FigEx: Aligned Extraction of Scientific Figures and Captions

Jifeng Song; Arun Das; Ge Cui; Yufei Huang

doi:10.18653/v1/2025.findings-emnlp.899

FigEx: Aligned Extraction of Scientific Figures and Captions

Jifeng Song, Arun Das, Ge Cui, Yufei Huang

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Automatic understanding of figures in scientific papers is challenging since they often contain subfigures and subcaptions in complex layouts. In this paper, we propose FigEx, a vision-language model to extract aligned pairs of subfigures and subcaptions from scientific papers. We also release BioSci-Fig, a curated dataset of 7,174 compound figures with annotated subfigure bounding boxes and aligned subcaptions. On BioSci-Fig, FigEx improves subfigure detection AP^b over Grounding DINO by 0.023 and boosts caption separation BLEU over Llama-2-13B by 0.465. The source code is available at: https://github.com/Huang-AI4Medicine-Lab/FigEx.

Anthology ID:: 2025.findings-emnlp.899
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2025
Month:: November
Year:: 2025
Address:: Suzhou, China
Editors:: Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 16558–16571
Language:
URL:: https://aclanthology.org/2025.findings-emnlp.899/
DOI:: 10.18653/v1/2025.findings-emnlp.899
Bibkey:
Cite (ACL):: Jifeng Song, Arun Das, Ge Cui, and Yufei Huang. 2025. FigEx: Aligned Extraction of Scientific Figures and Captions. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 16558–16571, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):: FigEx: Aligned Extraction of Scientific Figures and Captions (Song et al., Findings 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.findings-emnlp.899.pdf
Checklist:: 2025.findings-emnlp.899.checklist.pdf

PDF Cite Search Checklist Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{song-etal-2025-figex,
    title = "{F}ig{E}x: Aligned Extraction of Scientific Figures and Captions",
    author = "Song, Jifeng  and
      Das, Arun  and
      Cui, Ge  and
      Huang, Yufei",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.899/",
    doi = "10.18653/v1/2025.findings-emnlp.899",
    pages = "16558--16571",
    ISBN = "979-8-89176-335-7",
    abstract = "Automatic understanding of figures in scientific papers is challenging since they often contain subfigures and subcaptions in complex layouts. In this paper, we propose FigEx, a vision-language model to extract aligned pairs of subfigures and subcaptions from scientific papers. We also release BioSci-Fig, a curated dataset of 7,174 compound figures with annotated subfigure bounding boxes and aligned subcaptions. On BioSci-Fig, FigEx improves subfigure detection $AP^b$ over Grounding DINO by 0.023 and boosts caption separation BLEU over Llama-2-13B by 0.465. The source code is available at: https://github.com/Huang-AI4Medicine-Lab/FigEx."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2025-figex">
    <titleInfo>
        <title>FigEx: Aligned Extraction of Scientific Figures and Captions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jifeng</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arun</namePart>
        <namePart type="family">Das</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ge</namePart>
        <namePart type="family">Cui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yufei</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>Automatic understanding of figures in scientific papers is challenging since they often contain subfigures and subcaptions in complex layouts. In this paper, we propose FigEx, a vision-language model to extract aligned pairs of subfigures and subcaptions from scientific papers. We also release BioSci-Fig, a curated dataset of 7,174 compound figures with annotated subfigure bounding boxes and aligned subcaptions. On BioSci-Fig, FigEx improves subfigure detection AP^b over Grounding DINO by 0.023 and boosts caption separation BLEU over Llama-2-13B by 0.465. The source code is available at: https://github.com/Huang-AI4Medicine-Lab/FigEx.</abstract>
    <identifier type="citekey">song-etal-2025-figex</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-emnlp.899</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.899/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>16558</start>
            <end>16571</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T FigEx: Aligned Extraction of Scientific Figures and Captions
%A Song, Jifeng
%A Das, Arun
%A Cui, Ge
%A Huang, Yufei
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F song-etal-2025-figex
%X Automatic understanding of figures in scientific papers is challenging since they often contain subfigures and subcaptions in complex layouts. In this paper, we propose FigEx, a vision-language model to extract aligned pairs of subfigures and subcaptions from scientific papers. We also release BioSci-Fig, a curated dataset of 7,174 compound figures with annotated subfigure bounding boxes and aligned subcaptions. On BioSci-Fig, FigEx improves subfigure detection AP^b over Grounding DINO by 0.023 and boosts caption separation BLEU over Llama-2-13B by 0.465. The source code is available at: https://github.com/Huang-AI4Medicine-Lab/FigEx.
%R 10.18653/v1/2025.findings-emnlp.899
%U https://aclanthology.org/2025.findings-emnlp.899/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.899
%P 16558-16571

Download as File

Markdown (Informal)

[FigEx: Aligned Extraction of Scientific Figures and Captions](https://aclanthology.org/2025.findings-emnlp.899/) (Song et al., Findings 2025)

FigEx: Aligned Extraction of Scientific Figures and Captions (Song et al., Findings 2025)

ACL

Jifeng Song, Arun Das, Ge Cui, and Yufei Huang. 2025. FigEx: Aligned Extraction of Scientific Figures and Captions. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 16558–16571, Suzhou, China. Association for Computational Linguistics.