@inproceedings{ghosh-etal-2026-computational,
title = "A Computational Approach to Visual Metonymy",
author = "Ghosh, Saptarshi and
Liu, Linfeng and
Jiang, Tianyu",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.92/",
pages = "2075--2099",
ISBN = "979-8-89176-380-7",
abstract = "Images often communicate more than they literally depict: a set of tools can suggest an occupation and a cultural artifact can suggest a tradition. This kind of indirect visual reference, known as visual metonymy, invites viewers to recover a target concept via associated cues rather than explicit depiction. In this work, we present the first computational investigation of visual metonymy. We introduce a novel pipeline grounded in semiotic theory that leverages large language models and text-to-image models to generate metonymic visual representations. Using this framework, we construct ViMET, the first visual metonymy dataset comprising 2,000 multiple-choice questions to evaluate the cognitive reasoning abilities in multimodal language models. Experimental results on our dataset reveal a significant gap between human performance (86.9{\%}) and state-of-the-art vision-language models (65.9{\%}), highlighting limitations in machines' ability to interpret indirect visual references. Our dataset is publicly available at: https://github.com/cincynlp/ViMET."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghosh-etal-2026-computational">
<titleInfo>
<title>A Computational Approach to Visual Metonymy</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saptarshi</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linfeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Images often communicate more than they literally depict: a set of tools can suggest an occupation and a cultural artifact can suggest a tradition. This kind of indirect visual reference, known as visual metonymy, invites viewers to recover a target concept via associated cues rather than explicit depiction. In this work, we present the first computational investigation of visual metonymy. We introduce a novel pipeline grounded in semiotic theory that leverages large language models and text-to-image models to generate metonymic visual representations. Using this framework, we construct ViMET, the first visual metonymy dataset comprising 2,000 multiple-choice questions to evaluate the cognitive reasoning abilities in multimodal language models. Experimental results on our dataset reveal a significant gap between human performance (86.9%) and state-of-the-art vision-language models (65.9%), highlighting limitations in machines’ ability to interpret indirect visual references. Our dataset is publicly available at: https://github.com/cincynlp/ViMET.</abstract>
<identifier type="citekey">ghosh-etal-2026-computational</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.92/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>2075</start>
<end>2099</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Computational Approach to Visual Metonymy
%A Ghosh, Saptarshi
%A Liu, Linfeng
%A Jiang, Tianyu
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F ghosh-etal-2026-computational
%X Images often communicate more than they literally depict: a set of tools can suggest an occupation and a cultural artifact can suggest a tradition. This kind of indirect visual reference, known as visual metonymy, invites viewers to recover a target concept via associated cues rather than explicit depiction. In this work, we present the first computational investigation of visual metonymy. We introduce a novel pipeline grounded in semiotic theory that leverages large language models and text-to-image models to generate metonymic visual representations. Using this framework, we construct ViMET, the first visual metonymy dataset comprising 2,000 multiple-choice questions to evaluate the cognitive reasoning abilities in multimodal language models. Experimental results on our dataset reveal a significant gap between human performance (86.9%) and state-of-the-art vision-language models (65.9%), highlighting limitations in machines’ ability to interpret indirect visual references. Our dataset is publicly available at: https://github.com/cincynlp/ViMET.
%U https://aclanthology.org/2026.eacl-long.92/
%P 2075-2099
Markdown (Informal)
[A Computational Approach to Visual Metonymy](https://aclanthology.org/2026.eacl-long.92/) (Ghosh et al., EACL 2026)
ACL
- Saptarshi Ghosh, Linfeng Liu, and Tianyu Jiang. 2026. A Computational Approach to Visual Metonymy. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2075–2099, Rabat, Morocco. Association for Computational Linguistics.