{"url":"/sota/activity-detection-on-ava-speech","task":{"name":"Activity Detection","url":"/task/activity-detection","note":null},"dataset":{"name":"AVA-Speech","url":"/dataset/ava-speech"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Detecting activities in extended videos.","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":["ROC-AUC"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"ROC-AUC":"higher"}},"counts":{"rows":4,"rows_with_code":3,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CNN-BiLSTM_best","metrics":{"ROC-AUC":"95.14"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/a-hybrid-cnn-bilstm-voice-activity-detector","paper_url":"https://arxiv.org/abs/2103.03529v1","paper_title":"A Hybrid CNN-BiLSTM Voice Activity Detector","code":"https://github.com/NickWilkinson37/voxseg","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"CNN-BiLSTM_small","metrics":{"ROC-AUC":"95.13"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/a-hybrid-cnn-bilstm-voice-activity-detector","paper_url":"https://arxiv.org/abs/2103.03529v1","paper_title":"A Hybrid CNN-BiLSTM Voice Activity Detector","code":"https://github.com/NickWilkinson37/voxseg","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"SG-VAD (ours)","metrics":{"ROC-AUC":"94.3"},"uses_additional_data":false,"paper_date":"2022-10-28","paper":"/paper/sg-vad-stochastic-gates-based-speech-activity","paper_url":"https://arxiv.org/abs/2210.16022v1","paper_title":"SG-VAD: Stochastic Gates Based Speech Activity Detection","code":"https://github.com/jsvir/vad","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"ADA-VAD","metrics":{"ROC-AUC":"79.1"},"uses_additional_data":false,"paper_date":"2022-04-22","paper":"/paper/ada-vad-unpaired-adversarial-domain","paper_url":"https://ieeexplore.ieee.org/document/9746755","paper_title":"ADA-VAD: Unpaired Adversarial Domain Adaptation for Noise-Robust Voice Activity Detection","code":null,"n_code_links":0,"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"}}}