@inproceedings{zhang-etal-2024-amanda,
title = "Amanda: Adaptively Modality-Balanced Domain Adaptation for Multimodal Emotion Recognition",
author = "Zhang, Xinxin and
Sun, Jun and
Hong, Simin and
Li, Taihao",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.859",
pages = "14448--14458",
abstract = "This paper investigates unsupervised multimodal domain adaptation for multimodal emotion recognition, which is a solution for data scarcity yet remains under studied. Due to the varying distribution discrepancies of different modalities between source and target domains, the primary challenge lies in how to balance the domain alignment across modalities to guarantee they are all well aligned. To achieve this, we first develop our model based on the information bottleneck theory to learn optimal representation for each modality independently. Then, we align the domains via matching the label distributions and the representations. In order to balance the representation alignment, we propose to minimize a surrogate of the alignment losses, which is equivalent to adaptively adjusting the weights of the modalities throughout training, thus achieving balanced domain alignment across modalities. Overall, the proposed approach features \textbf{A}daptively \textbf{m}odality-bal\textbf{an}ced \textbf{d}omain \textbf{a}daptation, dubbed \textbf{Amanda}, for multimodal emotion recognition. Extensive empirical results on commonly used benchmark datasets demonstrate that Amanda significantly outperforms competing approaches. The code is available at \url{https://github.com/sunjunaimer/Amanda}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-amanda">
<titleInfo>
<title>Amanda: Adaptively Modality-Balanced Domain Adaptation for Multimodal Emotion Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinxin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simin</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taihao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper investigates unsupervised multimodal domain adaptation for multimodal emotion recognition, which is a solution for data scarcity yet remains under studied. Due to the varying distribution discrepancies of different modalities between source and target domains, the primary challenge lies in how to balance the domain alignment across modalities to guarantee they are all well aligned. To achieve this, we first develop our model based on the information bottleneck theory to learn optimal representation for each modality independently. Then, we align the domains via matching the label distributions and the representations. In order to balance the representation alignment, we propose to minimize a surrogate of the alignment losses, which is equivalent to adaptively adjusting the weights of the modalities throughout training, thus achieving balanced domain alignment across modalities. Overall, the proposed approach features Adaptively modality-balanced domain adaptation, dubbed Amanda, for multimodal emotion recognition. Extensive empirical results on commonly used benchmark datasets demonstrate that Amanda significantly outperforms competing approaches. The code is available at https://github.com/sunjunaimer/Amanda.</abstract>
<identifier type="citekey">zhang-etal-2024-amanda</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.859</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14448</start>
<end>14458</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Amanda: Adaptively Modality-Balanced Domain Adaptation for Multimodal Emotion Recognition
%A Zhang, Xinxin
%A Sun, Jun
%A Hong, Simin
%A Li, Taihao
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F zhang-etal-2024-amanda
%X This paper investigates unsupervised multimodal domain adaptation for multimodal emotion recognition, which is a solution for data scarcity yet remains under studied. Due to the varying distribution discrepancies of different modalities between source and target domains, the primary challenge lies in how to balance the domain alignment across modalities to guarantee they are all well aligned. To achieve this, we first develop our model based on the information bottleneck theory to learn optimal representation for each modality independently. Then, we align the domains via matching the label distributions and the representations. In order to balance the representation alignment, we propose to minimize a surrogate of the alignment losses, which is equivalent to adaptively adjusting the weights of the modalities throughout training, thus achieving balanced domain alignment across modalities. Overall, the proposed approach features Adaptively modality-balanced domain adaptation, dubbed Amanda, for multimodal emotion recognition. Extensive empirical results on commonly used benchmark datasets demonstrate that Amanda significantly outperforms competing approaches. The code is available at https://github.com/sunjunaimer/Amanda.
%U https://aclanthology.org/2024.findings-acl.859
%P 14448-14458
Markdown (Informal)
[Amanda: Adaptively Modality-Balanced Domain Adaptation for Multimodal Emotion Recognition](https://aclanthology.org/2024.findings-acl.859) (Zhang et al., Findings 2024)
ACL