@inproceedings{zhou-etal-2025-dual,
title = "Dual-Path Dynamic Fusion with Learnable Query for Multimodal Sentiment Analysis",
author = "Zhou, Miao and
Yang, Lina and
Wu, Thomas and
Yang, Dongnan and
Zhang, Xinru",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.571/",
pages = "11366--11376",
ISBN = "979-8-89176-332-6",
abstract = "Multimodal Sentiment Analysis (MSA) is the task of understanding human emotions by analyzing a combination of different data sources, such as text, audio, and visual inputs. Although recent advances have improved emotion modeling across modalities, existing methods still struggle with two fundamental challenges: balancing global and fine-grained sentiment contributions, and over-reliance on the text modality. To address these issues, we propose DPDF-LQ (Dual-Path Dynamic Fusion with Learnable Query), an architecture that processes inputs through two complementary paths: global and local. The global path is responsible for establishing cross-modal dependencies, while the local path captures fine-grained representations. Additionally, we introduce the key module Dynamic Global Learnable Query Attention (DGLQA) in the global path, which dynamically allocates weights to each modality to capture their relevant features and learn global representations. Extensive experiments on the CMU-MOSI and CMU-MOSEI benchmarks demonstrate that DPDF-LQ achieves state-of-the-art performance, particularly in fine-grained sentiment prediction by effectively combining global and local features. Our code will be released at \url{https://github.com/ZhouMiaoGX/DPDF-LQ}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2025-dual">
<titleInfo>
<title>Dual-Path Dynamic Fusion with Learnable Query for Multimodal Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongnan</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinru</namePart>
<namePart type="family">Zhang</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>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Multimodal Sentiment Analysis (MSA) is the task of understanding human emotions by analyzing a combination of different data sources, such as text, audio, and visual inputs. Although recent advances have improved emotion modeling across modalities, existing methods still struggle with two fundamental challenges: balancing global and fine-grained sentiment contributions, and over-reliance on the text modality. To address these issues, we propose DPDF-LQ (Dual-Path Dynamic Fusion with Learnable Query), an architecture that processes inputs through two complementary paths: global and local. The global path is responsible for establishing cross-modal dependencies, while the local path captures fine-grained representations. Additionally, we introduce the key module Dynamic Global Learnable Query Attention (DGLQA) in the global path, which dynamically allocates weights to each modality to capture their relevant features and learn global representations. Extensive experiments on the CMU-MOSI and CMU-MOSEI benchmarks demonstrate that DPDF-LQ achieves state-of-the-art performance, particularly in fine-grained sentiment prediction by effectively combining global and local features. Our code will be released at https://github.com/ZhouMiaoGX/DPDF-LQ.</abstract>
<identifier type="citekey">zhou-etal-2025-dual</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.571/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>11366</start>
<end>11376</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dual-Path Dynamic Fusion with Learnable Query for Multimodal Sentiment Analysis
%A Zhou, Miao
%A Yang, Lina
%A Wu, Thomas
%A Yang, Dongnan
%A Zhang, Xinru
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F zhou-etal-2025-dual
%X Multimodal Sentiment Analysis (MSA) is the task of understanding human emotions by analyzing a combination of different data sources, such as text, audio, and visual inputs. Although recent advances have improved emotion modeling across modalities, existing methods still struggle with two fundamental challenges: balancing global and fine-grained sentiment contributions, and over-reliance on the text modality. To address these issues, we propose DPDF-LQ (Dual-Path Dynamic Fusion with Learnable Query), an architecture that processes inputs through two complementary paths: global and local. The global path is responsible for establishing cross-modal dependencies, while the local path captures fine-grained representations. Additionally, we introduce the key module Dynamic Global Learnable Query Attention (DGLQA) in the global path, which dynamically allocates weights to each modality to capture their relevant features and learn global representations. Extensive experiments on the CMU-MOSI and CMU-MOSEI benchmarks demonstrate that DPDF-LQ achieves state-of-the-art performance, particularly in fine-grained sentiment prediction by effectively combining global and local features. Our code will be released at https://github.com/ZhouMiaoGX/DPDF-LQ.
%U https://aclanthology.org/2025.emnlp-main.571/
%P 11366-11376
Markdown (Informal)
[Dual-Path Dynamic Fusion with Learnable Query for Multimodal Sentiment Analysis](https://aclanthology.org/2025.emnlp-main.571/) (Zhou et al., EMNLP 2025)
ACL