{"url":"/dataset/svd","name":"SVD","full_name":"Short Video Dataset","description_markdown":"SVD is a large-scale short video dataset, which contains over 500,000 short videos collected from http://www.douyin.com and over 30,000 labeled pairs of near-duplicate videos.\r\n\r\nSource: [SVD: A Large-Scale Short Video Dataset for Near-Duplicate Video Retrieval](/paper/svd-a-large-scale-short-video-dataset-for)","description_withheld":null,"homepage":"https://svdbase.github.io/","introduced_date":"2019-10-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/svd-a-large-scale-short-video-dataset-for","title":"SVD: A Large-Scale Short Video Dataset for Near-Duplicate Video Retrieval","first_author":"Qing-Yuan Jiang","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[],"languages":[],"variants":["SVD"],"data_loaders":[{"repo":"https://github.com/koudounasalkis/AI4Voice","url":"https://github.com/koudounasalkis/AI4Voice","frameworks":["pytorch"]}],"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."}