{"url":"/dataset/stair-captions","name":"STAIR Captions","full_name":"STAIR Captions","description_markdown":"STAIR Captions is a large-scale dataset containing 820,310 Japanese captions.\r\nThis dataset can be used for caption generation, multimodal retrieval, and image generation.\r\n\r\nSource: [STAIR Captions](http://captions.stair.center/)","description_withheld":null,"homepage":"http://captions.stair.center/","introduced_date":"2017-05-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/stair-captions-constructing-a-large-scale","title":"STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset","first_author":"Yuya Yoshikawa","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Retrieval","url":"/task/image-retrieval","datasets_with_task":"/datasets/task/image-retrieval"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"}],"languages":[{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["STAIR Captions"],"data_loaders":[],"num_papers_in_archive":4,"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."}