{"url":"/dataset/ptvd","name":"PTVD","full_name":null,"description_markdown":"**PTVD** is a plot-oriented multimodal dataset in the TV domain. It is also the first non-English dataset of its kind. Additionally, PTVD contains more than 26 million bullet screen comments (BSCs), powering large-scale pre-training.","description_withheld":null,"homepage":"https://ptvd.github.io/#","introduced_date":"2023-06-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/ptvd-a-large-scale-plot-oriented-multimodal","title":"PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas","first_author":"Chen Li","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"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":"Retrieval","url":"/task/retrieval","datasets_with_task":"/datasets/task/retrieval"},{"name":"Genre classification","url":"/task/genre-classification","datasets_with_task":"/datasets/task/genre-classification"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["PTVD"],"data_loaders":[],"num_papers_in_archive":1,"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."}