{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/ava-activespeaker","name":"AVA-ActiveSpeaker","full_name":null,"description_markdown":"Contains temporally labeled face tracks in video, where each face instance is labeled as speaking or not, and whether the speech is audible. This dataset contains about 3.65 million human labeled frames or about 38.5 hours of face tracks, and the corresponding audio. \r\n\r\nSource: [AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection](/paper/ava-activespeaker-an-audio-visual-dataset-for)","description_withheld":null,"homepage":"https://research.google.com/ava/download.html#ava_active_speaker_download","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/ava-activespeaker-an-audio-visual-dataset-for","title":"AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection","first_author":"Joseph Roth","url":null},"license":null,"modalities":[],"tasks":[{"name":"Speech Enhancement","url":"/task/speech-enhancement","datasets_with_task":"/datasets/task/speech-enhancement"},{"name":"Speaker Diarization","url":"/task/speaker-diarization","datasets_with_task":"/datasets/task/speaker-diarization"},{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","datasets_with_task":"/datasets/task/self-supervised-learning"},{"name":"Audio-Visual Active Speaker Detection","url":"/task/audio-visual-active-speaker-detection","datasets_with_task":"/datasets/task/audio-visual-active-speaker-detection"}],"languages":[],"variants":["AVA-ActiveSpeaker"],"data_loaders":[],"num_papers_in_archive":22,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/audio-visual-active-speaker-detection-on-ava","task":"Audio-Visual Active Speaker Detection","dataset_variant":"AVA-ActiveSpeaker","rows":20,"metrics":["validation mean average precision"],"first_row_in_archive_order":{"model":"LoCoNet+TalkNCE","paper":"/paper/talknce-improving-active-speaker-detection","metrics":{"validation mean average precision":"95.5%"},"code_links":[{"title":"kaistmm/TalkNCE","url":"https://github.com/kaistmm/TalkNCE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":18,"of":18,"counts":{"papers_with_a_benchmark_row":18,"with_a_code_link":11,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":18,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/laser-lip-landmark-assisted-speaker-detection","slug":"laser-lip-landmark-assisted-speaker-detection","title":"LASER: Lip Landmark Assisted Speaker Detection for Robustness","date":"2025-01-21","arxiv_id":"2501.11899","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/talknce-improving-active-speaker-detection","slug":"talknce-improving-active-speaker-detection","title":"TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning","date":"2023-09-21","arxiv_id":"2309.12306","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-light-weight-model-for-active-speaker","slug":"a-light-weight-model-for-active-speaker","title":"A Light Weight Model for Active Speaker Detection","date":"2023-03-08","arxiv_id":"2303.04439","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["junhua-liao/light-asd"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-light-weight-model-for-active-speaker#ran","syntology_url":"https://syntology.ai/paper/2303.04439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04439"}}}},{"paper":"/paper/loconet-long-short-context-network-for-active","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/audio-visual-activity-guided-cross-modal","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-long-term-spatial-temporal-graphs","slug":"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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/unicon-ictcas-ucas-submission-to-the-ava","slug":"unicon-ictcas-ucas-submission-to-the-ava","title":"UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022","date":"2022-06-22","arxiv_id":"2206.10861","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/end-to-end-active-speaker-detection","slug":"end-to-end-active-speaker-detection","title":"End-to-End Active Speaker Detection","date":"2022-03-27","arxiv_id":"2203.14250","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":5,"official":{"repos":["fuankarion/end-to-end-asd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-active-speaker-detection#ran","syntology_url":"https://syntology.ai/paper/2203.14250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14250"}}}},{"paper":"/paper/sub-word-level-lip-reading-with-visual","slug":"sub-word-level-lip-reading-with-visual","title":"Sub-word Level Lip Reading With Visual Attention","date":"2021-10-14","arxiv_id":"2110.07603","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/unicon-unified-context-network-for-robust","slug":"unicon-unified-context-network-for-robust","title":"UniCon: Unified Context Network for Robust Active Speaker Detection","date":"2021-08-05","arxiv_id":"2108.02607","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/active-speaker-detection-as-a-multi-objective","slug":"active-speaker-detection-as-a-multi-objective","title":"Active Speaker Detection as a Multi-Objective Optimization with Uncertainty-based Multimodal Fusion","date":"2021-06-07","arxiv_id":"2106.03821","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/how-to-design-a-three-stage-architecture-for","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ictcas-ucas-tal-submission-to-the-ava","slug":"ictcas-ucas-tal-submission-to-the-ava","title":"ICTCAS-UCAS-TAL Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2021","date":"2021-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/nus-hlt-report-for-activitynet-challenge-2021","slug":"nus-hlt-report-for-activitynet-challenge-2021","title":"NUS-HLT Report for ActivityNet Challenge 2021 AVA (Speaker)","date":"2021-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/maas-multi-modal-assignation-for-active","slug":"maas-multi-modal-assignation-for-active","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","date":"2021-01-11","arxiv_id":"2101.03682","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/active-speakers-in-context","slug":"active-speakers-in-context","title":"Active Speakers in Context","date":"2020-05-20","arxiv_id":"2005.09812","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/naver-at-activitynet-challenge-2019-task-b","slug":"naver-at-activitynet-challenge-2019-task-b","title":"Naver at ActivityNet Challenge 2019 -- Task B Active Speaker Detection (AVA)","date":"2019-06-25","arxiv_id":"1906.10555","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-task-learning-for-audio-visual-active","slug":"multi-task-learning-for-audio-visual-active","title":"Multi-Task Learning for Audio Visual Active Speaker Detection","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/laser-lip-landmark-assisted-speaker-detection","slug":"laser-lip-landmark-assisted-speaker-detection","title":"LASER: Lip Landmark Assisted Speaker Detection for Robustness","date":"2025-01-21","arxiv_id":"2501.11899","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/talknce-improving-active-speaker-detection","slug":"talknce-improving-active-speaker-detection","title":"TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning","date":"2023-09-21","arxiv_id":"2309.12306","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-light-weight-model-for-active-speaker","slug":"a-light-weight-model-for-active-speaker","title":"A Light Weight Model for Active Speaker Detection","date":"2023-03-08","arxiv_id":"2303.04439","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["junhua-liao/light-asd"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-light-weight-model-for-active-speaker#ran","syntology_url":"https://syntology.ai/paper/2303.04439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04439"}}}},{"paper":"/paper/loconet-long-short-context-network-for-active","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/audio-visual-activity-guided-cross-modal","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-long-term-spatial-temporal-graphs","slug":"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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/unicon-ictcas-ucas-submission-to-the-ava","slug":"unicon-ictcas-ucas-submission-to-the-ava","title":"UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022","date":"2022-06-22","arxiv_id":"2206.10861","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/end-to-end-active-speaker-detection","slug":"end-to-end-active-speaker-detection","title":"End-to-End Active Speaker Detection","date":"2022-03-27","arxiv_id":"2203.14250","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":5,"official":{"repos":["fuankarion/end-to-end-asd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-active-speaker-detection#ran","syntology_url":"https://syntology.ai/paper/2203.14250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14250"}}}},{"paper":"/paper/sub-word-level-lip-reading-with-visual","slug":"sub-word-level-lip-reading-with-visual","title":"Sub-word Level Lip Reading With Visual Attention","date":"2021-10-14","arxiv_id":"2110.07603","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/unicon-unified-context-network-for-robust","slug":"unicon-unified-context-network-for-robust","title":"UniCon: Unified Context Network for Robust Active Speaker Detection","date":"2021-08-05","arxiv_id":"2108.02607","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/active-speaker-detection-as-a-multi-objective","slug":"active-speaker-detection-as-a-multi-objective","title":"Active Speaker Detection as a Multi-Objective Optimization with Uncertainty-based Multimodal Fusion","date":"2021-06-07","arxiv_id":"2106.03821","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/how-to-design-a-three-stage-architecture-for","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ictcas-ucas-tal-submission-to-the-ava","slug":"ictcas-ucas-tal-submission-to-the-ava","title":"ICTCAS-UCAS-TAL Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2021","date":"2021-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/nus-hlt-report-for-activitynet-challenge-2021","slug":"nus-hlt-report-for-activitynet-challenge-2021","title":"NUS-HLT Report for ActivityNet Challenge 2021 AVA (Speaker)","date":"2021-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/maas-multi-modal-assignation-for-active","slug":"maas-multi-modal-assignation-for-active","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","date":"2021-01-11","arxiv_id":"2101.03682","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/active-speakers-in-context","slug":"active-speakers-in-context","title":"Active Speakers in Context","date":"2020-05-20","arxiv_id":"2005.09812","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/naver-at-activitynet-challenge-2019-task-b","slug":"naver-at-activitynet-challenge-2019-task-b","title":"Naver at ActivityNet Challenge 2019 -- Task B Active Speaker Detection (AVA)","date":"2019-06-25","arxiv_id":"1906.10555","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-task-learning-for-audio-visual-active","slug":"multi-task-learning-for-audio-visual-active","title":"Multi-Task Learning for Audio Visual Active Speaker Detection","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/ava-activespeaker/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/ava-activespeaker/papers/ran/1","json":"/dataset/ava-activespeaker/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":11,"samples_ran":8,"samples_constructed":1,"samples_ran_checked":6,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":5,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"8ff047f79676959d1316ca3fc35effe90d08f6fb379cbe251c015d6cacf79ae2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}