@inproceedings{chen-etal-2026-munichus,
title = "{MUNIC}hus: {MU}ltilingual News Image Captioning Benchmark",
author = "Chen, Yuji and
Plum, Alistair and
Hettiarachchi, Hansi and
Kanojia, Diptesh and
Basnet, Saroj and
Zampieri, Marcos and
Ranasinghe, Tharindu",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.708/",
doi = "10.63317/3cu2uxnphh3g",
pages = "9008--9017",
abstract = "The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and visual elements. The majority of research on news image captioning focuses on English, primarily because datasets in other languages are scarce. To address this limitation, we release the first multilingual news image captioning benchmark, MUNIChus, comprising 9 languages, including several low-resource languages such as Sinhala and Urdu. We evaluate various state-of-the-art neural news image captioning models on MUNIChus and find that news image captioning remains challenging. We also make MUNIChus publicly available as a public leaderboard with over 20 models already benchmarked. We hope that MUNIChus will enable further advancements in developing and evaluating multilingual news image captioning models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-munichus">
<titleInfo>
<title>MUNIChus: MUltilingual News Image Captioning Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diptesh</namePart>
<namePart type="family">Kanojia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saroj</namePart>
<namePart type="family">Basnet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and visual elements. The majority of research on news image captioning focuses on English, primarily because datasets in other languages are scarce. To address this limitation, we release the first multilingual news image captioning benchmark, MUNIChus, comprising 9 languages, including several low-resource languages such as Sinhala and Urdu. We evaluate various state-of-the-art neural news image captioning models on MUNIChus and find that news image captioning remains challenging. We also make MUNIChus publicly available as a public leaderboard with over 20 models already benchmarked. We hope that MUNIChus will enable further advancements in developing and evaluating multilingual news image captioning models.</abstract>
<identifier type="citekey">chen-etal-2026-munichus</identifier>
<identifier type="doi">10.63317/3cu2uxnphh3g</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.708/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>9008</start>
<end>9017</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MUNIChus: MUltilingual News Image Captioning Benchmark
%A Chen, Yuji
%A Plum, Alistair
%A Hettiarachchi, Hansi
%A Kanojia, Diptesh
%A Basnet, Saroj
%A Zampieri, Marcos
%A Ranasinghe, Tharindu
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F chen-etal-2026-munichus
%X The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and visual elements. The majority of research on news image captioning focuses on English, primarily because datasets in other languages are scarce. To address this limitation, we release the first multilingual news image captioning benchmark, MUNIChus, comprising 9 languages, including several low-resource languages such as Sinhala and Urdu. We evaluate various state-of-the-art neural news image captioning models on MUNIChus and find that news image captioning remains challenging. We also make MUNIChus publicly available as a public leaderboard with over 20 models already benchmarked. We hope that MUNIChus will enable further advancements in developing and evaluating multilingual news image captioning models.
%R 10.63317/3cu2uxnphh3g
%U https://aclanthology.org/2026.lrec-1.708/
%U https://doi.org/10.63317/3cu2uxnphh3g
%P 9008-9017
Markdown (Informal)
[MUNIChus: MUltilingual News Image Captioning Benchmark](https://aclanthology.org/2026.lrec-1.708/) (Chen et al., LREC 2026)
ACL
- Yuji Chen, Alistair Plum, Hansi Hettiarachchi, Diptesh Kanojia, Saroj Basnet, Marcos Zampieri, and Tharindu Ranasinghe. 2026. MUNIChus: MUltilingual News Image Captioning Benchmark. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 9008–9017, Palma de Mallorca, Spain. ELRA Language Resource Association.