Papers › SciCap: Generating Captions for Scientific Figures

SciCap: Generating Captions for Scientific Figures

22 Oct 2021Findings (EMNLP) 2021 11arXiv:2110.11624archive 2025-07-28

Ting-Yao Hsu, C. Lee Giles, Ting-Hao 'Kenneth' Huang

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tingyaohsu/scicap officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ArticlesImage CaptioningText Normalization

Datasets

Introduced by this paper, per the archive.

SCICAP

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Captioning SCICAP CNN+LSTM (Vision only, First sentence) BLEU-4 0.0219 #1 of 9 Archive leaderboard report
Image Captioning SCICAP CNN+LSTM (Text only, First sentence) BLEU-4 0.0213 #2 of 9 Archive leaderboard report
Image Captioning SCICAP CNN+LSTM (Text only, Single-Sent Caption) BLEU-4 0.0212 #3 of 9 Archive leaderboard report
Image Captioning SCICAP CNN+LSTM (Vision only, Single-Sent Caption) BLEU-4 0.0207 #4 of 9 Archive leaderboard report
Image Captioning SCICAP CNN+LSTM (Vision + Text, First sentence) BLEU-4 0.0205 #5 of 9 Archive leaderboard report
Image Captioning SCICAP CNN+LSTM (Vision + Text, Single-Sent Caption) BLEU-4 0.0202 #6 of 9 Archive leaderboard report
Image Captioning SCICAP CNN+LSTM (Vision only, Caption w/ <=100 words) BLEU-4 0.0172 #7 of 9 Archive leaderboard report
Image Captioning SCICAP CNN+LSTM (Vision + Text, Caption w/ <=100 words) BLEU-4 0.0168 #8 of 9 Archive leaderboard report
Image Captioning SCICAP CNN+LSTM (Text only, Caption w/ <=100 words) BLEU-4 0.0165 #9 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections