{"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":6,"n_unverified":7,"n_pointer_only":0}}}],"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 (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":26,"items":[{"url":"/paper/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_unverified":1,"n_pointer_only":2}},{"url":"/paper/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_unverified":2,"n_pointer_only":6}},{"url":"/paper/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_unverified":1,"n_pointer_only":4}},{"url":"/paper/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":0,"n_unverified":14,"n_pointer_only":14}},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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":10,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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":6,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/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","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","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","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":1,"n_unverified":5,"n_pointer_only":0}}],"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"},"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"}}