{"url":"/sota/action-classification-on-kinetics-sounds","task":{"name":"Action Classification","url":"/task/action-classification","note":null},"dataset":{"name":"Kinetics-Sounds","url":"/dataset/kinetics"},"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":4,"rows_with_code":1,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CA2ST(B/16)","metrics":{"Top 1 Accuracy":"93.3"},"uses_additional_data":false,"paper_date":"2025-03-30","paper":"/paper/ca-2st-cross-attention-in-audio-space-and","paper_url":"https://arxiv.org/abs/2503.23447v1","paper_title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"CAVA(B/16)","metrics":{"Top 1 Accuracy":"92.9"},"uses_additional_data":false,"paper_date":"2025-03-30","paper":"/paper/ca-2st-cross-attention-in-audio-space-and","paper_url":"https://arxiv.org/abs/2503.23447v1","paper_title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Mirasol3B","metrics":{"Top 1 Accuracy":"90.1"},"uses_additional_data":false,"paper_date":"2023-11-09","paper":"/paper/mirasol3b-a-multimodal-autoregressive-model","paper_url":"https://arxiv.org/abs/2311.05698v3","paper_title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"MBT (AV)","metrics":{"Top 1 Accuracy":"85","Top 5 Accuracy":"96.8"},"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}],"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":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"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":0,"n_unverified":0,"n_samples":0,"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"}}}