ECMF: Enhanced Cross-Modal Fusion for Multimodal Emotion Recognition in MER-SEMI Challenge

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hu, Juewen, Li, Yexin, Li, Jiulin, Chen, Shuo, Wong, Pring
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915434453794816
author Hu, Juewen
Li, Yexin
Li, Jiulin
Chen, Shuo
Wong, Pring
author_facet Hu, Juewen
Li, Yexin
Li, Jiulin
Chen, Shuo
Wong, Pring
contents Emotion recognition plays a vital role in enhancing human-computer interaction. In this study, we tackle the MER-SEMI challenge of the MER2025 competition by proposing a novel multimodal emotion recognition framework. To address the issue of data scarcity, we leverage large-scale pre-trained models to extract informative features from visual, audio, and textual modalities. Specifically, for the visual modality, we design a dual-branch visual encoder that captures both global frame-level features and localized facial representations. For the textual modality, we introduce a context-enriched method that employs large language models to enrich emotional cues within the input text. To effectively integrate these multimodal features, we propose a fusion strategy comprising two key components, i.e., self-attention mechanisms for dynamic modality weighting, and residual connections to preserve original representations. Beyond architectural design, we further refine noisy labels in the training set by a multi-source labeling strategy. Our approach achieves a substantial performance improvement over the official baseline on the MER2025-SEMI dataset, attaining a weighted F-score of 87.49% compared to 78.63%, thereby validating the effectiveness of the proposed framework.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05991
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ECMF: Enhanced Cross-Modal Fusion for Multimodal Emotion Recognition in MER-SEMI Challenge
Hu, Juewen
Li, Yexin
Li, Jiulin
Chen, Shuo
Wong, Pring
Computer Vision and Pattern Recognition
Artificial Intelligence
Computers and Society
Emotion recognition plays a vital role in enhancing human-computer interaction. In this study, we tackle the MER-SEMI challenge of the MER2025 competition by proposing a novel multimodal emotion recognition framework. To address the issue of data scarcity, we leverage large-scale pre-trained models to extract informative features from visual, audio, and textual modalities. Specifically, for the visual modality, we design a dual-branch visual encoder that captures both global frame-level features and localized facial representations. For the textual modality, we introduce a context-enriched method that employs large language models to enrich emotional cues within the input text. To effectively integrate these multimodal features, we propose a fusion strategy comprising two key components, i.e., self-attention mechanisms for dynamic modality weighting, and residual connections to preserve original representations. Beyond architectural design, we further refine noisy labels in the training set by a multi-source labeling strategy. Our approach achieves a substantial performance improvement over the official baseline on the MER2025-SEMI dataset, attaining a weighted F-score of 87.49% compared to 78.63%, thereby validating the effectiveness of the proposed framework.
title ECMF: Enhanced Cross-Modal Fusion for Multimodal Emotion Recognition in MER-SEMI Challenge
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2508.05991