{"url":"/sota/action-classification-on-moments-in-time","task":{"name":"Action Classification","url":"/task/action-classification","note":null},"dataset":{"name":"MiT","url":null},"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":["Top 1 Accuracy","Top 5 Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Top 1 Accuracy":"higher","Top 5 Accuracy":"higher"}},"counts":{"rows":29,"rows_with_code":25,"rows_with_paper_page":29,"rows_dated":29,"rows_using_additional_data":10},"rows":[{"rank_in_archive_order":1,"model":"OmniVec2","metrics":{"Top 1 Accuracy":"53.1"},"uses_additional_data":true,"paper_date":"2024-01-01","paper":"/paper/omnivec2-a-novel-transformer-based-network","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Srivastava_OmniVec2_-_A_Novel_Transformer_based_Network_for_Large_Scale_CVPR_2024_paper.html","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"InternVideo2-1B","metrics":{"Top 1 Accuracy":"50.9"},"uses_additional_data":true,"paper_date":"2024-03-22","paper":"/paper/internvideo2-scaling-video-foundation-models","paper_url":"https://arxiv.org/abs/2403.15377v4","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"UMT-L (ViT-L/16)","metrics":{"Top 1 Accuracy":"48.7","Top 5 Accuracy":"78.2"},"uses_additional_data":true,"paper_date":"2023-03-28","paper":"/paper/unmasked-teacher-towards-training-efficient","paper_url":"https://arxiv.org/abs/2303.16058v2","paper_title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","code":"https://github.com/opengvlab/unmasked_teacher","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"UniFormerV2-L","metrics":{"Top 1 Accuracy":"47.8","Top 5 Accuracy":"76.9"},"uses_additional_data":true,"paper_date":"2022-09-22","paper":"/paper/uniformerv2-spatiotemporal-learning-by-arming","paper_url":"https://openreview.net/forum?id=d77RVuVg-Mf","paper_title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","code":"https://github.com/OpenGVLab/UniFormerV2","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"MTV-H (WTS 60M)","metrics":{"Top 1 Accuracy":"47.2","Top 5 Accuracy":"75.7"},"uses_additional_data":true,"paper_date":"2022-01-12","paper":"/paper/multiview-transformers-for-video-recognition","paper_url":"https://arxiv.org/abs/2201.04288v4","paper_title":"Multiview Transformers for Video Recognition","code":"https://github.com/google-research/scenic","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"CoVeR(JFT-3B)","metrics":{"Top 1 Accuracy":"46.1","Top 5 Accuracy":"75.4"},"uses_additional_data":true,"paper_date":"2021-12-14","paper":"/paper/co-training-transformer-with-videos-and","paper_url":"https://arxiv.org/abs/2112.07175v1","paper_title":"Co-training Transformer with Videos and Images Improves Action Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"CoVeR(JFT-300M)","metrics":{"Top 1 Accuracy":"45.0","Top 5 Accuracy":"73.9"},"uses_additional_data":true,"paper_date":"2021-12-14","paper":"/paper/co-training-transformer-with-videos-and","paper_url":"https://arxiv.org/abs/2112.07175v1","paper_title":"Co-training Transformer with Videos and Images Improves Action Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"VATT-Large","metrics":{"Top 1 Accuracy":"41.1","Top 5 Accuracy":"67.7"},"uses_additional_data":true,"paper_date":"2021-04-22","paper":"/paper/vatt-transformers-for-multimodal-self","paper_url":"https://arxiv.org/abs/2104.11178v3","paper_title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","code":"https://github.com/google-research/google-research/tree/master/vatt","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":9,"model":"MoViNet-A6","metrics":{"Top 1 Accuracy":"40.2"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"MoViNet-A5","metrics":{"Top 1 Accuracy":"39.1"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"MoViNet-A4","metrics":{"Top 1 Accuracy":"37.9"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"VTN","metrics":{"Top 1 Accuracy":"37.4","Top 5 Accuracy":"65.4"},"uses_additional_data":true,"paper_date":"2021-02-01","paper":"/paper/video-transformer-network","paper_url":"https://arxiv.org/abs/2102.00719v3","paper_title":"Video Transformer Network","code":"https://github.com/bomri/SlowFast/blob/master/projects/vtn/README.md","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"MBT (AV)","metrics":{"Top 1 Accuracy":"37.3","Top 5 Accuracy":"61.2"},"uses_additional_data":false,"paper_date":"2021-06-30","paper":"/paper/attention-bottlenecks-for-multimodal-fusion","paper_url":"https://arxiv.org/abs/2107.00135v3","paper_title":"Attention Bottlenecks for Multimodal Fusion","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/mbt","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"MoViNet-A3","metrics":{"Top 1 Accuracy":"35.6"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"MoViNet-A2","metrics":{"Top 1 Accuracy":"34.3"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"AssembleNet","metrics":{"Top 1 Accuracy":"34.27%","Top 5 Accuracy":"62.71%"},"uses_additional_data":false,"paper_date":"2019-05-30","paper":"/paper/assemblenet-searching-for-multi-stream-neural","paper_url":"https://arxiv.org/abs/1905.13209v4","paper_title":"AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/assemblenet","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"SRTG