{"url":"/dataset/vidsitu","name":"VidSitu","full_name":null,"description_markdown":"VidSitu is a dataset for the task of semantic role labeling in videos (VidSRL). It is a large-scale video understanding data source with 29K 10-second movie clips richly annotated with a verb and semantic-roles every 2 seconds. Entities are co-referenced across events within a movie clip and events are connected to each other via event-event relations. Clips in VidSitu are drawn from a large collection of movies (∼3K) and have been chosen to be both complex (∼4.2 unique verbs within a video) as well as diverse (∼200 verbs have more than 100 annotations each).","description_withheld":null,"homepage":"https://vidsitu.org/","introduced_date":"2021-04-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/visual-semantic-role-labeling-for-video","title":"Visual Semantic Role Labeling for Video Understanding","first_author":"Arka Sadhu","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Video Understanding","url":"/task/video-understanding","datasets_with_task":"/datasets/task/video-understanding"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VidSitu"],"data_loaders":[],"num_papers_in_archive":18,"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."}