@inproceedings{mallo-etal-2026-dream,
title = "{DREAM}: A Multicultural Multimodal Dataset Linking Dialogues and Realistic Image Sequences",
author = "Mallo, Juan and
Estecha-Garitagoitia, Marcos and
Cordoba, Ricardo and
D{'}Haro, Luis Fernando",
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-1.728/",
doi = "10.63317/2v7b4xhs2d5g",
pages = "9266--9281",
abstract = "An ongoing challenge in multimodal language research is creating and interpreting dialogues that preserve visual and cultural consistency across turns. We introduce DREAM (Dialogue to REAlistic Multicultural Image Sequences), a multicultural multimodal resource that ties dialogues grounded in explicit persona profiles to photorealistic, storyboard-like image sequences. Each of the 1,000 dialogues includes two rich persona profiles (structured traits plus descriptive language), two matching photorealistic portraits, and a collection of scene-level images depicting key dialogue moments. The pipeline integrates profile augmentation, culturally-sensitive prompt engineering, and turn selection to craft cohesive visual narratives, promoting character consistency across images. This is accomplished through a controlled generation process employing large language and image models. Beyond dialogue grounding, DREAM supports appearance-based demographic perception and culture-aware rendering: models can be evaluated on their ability to (i) perceive age, gender presentation, and broad ethnicity appearance clusters from profile portraits, and (ii) maintain these characteristics in dialogue scenes. We provide a unified JSON format integrating profiles, dialogue text, and visual turns, facilitating research on visually anchored dialogue understanding, consistency, and generation. A dual evaluation protocol combines human judgments (realism, coherence, consistency, and demographic perception) with automated portrait analysis via GPT-5. Ethical considerations, limitations, and recommended applications are discussed."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mallo-etal-2026-dream">
<titleInfo>
<title>DREAM: A Multicultural Multimodal Dataset Linking Dialogues and Realistic Image Sequences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Mallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Estecha-Garitagoitia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Cordoba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">Fernando</namePart>
<namePart type="family">D’Haro</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>An ongoing challenge in multimodal language research is creating and interpreting dialogues that preserve visual and cultural consistency across turns. We introduce DREAM (Dialogue to REAlistic Multicultural Image Sequences), a multicultural multimodal resource that ties dialogues grounded in explicit persona profiles to photorealistic, storyboard-like image sequences. Each of the 1,000 dialogues includes two rich persona profiles (structured traits plus descriptive language), two matching photorealistic portraits, and a collection of scene-level images depicting key dialogue moments. The pipeline integrates profile augmentation, culturally-sensitive prompt engineering, and turn selection to craft cohesive visual narratives, promoting character consistency across images. This is accomplished through a controlled generation process employing large language and image models. Beyond dialogue grounding, DREAM supports appearance-based demographic perception and culture-aware rendering: models can be evaluated on their ability to (i) perceive age, gender presentation, and broad ethnicity appearance clusters from profile portraits, and (ii) maintain these characteristics in dialogue scenes. We provide a unified JSON format integrating profiles, dialogue text, and visual turns, facilitating research on visually anchored dialogue understanding, consistency, and generation. A dual evaluation protocol combines human judgments (realism, coherence, consistency, and demographic perception) with automated portrait analysis via GPT-5. Ethical considerations, limitations, and recommended applications are discussed.</abstract>
<identifier type="citekey">mallo-etal-2026-dream</identifier>
<identifier type="doi">10.63317/2v7b4xhs2d5g</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.728/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>9266</start>
<end>9281</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DREAM: A Multicultural Multimodal Dataset Linking Dialogues and Realistic Image Sequences
%A Mallo, Juan
%A Estecha-Garitagoitia, Marcos
%A Cordoba, Ricardo
%A D’Haro, Luis Fernando
%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 mallo-etal-2026-dream
%X An ongoing challenge in multimodal language research is creating and interpreting dialogues that preserve visual and cultural consistency across turns. We introduce DREAM (Dialogue to REAlistic Multicultural Image Sequences), a multicultural multimodal resource that ties dialogues grounded in explicit persona profiles to photorealistic, storyboard-like image sequences. Each of the 1,000 dialogues includes two rich persona profiles (structured traits plus descriptive language), two matching photorealistic portraits, and a collection of scene-level images depicting key dialogue moments. The pipeline integrates profile augmentation, culturally-sensitive prompt engineering, and turn selection to craft cohesive visual narratives, promoting character consistency across images. This is accomplished through a controlled generation process employing large language and image models. Beyond dialogue grounding, DREAM supports appearance-based demographic perception and culture-aware rendering: models can be evaluated on their ability to (i) perceive age, gender presentation, and broad ethnicity appearance clusters from profile portraits, and (ii) maintain these characteristics in dialogue scenes. We provide a unified JSON format integrating profiles, dialogue text, and visual turns, facilitating research on visually anchored dialogue understanding, consistency, and generation. A dual evaluation protocol combines human judgments (realism, coherence, consistency, and demographic perception) with automated portrait analysis via GPT-5. Ethical considerations, limitations, and recommended applications are discussed.
%R 10.63317/2v7b4xhs2d5g
%U https://aclanthology.org/2026.lrec-1.728/
%U https://doi.org/10.63317/2v7b4xhs2d5g
%P 9266-9281
Markdown (Informal)
[DREAM: A Multicultural Multimodal Dataset Linking Dialogues and Realistic Image Sequences](https://aclanthology.org/2026.lrec-1.728/) (Mallo et al., LREC 2026)
ACL