r3d-101","metrics":{"Top 1 Accuracy":"33.56","Top 5 Accuracy":"58.49"},"uses_additional_data":false,"paper_date":"2020-06-15","paper":"/paper/learn-to-cycle-time-consistent-feature","paper_url":"https://arxiv.org/abs/2006.08247v2","paper_title":"Learn to cycle: Time-consistent feature discovery for action recognition","code":"https://github.com/alexandrosstergiou/Squeeze-and-Recursion-Temporal-Gates/blob/master/train_model.py","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"CoST (ResNet-101, 32 frames)","metrics":{"Top 1 Accuracy":"32.4%","Top 5 Accuracy":"60.0%"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/collaborative-spatiotemporal-feature-learning","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Collaborative_Spatiotemporal_Feature_Learning_for_Video_Action_Recognition_CVPR_2019_paper.html","paper_title":"Collaborative Spatiotemporal Feature Learning for Video Action Recognition","code":"https://github.com/hikvision-research/cost","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"MoViNet-A1","metrics":{"Top 1 Accuracy":"32.0"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"EvaNet","metrics":{"Top 1 Accuracy":"31.8%"},"uses_additional_data":false,"paper_date":"2018-11-26","paper":"/paper/evolving-space-time-neural-architectures-for","paper_url":"https://arxiv.org/abs/1811.10636v2","paper_title":"Evolving Space-Time Neural Architectures for Videos","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"SRTG r(2+1)d-50","metrics":{"Top 1 Accuracy":"31.60","Top 5 Accuracy":"56.80"},"uses_additional_data":false,"paper_date":"2020-06-15","paper":"/paper/learn-to-cycle-time-consistent-feature","paper_url":"https://arxiv.org/abs/2006.08247v2","paper_title":"Learn to cycle: Time-consistent feature discovery for action recognition","code":"https://github.com/alexandrosstergiou/Squeeze-and-Recursion-Temporal-Gates/blob/master/train_model.py","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"SRTG r3d-50","metrics":{"Top 1 Accuracy":"30.72","Top 5 Accuracy":"55.65"},"uses_additional_data":false,"paper_date":"2020-06-15","paper":"/paper/learn-to-cycle-time-consistent-feature","paper_url":"https://arxiv.org/abs/2006.08247v2","paper_title":"Learn to cycle: Time-consistent feature discovery for action recognition","code":"https://github.com/alexandrosstergiou/Squeeze-and-Recursion-Temporal-Gates/blob/master/train_model.py","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"I3D","metrics":{"Top 1 Accuracy":"29.51%","Top 5 Accuracy":"56.06%"},"uses_additional_data":false,"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":24,"model":"SRTG r(2+1)d-34","metrics":{"Top 1 Accuracy":"28.97","Top 5 Accuracy":"54.18"},"uses_additional_data":false,"paper_date":"2020-06-15","paper":"/paper/learn-to-cycle-time-consistent-feature","paper_url":"https://arxiv.org/abs/2006.08247v2","paper_title":"Learn to cycle: Time-consistent feature discovery for action recognition","code":"https://github.com/alexandrosstergiou/Squeeze-and-Recursion-Temporal-Gates/blob/master/train_model.py","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"SRTG r3d-34","metrics":{"Top 1 Accuracy":"28.55","Top 5 Accuracy":"52.35"},"uses_additional_data":false,"paper_date":"2020-06-15","paper":"/paper/learn-to-cycle-time-consistent-feature","paper_url":"https://arxiv.org/abs/2006.08247v2","paper_title":"Learn to cycle: Time-consistent feature discovery for action recognition","code":"https://github.com/alexandrosstergiou/Squeeze-and-Recursion-Temporal-Gates/blob/master/train_model.py","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"TRN-Multiscale","metrics":{"Top 1 Accuracy":"28.27","Top 5 Accuracy":"53.87"},"uses_additional_data":false,"paper_date":"2017-11-22","paper":"/paper/temporal-relational-reasoning-in-videos","paper_url":"http://arxiv.org/abs/1711.08496v2","paper_title":"Temporal Relational Reasoning in Videos","code":"https://github.com/metalbubble/TRN-pytorch","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":27,"model":"MoViNet-A0","metrics":{"Top 1 Accuracy":"27.5"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"ViViT-L/16x2","metrics":{"Top 5 Accuracy":"64.9"},"uses_additional_data":true,"paper_date":"2021-03-29","paper":"/paper/2103-15691","paper_url":"https://arxiv.org/abs/2103.15691v2","paper_title":"ViViT: A Video Vision Transformer","code":"https://github.com/google-research/scenic","n_code_links":10,"syntology":{"n_ran":14,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":1}},{"rank_in_archive_order":29,"model":"TSN-2Stream","metrics":{"Top 5 Accuracy":"50.10%"},"uses_additional_data":false,"paper_date":"2017-05-08","paper":"/paper/temporal-segment-networks-for-action","paper_url":"http://arxiv.org/abs/1705.02953v1","paper_title":"Temporal Segment Networks for Action Recognition in Videos","code":"https://github.com/open-mmlab/mmaction2","n_code_links":11,"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":12,"rows_with_any_sample_ran":12,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":51,"n_unverified":30,"n_samples":81,"n_pointer_only_licence":19,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":105,"n_unverified":54,"n_samples":159,"n_pointer_only_licence":19,"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"}}}