{"url":"/dataset/celebv-text","name":"CelebV-Text","full_name":null,"description_markdown":"**CelebV-Text** comprises 70,000 in-the-wild face video clips with diverse visual content, each paired with 20 texts generated using the proposed semi-automatic text generation strategy. The provided texts describes both static and dynamic attributes precisely.\r\n\r\nSource: [CelebV-Text: A Large-Scale Facial Text-Video Dataset](https://arxiv.org/pdf/2303.14717v1.pdf)\r\n\r\nImage Source: [CelebV-Text: A Large-Scale Facial Text-Video Dataset](https://arxiv.org/pdf/2303.14717v1.pdf)","description_withheld":null,"homepage":"https://celebv-text.github.io","introduced_date":"2023-03-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/celebv-text-a-large-scale-facial-text-video","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","first_author":"Jianhui Yu","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Video Generation","url":"/task/video-generation","datasets_with_task":"/datasets/task/video-generation"},{"name":"Text-to-Video Generation","url":"/task/text-to-video-generation","datasets_with_task":"/datasets/task/text-to-video-generation"}],"languages":[],"variants":["CelebV-Text"],"data_loaders":[],"num_papers_in_archive":15,"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."}