{"url":"/dataset/ave","name":"AVE","full_name":"Audio-Visual Event Localization","description_markdown":"To investigate three temporal localization tasks: supervised and weakly-supervised audio-visual event localization, and cross-modality localization.\r\n\r\nSource: [Audio-Visual Event Localization in Unconstrained Videos](/paper/audio-visual-event-localization-in)","description_withheld":null,"homepage":"https://sites.google.com/view/audiovisualresearch","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/audio-visual-event-localization-in","title":"Audio-Visual Event Localization in Unconstrained Videos","first_author":"Yapeng Tian","url":null},"license":null,"modalities":[],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Multiple Instance Learning","url":"/task/multiple-instance-learning","datasets_with_task":"/datasets/task/multiple-instance-learning"},{"name":"Temporal Localization","url":"/task/temporal-localization","datasets_with_task":"/datasets/task/temporal-localization"}],"languages":[],"variants":["AVE"],"data_loaders":[],"num_papers_in_archive":103,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}