@inproceedings{zhu-etal-2025-survey,
title = "A Survey on Multi-modal Intent Recognition: Recent Advances and New Frontiers",
author = "Zhu, Zhihong and
Zhang, Fan and
Zhang, Yunyan and
Sun, Jinghan and
Huang, Zhiqi and
Long, Qingqing and
Xing, Bowen and
Wu, Xian",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.823/",
doi = "10.18653/v1/2025.findings-emnlp.823",
pages = "15223--15236",
ISBN = "979-8-89176-335-7",
abstract = "Multi-modal intent recognition (MIR) requires integrating non-verbal cues from real-world contexts to enhance human intention understanding, which has attracted substantial research attention in recent years. Despite promising advancements, a comprehensive survey summarizing recent advances and new frontiers remains absent. To this end, we present a thorough and unified review of MIR, covering different aspects including (1) Extensive survey: we take the first step to present a thorough survey of this research field covering textual, visual (image/video), and acoustic signals. (2) Unified taxonomy: we provide a unified framework including evaluation protocol and advanced methods to summarize the current progress in MIR. (3) Emerging frontiers: We discuss some future directions such as multi-task, multi-domain, and multi-lingual MIR, and give our thoughts respectively. (4) Abundant resources: we collect abundant open-source resources, including relevant papers, data corpora, and leaderboards. We hope this survey can shed light on future research in MIR."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2025-survey">
<titleInfo>
<title>A Survey on Multi-modal Intent Recognition: Recent Advances and New Frontiers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihong</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinghan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqi</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingqing</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Multi-modal intent recognition (MIR) requires integrating non-verbal cues from real-world contexts to enhance human intention understanding, which has attracted substantial research attention in recent years. Despite promising advancements, a comprehensive survey summarizing recent advances and new frontiers remains absent. To this end, we present a thorough and unified review of MIR, covering different aspects including (1) Extensive survey: we take the first step to present a thorough survey of this research field covering textual, visual (image/video), and acoustic signals. (2) Unified taxonomy: we provide a unified framework including evaluation protocol and advanced methods to summarize the current progress in MIR. (3) Emerging frontiers: We discuss some future directions such as multi-task, multi-domain, and multi-lingual MIR, and give our thoughts respectively. (4) Abundant resources: we collect abundant open-source resources, including relevant papers, data corpora, and leaderboards. We hope this survey can shed light on future research in MIR.</abstract>
<identifier type="citekey">zhu-etal-2025-survey</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.823</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.823/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>15223</start>
<end>15236</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey on Multi-modal Intent Recognition: Recent Advances and New Frontiers
%A Zhu, Zhihong
%A Zhang, Fan
%A Zhang, Yunyan
%A Sun, Jinghan
%A Huang, Zhiqi
%A Long, Qingqing
%A Xing, Bowen
%A Wu, Xian
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F zhu-etal-2025-survey
%X Multi-modal intent recognition (MIR) requires integrating non-verbal cues from real-world contexts to enhance human intention understanding, which has attracted substantial research attention in recent years. Despite promising advancements, a comprehensive survey summarizing recent advances and new frontiers remains absent. To this end, we present a thorough and unified review of MIR, covering different aspects including (1) Extensive survey: we take the first step to present a thorough survey of this research field covering textual, visual (image/video), and acoustic signals. (2) Unified taxonomy: we provide a unified framework including evaluation protocol and advanced methods to summarize the current progress in MIR. (3) Emerging frontiers: We discuss some future directions such as multi-task, multi-domain, and multi-lingual MIR, and give our thoughts respectively. (4) Abundant resources: we collect abundant open-source resources, including relevant papers, data corpora, and leaderboards. We hope this survey can shed light on future research in MIR.
%R 10.18653/v1/2025.findings-emnlp.823
%U https://aclanthology.org/2025.findings-emnlp.823/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.823
%P 15223-15236
Markdown (Informal)
[A Survey on Multi-modal Intent Recognition: Recent Advances and New Frontiers](https://aclanthology.org/2025.findings-emnlp.823/) (Zhu et al., Findings 2025)
ACL
- Zhihong Zhu, Fan Zhang, Yunyan Zhang, Jinghan Sun, Zhiqi Huang, Qingqing Long, Bowen Xing, and Xian Wu. 2025. A Survey on Multi-modal Intent Recognition: Recent Advances and New Frontiers. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 15223–15236, Suzhou, China. Association for Computational Linguistics.