{"url":"/task/audio-visual-active-speaker-detection","name":"Audio-Visual Active Speaker Detection","slug":"audio-visual-active-speaker-detection","description_markdown":"Determine if and when each visible person in the video is speaking.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":25,"papers_with_code":13,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/audio-visual-active-speaker-detection-on-ava","slug":"audio-visual-active-speaker-detection-on-ava","dataset":"AVA-ActiveSpeaker","dataset_url":"/dataset/ava-activespeaker","rows_in_archive":20,"metrics":["validation mean average precision"],"first_row_in_archive_order":{"model":"LoCoNet+TalkNCE","paper_title":"TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning","paper_url":"/paper/talknce-improving-active-speaker-detection","paper_date":"2023-09-21","arxiv_id":"2309.12306","code_links":[{"title":"kaistmm/TalkNCE","url":"https://github.com/kaistmm/TalkNCE"}],"syntology":null}},{"leaderboard":"/sota/audio-visual-active-speaker-detection-on-vpcd","slug":"audio-visual-active-speaker-detection-on-vpcd","dataset":"VPCD","dataset_url":"/dataset/vpcd","rows_in_archive":1,"metrics":["mean average precision"],"first_row_in_archive_order":{"model":"GSCMIA","paper_title":"Audio-Visual Activity Guided Cross-Modal Identity Association for Active Speaker Detection","paper_url":"/paper/audio-visual-activity-guided-cross-modal","paper_date":"2022-12-01","arxiv_id":"2212.00539","code_links":[{"title":"rash1993/movie-asd","url":"https://github.com/rash1993/movie-asd"}],"syntology":null}}],"datasets":[{"url":"/dataset/ava","name":"AVA","full_name":"Atomic Visual Actions","num_papers_in_archive":113},{"url":"/dataset/ava-activespeaker","name":"AVA-ActiveSpeaker","full_name":"","num_papers_in_archive":22},{"url":"/dataset/vpcd","name":"VPCD","full_name":"Video Person-Clustering","num_papers_in_archive":7}],"subtasks":[],"parent_tasks":[{"url":"/task/action-detection","name":"Action Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":13,"of":13,"tagged_in_all":25,"items":[{"url":"/paper/is-someone-speaking-exploring-long-term","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","date":"2021-07-14","arxiv_id":"2107.06592","repositories_listed":4,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":1}},{"url":"/paper/end-to-end-active-speaker-detection","title":"End-to-End Active Speaker Detection","date":"2022-03-27","arxiv_id":"2203.14250","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/loconet-long-short-context-network-for-active","title":"LoCoNet: Long-Short Context Network for Active Speaker Detection","date":"2023-01-19","arxiv_id":"2301.08237","repositories_listed":2,"syntology":null},{"url":"/paper/learning-long-term-spatial-temporal-graphs","title":"Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection","date":"2022-07-15","arxiv_id":"2207.07783","repositories_listed":2,"syntology":null},{"url":"/paper/ava-activespeaker-an-audio-visual-dataset-for","title":"AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection","date":"2019-01-05","arxiv_id":"1901.01342","repositories_listed":2,"syntology":null},{"url":"/paper/laser-lip-landmark-assisted-speaker-detection","title":"LASER: Lip Landmark Assisted Speaker Detection for Robustness","date":"2025-01-21","arxiv_id":"2501.11899","repositories_listed":1,"syntology":null},{"url":"/paper/talknce-improving-active-speaker-detection","title":"TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning","date":"2023-09-21","arxiv_id":"2309.12306","repositories_listed":1,"syntology":null},{"url":"/paper/a-light-weight-model-for-active-speaker","title":"A Light Weight Model for Active Speaker Detection","date":"2023-03-08","arxiv_id":"2303.04439","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/audio-visual-activity-guided-cross-modal","title":"Audio-Visual Activity Guided Cross-Modal Identity Association for Active Speaker Detection","date":"2022-12-01","arxiv_id":"2212.00539","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-design-a-three-stage-architecture-for","title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","date":"2021-06-07","arxiv_id":"2106.03932","repositories_listed":1,"syntology":null},{"url":"/paper/nus-hlt-report-for-activitynet-challenge-2021","title":"NUS-HLT Report for ActivityNet Challenge 2021 AVA (Speaker)","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/maas-multi-modal-assignation-for-active","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","date":"2021-01-11","arxiv_id":"2101.03682","repositories_listed":1,"syntology":null},{"url":"/paper/active-speakers-in-context","title":"Active Speakers in Context","date":"2020-05-20","arxiv_id":"2005.09812","repositories_listed":1,"syntology":null}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}