{"url":"/dataset/avsync15","name":"AVSync15","full_name":null,"description_markdown":"AVSync15 is a high-quality synchronized audio-video dataset curated from VGGSound. It is carefully curated with both automatic and manual steps, ensuring:\r\n\r\nHigh semantic and temporal audio-visual correlation\r\nClean and stable audio-visual contents\r\nRich in audio-video synchronization clues\r\nDiverse in categories","description_withheld":null,"homepage":"https://lzhangbj.github.io/projects/asva/asva.html","introduced_date":"2024-03-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/audio-synchronized-visual-animation","title":"Audio-Synchronized Visual Animation","first_author":"Lin Zhang","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Video Generation","url":"/task/video-generation","datasets_with_task":"/datasets/task/video-generation"},{"name":"Audio-Visual Synchronization","url":"/task/audio-visual-synchronization","datasets_with_task":"/datasets/task/audio-visual-synchronization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["AVSync15"],"data_loaders":[],"num_papers_in_archive":2,"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."}