{"url":"/dataset/vpcd","name":"VPCD","full_name":"Video Person-Clustering","description_markdown":"**VPCD** contains multi-modal annotations (face, body and voice) for all primary and secondary characters from a range of diverse TV-shows and movies. It is used for evaluating multi-modal person-clustering. It contains body-tracks for each annotated character, face-tracks when visible, and voice-tracks when speaking, with their associated features.\r\n\r\nIt consists of more than 30,000 face and body tracks of 300+ characters, from over 23 hours of video.","description_withheld":null,"homepage":"https://www.robots.ox.ac.uk/~vgg/data/Video_Person_Clustering/","introduced_date":"2021-05-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/face-body-voice-video-person-clustering-with","title":"Face, Body, Voice: Video Person-Clustering with Multiple Modalities","first_author":"Andrew Brown","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Audio-Visual Active Speaker Detection","url":"/task/audio-visual-active-speaker-detection","datasets_with_task":"/datasets/task/audio-visual-active-speaker-detection"}],"languages":[],"variants":["VPCD"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/audio-visual-active-speaker-detection-on-vpcd","task":"Audio-Visual Active Speaker Detection","dataset_variant":"VPCD","rows":1,"metrics":["mean average precision"],"first_row_in_archive_order":{"model":"GSCMIA","paper":"/paper/audio-visual-activity-guided-cross-modal","metrics":{"mean average precision":"83.90"},"code_links":[{"title":"rash1993/movie-asd","url":"https://github.com/rash1993/movie-asd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/audio-visual-activity-guided-cross-modal","title":"Audio-Visual Activity Guided Cross-Modal Identity Association for Active Speaker Detection","date":"2022-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}