{"url":"/dataset/acav100m","name":"ACAV100M","full_name":"Automatically Curated Audio-Visual","description_markdown":"ACAV100M processes 140 million full-length videos (total duration 1,030 years) which are used to produce a dataset of 100 million 10-second clips (31 years) with high audio-visual correspondence. This is two orders of magnitude larger than the current largest video dataset used in the audio-visual learning literature, i.e., AudioSet (8 months), and twice as large as the largest video dataset in the literature, i.e., HowTo100M (15 years).","description_withheld":null,"homepage":"https://acav100m.github.io/","introduced_date":"2021-01-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/automatic-curation-of-large-scale-datasets","title":"ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning","first_author":"Sangho Lee","url":null},"license":{"name":"MIT License","url":"https://github.com/sangho-vision/acav100m/blob/master/LICENSE"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","datasets_with_task":"/datasets/task/self-supervised-learning"}],"languages":[],"variants":["ACAV100M"],"data_loaders":[{"repo":"https://github.com/sangho-vision/acav100m","url":"https://github.com/sangho-vision/acav100m","frameworks":[]}],"num_papers_in_archive":7,"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."}