{"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":"/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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":25,"of":25,"of_with_code":13,"tagged_in_all":25,"counts":{"archive_papers_tagged":25,"with_a_code_link":13,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":25,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/is-someone-speaking-exploring-long-term","slug":"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":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/is-someone-speaking-exploring-long-term#ran","syntology_url":"https://syntology.ai/paper/2107.06592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06592"}},"official":{"repos":["TaoRuijie/TalkNet_ASD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/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","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/ava-activespeaker-an-audio-visual-dataset-for","slug":"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","slug":"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","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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/active-speakers-in-context","slug":"active-speakers-in-context","title":"Active Speakers in Context","date":"2020-05-20","arxiv_id":"2005.09812","repositories_listed":1,"syntology":null},{"url":null,"slug":"an-efficient-and-streaming-audio-visual","title":"An Efficient and Streaming Audio Visual Active Speaker Detection System","date":"2024-09-13","arxiv_id":"2409.09018","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-real-world-active-speaker-detection","title":"Enhancing Real-World Active Speaker Detection with Multi-Modal Extraction Pre-Training","date":"2024-04-01","arxiv_id":"2404.00861","repositories_listed":0,"syntology":null},{"url":null,"slug":"push-pull-characterizing-the-adversarial","title":"Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection","date":"2022-10-03","arxiv_id":"2210.00753","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/paper/egocentric-deep-multi-channel-audio-visual","slug":"egocentric-deep-multi-channel-audio-visual","title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","date":"2022-01-06","arxiv_id":"2201.01928","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-spatial-temporal-graphs-for-active","title":"Learning Spatial-Temporal Graphs for Active Speaker Detection","date":"2021-12-02","arxiv_id":"2112.01479","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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,"repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":"/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,"repositories_listed":0,"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"},"key_notes":{"n_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'","n_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_where_code_ran":3,"papers_where_code_ran_first_page":"/task/audio-visual-active-speaker-detection/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/audio-visual-active-speaker-detection/papers/ran/1","json":"/task/audio-visual-active-speaker-detection/papers/ran/1.json","rows":3}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"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"},"record_sha256":"65f8651a4a2210d59bb18cb00a57f284f8933b2d24bea926b8df4073dc9c576d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}