{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/scicap-generating-captions-for-scientific","title":"SciCap: Generating Captions for Scientific Figures","arxiv_id":"2110.11624","date":"2021-10-22","proceeding":"Findings (EMNLP) 2021 11","authors":["Ting-Yao Hsu","C. Lee Giles","Ting-Hao 'Kenneth' Huang"],"abstract":"Researchers use figures to communicate rich, complex information in scientific papers. The captions of these figures are critical to conveying effective messages. However, low-quality figure captions commonly occur in scientific articles and may decrease understanding. In this paper, we propose an end-to-end neural framework to automatically generate informative, high-quality captions for scientific figures. To this end, we introduce SCICAP, a large-scale figure-caption dataset based on computer science arXiv papers published between 2010 and 2020. After pre-processing - including figure-type classification, sub-figure identification, text normalization, and caption text selection - SCICAP contained more than two million figures extracted from over 290,000 papers. We then established baseline models that caption graph plots, the dominant (19.2%) figure type. The experimental results showed both opportunities and steep challenges of generating captions for scientific figures.","url_abs":"https://arxiv.org/abs/2110.11624v2","url_pdf":"https://arxiv.org/pdf/2110.11624v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"scicap-generating-captions-for-scientific","repo_url":"https://github.com/tingyaohsu/scicap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"text-normalization","task_name":"Text Normalization"}],"methods":[],"datasets_introduced":[{"slug":"scicap","name":"SCICAP","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-captioning-on-scicap","task":"Image Captioning","dataset":"SCICAP","model":"CNN+LSTM (Vision only, First sentence)","rank_in_archive_order":1,"of":9,"metrics":{"BLEU-4":"0.0219"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-scicap","task":"Image Captioning","dataset":"SCICAP","model":"CNN+LSTM (Text only, First sentence)","rank_in_archive_order":2,"of":9,"metrics":{"BLEU-4":"0.0213"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-scicap","task":"Image Captioning","dataset":"SCICAP","model":"CNN+LSTM (Text only, Single-Sent Caption)","rank_in_archive_order":3,"of":9,"metrics":{"BLEU-4":"0.0212"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-scicap","task":"Image Captioning","dataset":"SCICAP","model":"CNN+LSTM (Vision only, Single-Sent Caption)","rank_in_archive_order":4,"of":9,"metrics":{"BLEU-4":"0.0207"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-scicap","task":"Image Captioning","dataset":"SCICAP","model":"CNN+LSTM (Vision + Text, First sentence)","rank_in_archive_order":5,"of":9,"metrics":{"BLEU-4":"0.0205"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-scicap","task":"Image Captioning","dataset":"SCICAP","model":"CNN+LSTM (Vision + Text, Single-Sent Caption)","rank_in_archive_order":6,"of":9,"metrics":{"BLEU-4":"0.0202"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-scicap","task":"Image Captioning","dataset":"SCICAP","model":"CNN+LSTM (Vision only, Caption w/ <=100 words)","rank_in_archive_order":7,"of":9,"metrics":{"BLEU-4":"0.0172"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-scicap","task":"Image Captioning","dataset":"SCICAP","model":"CNN+LSTM (Vision + Text, Caption w/ <=100 words)","rank_in_archive_order":8,"of":9,"metrics":{"BLEU-4":"0.0168"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-scicap","task":"Image Captioning","dataset":"SCICAP","model":"CNN+LSTM (Text only, Caption w/ <=100 words)","rank_in_archive_order":9,"of":9,"metrics":{"BLEU-4":"0.0165"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.11624","atlas_url":"https://app.syntology.ai/?focus=2110.11624","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2110.11624"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.11624\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.11624"},"call":"get_concepts_for_paper(arxiv_id=\"2110.11624\")"}],"by_repo":[{"repo":"tingyaohsu/scicap","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0ec14af95cfea87ee4417f8510070873c9f75f333ddd285595b43a95ae125c84","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}