{"url":"/dataset/scicap","name":"SCICAP","full_name":null,"description_markdown":"SCICAP is a large-scale image captioning dataset that contains real-world scientific figures and captions. SCICAP was constructed using more than two million images from over 290,000 papers collected and released by arXiv.\r\n\r\nImage source: [https://arxiv.org/pdf/2110.11624v1.pdf](https://arxiv.org/pdf/2110.11624v1.pdf)","description_withheld":null,"homepage":"https://github.com/tingyaohsu/SciCap","introduced_date":"2021-10-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/scicap-generating-captions-for-scientific","title":"SciCap: Generating Captions for Scientific Figures","first_author":"Ting-Yao Hsu","url":null},"license":{"name":"CC0 1.0","url":"https://creativecommons.org/publicdomain/zero/1.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SCICAP"],"data_loaders":[{"repo":"https://github.com/tingyaohsu/scicap","url":"https://github.com/tingyaohsu/scicap","frameworks":[]}],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-captioning-on-scicap","task":"Image Captioning","dataset_variant":"SCICAP","rows":9,"metrics":["BLEU-4"],"first_row_in_archive_order":{"model":"CNN+LSTM (Vision only, First sentence)","paper":"/paper/scicap-generating-captions-for-scientific","metrics":{"BLEU-4":"0.0219"},"code_links":[{"title":"tingyaohsu/scicap","url":"https://github.com/tingyaohsu/scicap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/scicap-generating-captions-for-scientific","title":"SciCap: Generating Captions for Scientific Figures","date":"2021-10-22","rows_on_this_dataset":9,"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."}