{"url":"/sota/action-classification-on-toyota-smarthome","task":{"name":"Action Classification","url":"/task/action-classification","note":null},"dataset":{"name":"Toyota Smarthome dataset","url":"/dataset/toyota-smarthome"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Image source: [The Kinetics Human Action Video Dataset](https://arxiv.org/pdf/1705.06950.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":["CS","CV1","CV2","Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"CS":null,"CV1":null,"CV2":null,"Accuracy":"higher"}},"counts":{"rows":13,"rows_with_code":9,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"π-ViT","metrics":{"CS":"72.9","CV1":"55.2","CV2":"64.8"},"uses_additional_data":true,"paper_date":"2023-11-30","paper":"/paper/just-add-p-pose-induced-video-transformers","paper_url":"https://arxiv.org/abs/2311.18840v1","paper_title":"Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living","code":"https://github.com/dominickrei/pi-vit","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"EPAM-Net","metrics":{"CS":"71.7","CV2":"67.8"},"uses_additional_data":true,"paper_date":"2024-08-10","paper":"/paper/epam-net-an-efficient-pose-driven-attention","paper_url":"https://arxiv.org/abs/2408.05421v1","paper_title":"EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition","code":"https://github.com/ahmed-nady/multimodal-action-recognition","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"MMNet","metrics":{"CS":"70.1"},"uses_additional_data":true,"paper_date":"2022-05-26","paper":"/paper/mmnet-a-model-based-multimodal-network-for","paper_url":"https://ieeexplore.ieee.org/abstract/document/9782511","paper_title":"MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos","code":"https://github.com/bruceyo/MMNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"UNIK","metrics":{"CS":"64.3","CV1":"36.1","CV2":"65.0"},"uses_additional_data":false,"paper_date":"2021-07-19","paper":"/paper/unik-a-unified-framework-for-real-world","paper_url":"https://arxiv.org/abs/2107.08580v1","paper_title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","code":"https://github.com/YangDi666/UNIK","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"AssembleNet++","metrics":{"CS":"63.6"},"uses_additional_data":false,"paper_date":"2020-08-18","paper":"/paper/assemblenet-assembling-modality","paper_url":"https://arxiv.org/abs/2008.08072v1","paper_title":"AssembleNet++: Assembling Modality Representations via Attention Connections","code":"https://github.com/google-research/google-research/tree/master/assemblenet","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"AIRStreams","metrics":{"CS":"62.11"},"uses_additional_data":false,"paper_date":"2021-04-14","paper":"/paper/adaptive-intermediate-representations-for","paper_url":"https://arxiv.org/abs/2104.07135v1","paper_title":"Adaptive Intermediate Representations for Video Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"VPN (RGB + Pose)","metrics":{"CS":"60.8","CV1":"43.8","CV2":"53.5"},"uses_additional_data":true,"paper_date":"2020-07-06","paper":"/paper/vpn-learning-video-pose-embedding-for","paper_url":"https://arxiv.org/abs/2007.03056v1","paper_title":"VPN: Learning Video-Pose Embedding for Activities of Daily Living","code":"https://github.com/srijandas07/VPN","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"Separable STA (RGB + Pose)","metrics":{"CS":"54.2","CV1":"35.2","CV2":"50.3"},"uses_additional_data":true,"paper_date":"2019-10-01","paper":"/paper/toyota-smarthome-real-world-activities-of","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Das_Toyota_Smarthome_Real-World_Activities_of_Daily_Living_ICCV_2019_paper.html","paper_title":"Toyota Smarthome: Real-World Activities of Daily Living","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"I3D + Non Local","metrics":{"CS":"53.6","CV1":"34.3","CV2":"43.9"},"uses_additional_data":true,"paper_date":"2017-11-21","paper":"/paper/non-local-neural-networks","paper_url":"http://arxiv.org/abs/1711.07971v3","paper_title":"Non-local Neural Networks","code":"https://github.com/facebookresearch/detectron","n_code_links":32,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":10,"model":"I3D","metrics":{"CS":"53.4","CV1":"34.9","CV2":"45.1"},"uses_additional_data":true,"paper_date":"2017-05-22","paper":"/paper/quo-vadis-action-recognition-a-new-model-and","paper_url":"http://arxiv.org/abs/1705.07750v3","paper_title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","code":"https://github.com/open-mmlab/mmaction2","n_code_links":34,"syntology":{"n_ran":16,"n_unverified":12,"n_samples":28,"n_pointer_only_licence":7}},{"rank_in_archive_order":11,"model":"Dense Trajectories","metrics":{"CS":"41.9","CV1":"20.9","CV2":"23.7"},"uses_additional_data":false,"paper_date":"2016-04-29","paper":"/paper/improved-dense-trajectory-with-cross-streams","paper_url":"http://arxiv.org/abs/1604.08826v1","paper_title":"Improved Dense Trajectory with Cross Streams","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"NPL","metrics":{"CV1":"39.6","CV2":"54.6"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/recognizing-actions-in-videos-from-unseen","paper_url":"https://arxiv.org/abs/2103.16516v1","paper_title":"Recognizing Actions in Videos from Unseen Viewpoints","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"Trans4SOAR (Pose)","metrics":{"Accuracy":"70.22"},"uses_additional_data":false,"paper_date":"2022-02-23","paper":"/paper/proformer-learning-data-efficient","paper_url":"https://arxiv.org/abs/2202.11423v3","paper_title":"Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions","code":"https://github.com/kpeng9510/trans4soar","n_code_links":2,"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":19,"n_unverified":13,"n_samples":32,"n_pointer_only_licence":11,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":19,"n_unverified":13,"n_samples":32,"n_pointer_only_licence":11,"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"}}}