@inproceedings{xiong-etal-2026-progressive,
title = "Progressive Visual Refinement for Multi-modal Summarization",
author = "Xiong, Ye and
Kamigaito, Hidetaka and
Murakami, Soichiro and
Zhang, Peinan and
Takamura, Hiroya and
Okumura, Manabu",
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 2: Short Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-short.5/",
pages = "93--104",
ISBN = "979-8-89176-381-4",
abstract = "Multi-modal summarization (MMS) has emerged as a critical research area driven by the proliferation of multimedia content, focusing on generating condensed summaries by cross-modal complementary information synthesis. Previous studies have demonstrated the effectiveness of heterogeneous fusion paradigms, particularly through visual-centric feature extraction mechanisms, in constructing cross-modal representations that yield substantial performance gains. Nevertheless, the comprehensive utilization of multimodal information along with the intricate interdependencies among textual content, visual elements, and the summary generation process has been still insufficiently explored. We propose the Patch-Refined Visual Information Network (PRVIN) to address the insufficient exploitation of visual information. The essential patch selector and patch refiner components in PRVIN work collaboratively to progressively identify and refine critical visual features. An additional vision-to-summary alignment mechanism is also introduced to enhance the semantic connections between multi-modal representations and summary outputs. Extensive experiments conducted on two public MMS benchmark datasets demonstrate the superiority of PRVIN while quantitatively validating the crucial role of comprehensive visual information utilization in MMS tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiong-etal-2026-progressive">
<titleInfo>
<title>Progressive Visual Refinement for Multi-modal Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soichiro</namePart>
<namePart type="family">Murakami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peinan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manabu</namePart>
<namePart type="family">Okumura</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 2: Short 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">979-8-89176-381-4</identifier>
</relatedItem>
<abstract>Multi-modal summarization (MMS) has emerged as a critical research area driven by the proliferation of multimedia content, focusing on generating condensed summaries by cross-modal complementary information synthesis. Previous studies have demonstrated the effectiveness of heterogeneous fusion paradigms, particularly through visual-centric feature extraction mechanisms, in constructing cross-modal representations that yield substantial performance gains. Nevertheless, the comprehensive utilization of multimodal information along with the intricate interdependencies among textual content, visual elements, and the summary generation process has been still insufficiently explored. We propose the Patch-Refined Visual Information Network (PRVIN) to address the insufficient exploitation of visual information. The essential patch selector and patch refiner components in PRVIN work collaboratively to progressively identify and refine critical visual features. An additional vision-to-summary alignment mechanism is also introduced to enhance the semantic connections between multi-modal representations and summary outputs. Extensive experiments conducted on two public MMS benchmark datasets demonstrate the superiority of PRVIN while quantitatively validating the crucial role of comprehensive visual information utilization in MMS tasks.</abstract>
<identifier type="citekey">xiong-etal-2026-progressive</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-short.5/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>93</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Progressive Visual Refinement for Multi-modal Summarization
%A Xiong, Ye
%A Kamigaito, Hidetaka
%A Murakami, Soichiro
%A Zhang, Peinan
%A Takamura, Hiroya
%A Okumura, Manabu
%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 2: Short Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-381-4
%F xiong-etal-2026-progressive
%X Multi-modal summarization (MMS) has emerged as a critical research area driven by the proliferation of multimedia content, focusing on generating condensed summaries by cross-modal complementary information synthesis. Previous studies have demonstrated the effectiveness of heterogeneous fusion paradigms, particularly through visual-centric feature extraction mechanisms, in constructing cross-modal representations that yield substantial performance gains. Nevertheless, the comprehensive utilization of multimodal information along with the intricate interdependencies among textual content, visual elements, and the summary generation process has been still insufficiently explored. We propose the Patch-Refined Visual Information Network (PRVIN) to address the insufficient exploitation of visual information. The essential patch selector and patch refiner components in PRVIN work collaboratively to progressively identify and refine critical visual features. An additional vision-to-summary alignment mechanism is also introduced to enhance the semantic connections between multi-modal representations and summary outputs. Extensive experiments conducted on two public MMS benchmark datasets demonstrate the superiority of PRVIN while quantitatively validating the crucial role of comprehensive visual information utilization in MMS tasks.
%U https://aclanthology.org/2026.eacl-short.5/
%P 93-104
Markdown (Informal)
[Progressive Visual Refinement for Multi-modal Summarization](https://aclanthology.org/2026.eacl-short.5/) (Xiong et al., EACL 2026)
ACL
- Ye Xiong, Hidetaka Kamigaito, Soichiro Murakami, Peinan Zhang, Hiroya Takamura, and Manabu Okumura. 2026. Progressive Visual Refinement for Multi-modal Summarization. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 93–104, Rabat, Morocco. Association for Computational Linguistics.