The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
SciCap: Generating Captions for Scientific Figures
Open accessAbstract
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, 1 a largescale 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Research has explored methods to automate alt text creation, but has yielded mixed results [30, 52, 81, 85].”
From How University Disability Services Professionals Write Image Descriptions for HCI Figures Using Generative AI (2026) · cites this paper as [30]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061
Loper, E., & Bird, S. (2002) · doi:10.3115/1118108.1118117 · Cited by 3,323
SciBERT: A Pretrained Language Model for Scientific Text
Beltagy, I., Lo, K., & Cohan, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1371 · Cited by 3,218
NLTK: The Natural Language ToolkitPreprint
Loper, E., & Bird, S. (2002) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/0205028 · Cited by 1,893
FigureQA: An Annotated Figure Dataset for Visual ReasoningPreprint
Kahou, S. E., Michalski, V., Atkinson, A., Kádár, Á., Trischler, A., & Bengio, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.07300 · Cited by 420
Flagged first, then by citations
Research works printed but not linked: 4
- Iz Beltagy, Kyle Lo, and Arman Cohan. 2019. Scib- ert: Pretrained language model for scientific text. In EMNLP.
- Christopher Clark and Santosh Divvala. 2016. Pdf- figures 2.0: Mining figures from research papers. In 2016 IEEE/ACM Joint Conference on Digital Li- braries (JCDL), pages 143-152. IEEE.
- Saiganesh Swaminathan, Thijs Roumen, Robert Ko- vacs, David Stangl, Stefanie Mueller, and Patrick Baudisch. 2016. Linespace: A sensemaking plat- form for the blind. In Proceedings of the 2016 CHI Conference on Human Factors in Computing Sys- tems, pages 2175-2185. ACM.
- Shaomei Wu, Jeffrey Wieland, Omid Farivar, and Julie Schiller. 2017. Automatic alt-text: Computer- generated image descriptions for blind users on a so- cial network service. In Proceedings of the 2017 ACM Conference on Computer Supported Coopera- tive Work and Social Computing, pages 1180-1192. ACM.
Cited by
Sorted by citations
Knowledge-integrated machine learning for materials: lessons from gameplaying and robotics
Hippalgaonkar, K., Li, Q., Wang, X., Fisher, J. S., Kirkpatrick, J., & Buonassisi, T. (2023) · Nature Reviews Materials · doi:10.1038/s41578-022-00513-1 · Cited by 156
Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
Kantharaj, S., Leong, R. T. K., Lin, X., Masry, A., Thakkar, M., Hoque, E., & Joty, S. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.277 · Cited by 200
Artificial intelligence for science in quantum, atomistic, and continuum systems
Zhang, X., Wang, L., Helwig, J., Luo, Y., Fu, C., Xie, Y., Liu, M., Lin, Y., Zhao, X., Yan, K., et al. (2025) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000115 · Cited by 214
Generating Image Captions Using Bahdanau Attention Mechanism and Transfer Learning
Ayoub, S., Gulzar, Y., Reegu, F. A., & Turaev, S. (2022) · Symmetry · doi:10.3390/sym14122681 · Cited by 69
Kunlamai, T., Yamane, T., Suganuma, M., Chun, P., & Okatani, T. (2023) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13086 · Cited by 61
Metadata
- Authors
- Hsu, T.-Y., Giles, C. L., & Huang, T.-H.
- Affiliations
- Pennsylvania State University (US)
- Venue
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Published
- 2021
- Pages
- 3258-3264
- OpenAlex
- W3210140424
- Cited by
- 59
- References
- 33
- Citations by year
- 2026: 11 · 2025: 13 · 2024: 7 · 2023: 18 · 2022: 9 · 2021: 1
- FWCI
- 2.86
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Strong
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques
- Keywords
- automatic caption generation, scientific figures, figure captions, text normalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
