{"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-event-localization","name":"audio-visual event localization","slug":"audio-visual-event-localization","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":26,"papers_with_code":13,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/audio-visual-event-localization-on-unav-100","slug":"audio-visual-event-localization-on-unav-100","dataset":"UnAV-100","dataset_url":"/dataset/unav-100","rows_in_archive":2,"metrics":[" mAP","AP@IOU0.5"],"first_row_in_archive_order":{"model":"UnAV","paper_title":"Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline","paper_url":"/paper/dense-localizing-audio-visual-events-in","paper_date":"2023-03-22","arxiv_id":"2303.12930","code_links":[{"title":"ttgeng233/UnAV","url":"https://github.com/ttgeng233/UnAV"}],"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":3,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dense-localizing-audio-visual-events-in#ran","syntology_url":"https://syntology.ai/paper/2303.12930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12930"}},"official":{"repos":["ttgeng233/UnAV"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/unav-100","name":"UnAV-100","full_name":"","num_papers_in_archive":13},{"url":"/dataset/longvale","name":"LongVALE","full_name":"","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[],"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":26,"of":26,"of_with_code":13,"tagged_in_all":26,"counts":{"archive_papers_tagged":26,"with_a_code_link":13,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":26,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/positive-sample-propagation-along-the-audio","slug":"positive-sample-propagation-along-the-audio","title":"Positive Sample Propagation along the Audio-Visual Event Line","date":"2021-04-01","arxiv_id":"2104.00239","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/positive-sample-propagation-along-the-audio#ran","syntology_url":"https://syntology.ai/paper/2104.00239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00239"}},"official":{"repos":["jasongief/PSP_CVPR_2021"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/dual-modality-seq2seq-network-for-audio","slug":"dual-modality-seq2seq-network-for-audio","title":"Dual-modality seq2seq network for audio-visual event localization","date":"2019-02-20","arxiv_id":"1902.07473","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dual-modality-seq2seq-network-for-audio#ran","syntology_url":"https://syntology.ai/paper/1902.07473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.07473"}},"official":null}},{"url":"/paper/audio-visual-event-localization-in","slug":"audio-visual-event-localization-in","title":"Audio-Visual Event Localization in Unconstrained Videos","date":"2018-03-23","arxiv_id":"1803.08842","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/audio-visual-event-localization-in#ran","syntology_url":"https://syntology.ai/paper/1803.08842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08842"}},"official":null}},{"url":"/paper/dense-audio-visual-event-localization-under","slug":"dense-audio-visual-event-localization-under","title":"Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration","date":"2024-12-17","arxiv_id":"2412.12628","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":3,"n_instrument":10,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dense-audio-visual-event-localization-under#ran","syntology_url":"https://syntology.ai/paper/2412.12628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12628"}},"official":{"repos":["zzhhfut/ccnet-aaai2025"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-open-vocabulary-audio-visual-event","slug":"towards-open-vocabulary-audio-visual-event","title":"Towards Open-Vocabulary Audio-Visual Event Localization","date":"2024-11-18","arxiv_id":"2411.11278","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-open-vocabulary-audio-visual-event#ran","syntology_url":"https://syntology.ai/paper/2411.11278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11278"}},"official":{"repos":["jasongief/ov-avel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-01952","slug":"2408-01952","title":"CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization","date":"2024-08-04","arxiv_id":"2408.01952","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2408-01952#ran","syntology_url":"https://syntology.ai/paper/2408.01952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01952"}},"official":{"repos":["brain-cog-lab/cace-net"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/uniav-unified-audio-visual-perception-for","slug":"uniav-unified-audio-visual-perception-for","title":"UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization","date":"2024-04-04","arxiv_id":"2404.03179","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":1,"n_ran_checked":4,"n_instrument":9,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"13 