{"url":"/dataset/vtc","name":"VTC","full_name":"Videos, Titles and Comments","description_markdown":"VTC is a large-scale multimodal dataset containing video-caption pairs (~300k) alongside comments that can be used for multimodal representation learning.","description_withheld":null,"homepage":"https://unitaryai.github.io/vtc-paper/","introduced_date":"2022-10-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/vtc-improving-video-text-retrieval-with-user","title":"VTC: Improving Video-Text Retrieval with User Comments","first_author":"Laura Hanu","url":null},"license":{"name":"LICENSE-CC-BY-NC-SA","url":"https://github.com/unitaryai/VTC-dataset/blob/main/LICENSE-CC-BY-NC-SA"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Video Retrieval","url":"/task/video-retrieval","datasets_with_task":"/datasets/task/video-retrieval"},{"name":"Video Understanding","url":"/task/video-understanding","datasets_with_task":"/datasets/task/video-understanding"},{"name":"Video-Text Retrieval","url":"/task/video-text-retrieval","datasets_with_task":"/datasets/task/video-text-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VTC"],"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."}