczki/pytorch_geometric_temporal","n_code_links":4,"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":5,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":20,"n_unverified":15,"n_samples":35,"n_pointer_only_licence":4,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":20,"n_unverified":15,"n_samples":35,"n_pointer_only_licence":4,"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"}}}