@inproceedings{blaga-etal-2026-entity,
title = "Entity Image and Mixed-Modal Image Retrieval Datasets",
author = "Blaga, Cristian-Ioan and
G C, Paul Suganthan and
Dua, Sahil and
Srinivasan, Krishna and
Alfonseca, Enrique and
Dornbach, Peter and
Duerig, Tom and
Zitouni, Imed and
Dong, Zhe",
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-1.734/",
doi = "10.63317/2fnaa4f79qa5",
pages = "9349--9357",
abstract = "Despite advances in multimodal learning, challenging benchmarks for mixed-modal image retrieval that combines visual and textual information are lacking. This paper introduces a novel benchmark to rigorously evaluate image retrieval that demands deep cross-modal contextual understanding. We present two new datasets: the Entity Image Dataset (EI), providing canonical images for Wikipedia entities, and the Mixed-Modal Image Retrieval Dataset (MMIR), derived from the WIT dataset. The MMIR benchmark features two challenging query types requiring models to ground textual descriptions in the context of provided visual entities: single entity-image queries (one entity image with descriptive text) and multi-entity-image queries (multiple entity images with relational text). We empirically validate the benchmark{'}s utility as both a training corpus and an evaluation set for mixed-modal retrieval. The quality of both datasets is further affirmed through crowd-sourced human annotations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="blaga-etal-2026-entity">
<titleInfo>
<title>Entity Image and Mixed-Modal Image Retrieval Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cristian-Ioan</namePart>
<namePart type="family">Blaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="given">Suganthan</namePart>
<namePart type="family">G C</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahil</namePart>
<namePart type="family">Dua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krishna</namePart>
<namePart type="family">Srinivasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Alfonseca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Dornbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Duerig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Dong</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>Despite advances in multimodal learning, challenging benchmarks for mixed-modal image retrieval that combines visual and textual information are lacking. This paper introduces a novel benchmark to rigorously evaluate image retrieval that demands deep cross-modal contextual understanding. We present two new datasets: the Entity Image Dataset (EI), providing canonical images for Wikipedia entities, and the Mixed-Modal Image Retrieval Dataset (MMIR), derived from the WIT dataset. The MMIR benchmark features two challenging query types requiring models to ground textual descriptions in the context of provided visual entities: single entity-image queries (one entity image with descriptive text) and multi-entity-image queries (multiple entity images with relational text). We empirically validate the benchmark’s utility as both a training corpus and an evaluation set for mixed-modal retrieval. The quality of both datasets is further affirmed through crowd-sourced human annotations.</abstract>
<identifier type="citekey">blaga-etal-2026-entity</identifier>
<identifier type="doi">10.63317/2fnaa4f79qa5</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.734/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>9349</start>
<end>9357</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity Image and Mixed-Modal Image Retrieval Datasets
%A Blaga, Cristian-Ioan
%A G C, Paul Suganthan
%A Dua, Sahil
%A Srinivasan, Krishna
%A Alfonseca, Enrique
%A Dornbach, Peter
%A Duerig, Tom
%A Zitouni, Imed
%A Dong, Zhe
%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 blaga-etal-2026-entity
%X Despite advances in multimodal learning, challenging benchmarks for mixed-modal image retrieval that combines visual and textual information are lacking. This paper introduces a novel benchmark to rigorously evaluate image retrieval that demands deep cross-modal contextual understanding. We present two new datasets: the Entity Image Dataset (EI), providing canonical images for Wikipedia entities, and the Mixed-Modal Image Retrieval Dataset (MMIR), derived from the WIT dataset. The MMIR benchmark features two challenging query types requiring models to ground textual descriptions in the context of provided visual entities: single entity-image queries (one entity image with descriptive text) and multi-entity-image queries (multiple entity images with relational text). We empirically validate the benchmark’s utility as both a training corpus and an evaluation set for mixed-modal retrieval. The quality of both datasets is further affirmed through crowd-sourced human annotations.
%R 10.63317/2fnaa4f79qa5
%U https://aclanthology.org/2026.lrec-1.734/
%U https://doi.org/10.63317/2fnaa4f79qa5
%P 9349-9357
Markdown (Informal)
[Entity Image and Mixed-Modal Image Retrieval Datasets](https://aclanthology.org/2026.lrec-1.734/) (Blaga et al., LREC 2026)
ACL
- Cristian-Ioan Blaga, Paul Suganthan G C, Sahil Dua, Krishna Srinivasan, Enrique Alfonseca, Peter Dornbach, Tom Duerig, Imed Zitouni, and Zhe Dong. 2026. Entity Image and Mixed-Modal Image Retrieval Datasets. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 9349–9357, Palma de Mallorca, Spain. ELRA Language Resource Association.