@inproceedings{li-etal-2025-change,
title = "Change Entity-guided Heterogeneous Representation Disentangling for Change Captioning",
author = "Li, Yi and
Tu, Yunbin and
Li, Liang and
Su, Li and
Huang, Qingming",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.876/",
doi = "10.18653/v1/2025.findings-acl.876",
pages = "17050--17060",
ISBN = "979-8-89176-256-5",
abstract = "Change captioning aims to describe differences between a pair of images using natural language. However, learning effective difference representations is highly challenging due to distractors such as illumination and viewpoint changes. To address this, we propose a change-entity-guided disentanglement network that explicitly learns difference representations while mitigating the impact of distractors. Specifically, we first design a change entity retrieval module to identify key objects involved in the change from a textual perspective. Then, we introduce a difference representation enhancement module that strengthens the learned features, disentangling genuine differences from background variations. To further refine the generation process, we incorporate a gated Transformer decoder, which dynamically integrates both visual difference and textual change-entity information. Extensive experiments on CLEVR-Change, CLEVR-DC and Spot-the-Diff datasets demonstrate that our method outperforms existing approaches, achieving state-of-the-art performance. The code is available at https://github.com/yili-19/CHEER"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-change">
<titleInfo>
<title>Change Entity-guided Heterogeneous Representation Disentangling for Change Captioning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunbin</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingming</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Change captioning aims to describe differences between a pair of images using natural language. However, learning effective difference representations is highly challenging due to distractors such as illumination and viewpoint changes. To address this, we propose a change-entity-guided disentanglement network that explicitly learns difference representations while mitigating the impact of distractors. Specifically, we first design a change entity retrieval module to identify key objects involved in the change from a textual perspective. Then, we introduce a difference representation enhancement module that strengthens the learned features, disentangling genuine differences from background variations. To further refine the generation process, we incorporate a gated Transformer decoder, which dynamically integrates both visual difference and textual change-entity information. Extensive experiments on CLEVR-Change, CLEVR-DC and Spot-the-Diff datasets demonstrate that our method outperforms existing approaches, achieving state-of-the-art performance. The code is available at https://github.com/yili-19/CHEER</abstract>
<identifier type="citekey">li-etal-2025-change</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.876</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.876/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>17050</start>
<end>17060</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Change Entity-guided Heterogeneous Representation Disentangling for Change Captioning
%A Li, Yi
%A Tu, Yunbin
%A Li, Liang
%A Su, Li
%A Huang, Qingming
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F li-etal-2025-change
%X Change captioning aims to describe differences between a pair of images using natural language. However, learning effective difference representations is highly challenging due to distractors such as illumination and viewpoint changes. To address this, we propose a change-entity-guided disentanglement network that explicitly learns difference representations while mitigating the impact of distractors. Specifically, we first design a change entity retrieval module to identify key objects involved in the change from a textual perspective. Then, we introduce a difference representation enhancement module that strengthens the learned features, disentangling genuine differences from background variations. To further refine the generation process, we incorporate a gated Transformer decoder, which dynamically integrates both visual difference and textual change-entity information. Extensive experiments on CLEVR-Change, CLEVR-DC and Spot-the-Diff datasets demonstrate that our method outperforms existing approaches, achieving state-of-the-art performance. The code is available at https://github.com/yili-19/CHEER
%R 10.18653/v1/2025.findings-acl.876
%U https://aclanthology.org/2025.findings-acl.876/
%U https://doi.org/10.18653/v1/2025.findings-acl.876
%P 17050-17060
Markdown (Informal)
[Change Entity-guided Heterogeneous Representation Disentangling for Change Captioning](https://aclanthology.org/2025.findings-acl.876/) (Li et al., Findings 2025)
ACL