{"url":"/dataset/stair-actions-captions","name":"STAIR Actions Captions","full_name":null,"description_markdown":"A large-scale Japanese video caption dataset consisting of 79,822 videos and 399,233 captions. Each caption in the dataset describes a video in the form of \"who does what and where.\"\r\n\r\nSource: [Video Caption Dataset for Describing Human Actions in Japanese](/paper/video-caption-dataset-for-describing-human)","description_withheld":null,"homepage":"https://actions.stair.center/captions.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/video-caption-dataset-for-describing-human","title":"Video Caption Dataset for Describing Human Actions in Japanese","first_author":"Yutaro Shigeto","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["STAIR Actions Captions"],"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."}