{"url":"/dataset/tvc","name":"TVC","full_name":"TV show Captions","description_markdown":"TV show Caption is a large-scale multimodal captioning dataset, containing 261,490 caption descriptions paired with 108,965 short video moments. **TVC** is unique as its captions may also describe dialogues/subtitles while the captions in the other datasets are only describing the visual content.\n\nSource: [https://tvr.cs.unc.edu/tvc.html](https://tvr.cs.unc.edu/tvc.html)\nImage Source: [https://github.com/jayleicn/TVCaption](https://github.com/jayleicn/TVCaption)","description_withheld":null,"homepage":"https://tvr.cs.unc.edu/tvc.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/tvr-a-large-scale-dataset-for-video-subtitle","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","first_author":"Jie Lei","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Video Retrieval","url":"/task/video-retrieval","datasets_with_task":"/datasets/task/video-retrieval"},{"name":"Video Captioning","url":"/task/video-captioning","datasets_with_task":"/datasets/task/video-captioning"},{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","datasets_with_task":"/datasets/task/self-supervised-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TVC"],"data_loaders":[],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-captioning-on-tvc","task":"Video Captioning","dataset_variant":"TVC","rows":2,"metrics":["BLEU-4","CIDEr"],"first_row_in_archive_order":{"model":"VAST","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","metrics":{"BLEU-4":"19.9","CIDEr":"74.1"},"code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/cosa-concatenated-sample-pretrained-vision","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","date":"2023-06-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":42,"samples_ran":15,"samples_unverified":27,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":1,"samples_harvested":42,"samples_ran":15,"samples_unverified":27,"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."}