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/uniav-unified-audio-visual-perception-for#ran","syntology_url":"https://syntology.ai/paper/2404.03179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03179"}},"official":{"repos":["ttgeng233/UniAV"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/modality-independent-teachers-meet-weakly-1","slug":"modality-independent-teachers-meet-weakly-1","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","date":"2023-05-27","arxiv_id":"2305.17343","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":2,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modality-independent-teachers-meet-weakly-1#ran","syntology_url":"https://syntology.ai/paper/2305.17343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17343"}},"official":{"repos":["franklin905/valor"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dense-localizing-audio-visual-events-in","slug":"dense-localizing-audio-visual-events-in","title":"Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline","date":"2023-03-22","arxiv_id":"2303.12930","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":3,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dense-localizing-audio-visual-events-in#ran","syntology_url":"https://syntology.ai/paper/2303.12930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12930"}},"official":{"repos":["ttgeng233/UnAV"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-the-video-level-semantic","slug":"leveraging-the-video-level-semantic","title":"Leveraging the Video-level Semantic Consistency of Event for Audio-visual Event Localization","date":"2022-10-11","arxiv_id":"2210.05242","repositories_listed":1,"syntology":null},{"url":"/paper/actionformer-localizing-moments-of-actions","slug":"actionformer-localizing-moments-of-actions","title":"ActionFormer: Localizing Moments of Actions with Transformers","date":"2022-02-16","arxiv_id":"2202.07925","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-background-suppression-for-audio","slug":"cross-modal-background-suppression-for-audio","title":"Cross-Modal Background Suppression for Audio-Visual Event Localization","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mm-pyramid-multimodal-pyramid-attentional","slug":"mm-pyramid-multimodal-pyramid-attentional","title":"MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing","date":"2021-11-24","arxiv_id":"2111.12374","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mm-pyramid-multimodal-pyramid-attentional#ran","syntology_url":"https://syntology.ai/paper/2111.12374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12374"}},"official":{"repos":["JustinYuu/MM_Pyramid"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":null,"slug":"audio-visual-event-localization-on-portrait","title":"Audio-visual Event Localization on Portrait Mode Short Videos","date":"2025-04-09","arxiv_id":"2504.06884","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-semantic-graph-network-for-audio","title":"Audio-Visual Semantic Graph Network for Audio-Visual Event Localization","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pilot-guided-multimodal-semantic","title":"Pilot-guided Multimodal Semantic Communication for Audio-Visual Event Localization","date":"2024-12-09","arxiv_id":"2412.06208","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-trustworthy-semantic-communication","title":"Multimodal Trustworthy Semantic Communication for Audio-Visual Event Localization","date":"2024-11-04","arxiv_id":"2411.01991","repositories_listed":0,"syntology":null},{"url":null,"slug":"label-anticipated-event-disentanglement-for","title":"Label-anticipated Event Disentanglement for Audio-Visual Video Parsing","date":"2024-07-11","arxiv_id":"2407.08126","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-weakly-supervised-audio-visual","title":"Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling","date":"2024-06-03","arxiv_id":"2406.00919","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-label-refinement-for-weakly","title":"Temporal Label-Refinement for Weakly-Supervised Audio-Visual Event Localization","date":"2023-07-12","arxiv_id":"2307.06385","repositories_listed":0,"syntology":null},{"url":null,"slug":"ave-clip-audioclip-based-multi-window","title":"AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization","date":"2022-10-11","arxiv_id":"2210.05060","repositories_listed":0,"syntology":null},{"url":null,"slug":"past-and-future-motion-guided-network-for","title":"Past and Future Motion Guided Network for Audio Visual Event Localization","date":"2022-05-08","arxiv_id":"2205.03802","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modulation-network-for-audio-visual","title":"Multi-Modulation Network for Audio-Visual Event Localization","date":"2021-08-26","arxiv_id":"2108.11773","repositories_listed":0,"syntology":null},{"url":null,"slug":"mpn-multimodal-parallel-network-for-audio","title":"MPN: Multimodal Parallel Network for Audio-Visual Event Localization","date":"2021-04-07","arxiv_id":"2104.02971","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-event-localization-via-recursive","title":"Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention","date":"2020-08-14","arxiv_id":"2008.06581","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-attention-matching-for-audio-visual","title":"Dual Attention Matching for Audio-Visual Event Localization","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":10,"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":10,"papers_where_code_ran_first_page":"/task/audio-visual-event-localization/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-event-localization/papers/ran/1","json":"/task/audio-visual-event-localization/papers/ran/1.json","rows":10}],"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":"9af70c32f31d479d717dfe204b4a011f70d0411b4618670d383c9d6a6f36d98c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}