@inproceedings{she-etal-2026-aica,
title = "{AICA}-Bench: Holistically Examining the Capabilities of {VLM}s in Affective Image Content Analysis",
author = "She, Dong and
Yao, Xianrong and
Chen, Liqun and
Yu, Jinghe and
Gao, Yang and
Jin, Zhanpeng",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.661/",
pages = "13501--13528",
ISBN = "979-8-89176-395-1",
abstract = "Vision-Language Models (VLMs) have demonstrated strong capabilities in perception, yet holistic Affective Image Content Analysis (AICA){---}which integrates perception, reasoning, and generation into a unified framework{---}remains underexplored. To address this, we introduce AICA-Bench, a comprehensive benchmark comprising three core tasks: Emotion Understanding (EU), Reasoning (ER), and Generation (EGCG). We evaluate 23 VLMs, revealing critical gaps: models struggle with intensity calibration and suffer from descriptive shallowness in open-ended tasks. To bridge these gaps, we propose Grounded Affective Tree (GAT) Prompting, a training-free framework that integrates visual scaffolding with hierarchical reasoning. Experiments show that GAT effectively corrects intensity errors and significantly enhances descriptive depth, establishing a robust baseline for future affective multimodal research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="she-etal-2026-aica">
<titleInfo>
<title>AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">She</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianrong</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinghe</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanpeng</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Vision-Language Models (VLMs) have demonstrated strong capabilities in perception, yet holistic Affective Image Content Analysis (AICA)—which integrates perception, reasoning, and generation into a unified framework—remains underexplored. To address this, we introduce AICA-Bench, a comprehensive benchmark comprising three core tasks: Emotion Understanding (EU), Reasoning (ER), and Generation (EGCG). We evaluate 23 VLMs, revealing critical gaps: models struggle with intensity calibration and suffer from descriptive shallowness in open-ended tasks. To bridge these gaps, we propose Grounded Affective Tree (GAT) Prompting, a training-free framework that integrates visual scaffolding with hierarchical reasoning. Experiments show that GAT effectively corrects intensity errors and significantly enhances descriptive depth, establishing a robust baseline for future affective multimodal research.</abstract>
<identifier type="citekey">she-etal-2026-aica</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.661/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>13501</start>
<end>13528</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis
%A She, Dong
%A Yao, Xianrong
%A Chen, Liqun
%A Yu, Jinghe
%A Gao, Yang
%A Jin, Zhanpeng
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F she-etal-2026-aica
%X Vision-Language Models (VLMs) have demonstrated strong capabilities in perception, yet holistic Affective Image Content Analysis (AICA)—which integrates perception, reasoning, and generation into a unified framework—remains underexplored. To address this, we introduce AICA-Bench, a comprehensive benchmark comprising three core tasks: Emotion Understanding (EU), Reasoning (ER), and Generation (EGCG). We evaluate 23 VLMs, revealing critical gaps: models struggle with intensity calibration and suffer from descriptive shallowness in open-ended tasks. To bridge these gaps, we propose Grounded Affective Tree (GAT) Prompting, a training-free framework that integrates visual scaffolding with hierarchical reasoning. Experiments show that GAT effectively corrects intensity errors and significantly enhances descriptive depth, establishing a robust baseline for future affective multimodal research.
%U https://aclanthology.org/2026.findings-acl.661/
%P 13501-13528
Markdown (Informal)
[AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis](https://aclanthology.org/2026.findings-acl.661/) (She et al., Findings 2026)
ACL