Orthogonal Disentanglement with Projected Feature Alignment for Multimodal Emotion Recognition in Conversation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Che, Xinyi, Wang, Wenbo, Guan, Jian, Zhao, Qijun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908827215986688
author Che, Xinyi
Wang, Wenbo
Guan, Jian
Zhao, Qijun
author_facet Che, Xinyi
Wang, Wenbo
Guan, Jian
Zhao, Qijun
contents Multimodal Emotion Recognition in Conversation (MERC) significantly enhances emotion recognition performance by integrating complementary emotional cues from text, audio, and visual modalities. While existing methods commonly utilize techniques such as contrastive learning and cross-attention mechanisms to align cross-modal emotional semantics, they typically overlook modality-specific emotional nuances like micro-expressions, tone variations, and sarcastic language. To overcome these limitations, we propose Orthogonal Disentanglement with Projected Feature Alignment (OD-PFA), a novel framework designed explicitly to capture both shared semantics and modality-specific emotional cues. Our approach first decouples unimodal features into shared and modality-specific components. An orthogonal disentanglement strategy (OD) enforces effective separation between these components, aided by a reconstruction loss to maintain critical emotional information from each modality. Additionally, a projected feature alignment strategy (PFA) maps shared features across modalities into a common latent space and applies a cross-modal consistency alignment loss to enhance semantic coherence. Extensive evaluations on widely-used benchmark datasets, IEMOCAP and MELD, demonstrate effectiveness of our proposed OD-PFA multimodal emotion recognition tasks, as compared with the state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22463
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Orthogonal Disentanglement with Projected Feature Alignment for Multimodal Emotion Recognition in Conversation
Che, Xinyi
Wang, Wenbo
Guan, Jian
Zhao, Qijun
Multimedia
Multimodal Emotion Recognition in Conversation (MERC) significantly enhances emotion recognition performance by integrating complementary emotional cues from text, audio, and visual modalities. While existing methods commonly utilize techniques such as contrastive learning and cross-attention mechanisms to align cross-modal emotional semantics, they typically overlook modality-specific emotional nuances like micro-expressions, tone variations, and sarcastic language. To overcome these limitations, we propose Orthogonal Disentanglement with Projected Feature Alignment (OD-PFA), a novel framework designed explicitly to capture both shared semantics and modality-specific emotional cues. Our approach first decouples unimodal features into shared and modality-specific components. An orthogonal disentanglement strategy (OD) enforces effective separation between these components, aided by a reconstruction loss to maintain critical emotional information from each modality. Additionally, a projected feature alignment strategy (PFA) maps shared features across modalities into a common latent space and applies a cross-modal consistency alignment loss to enhance semantic coherence. Extensive evaluations on widely-used benchmark datasets, IEMOCAP and MELD, demonstrate effectiveness of our proposed OD-PFA multimodal emotion recognition tasks, as compared with the state-of-the-art approaches.
title Orthogonal Disentanglement with Projected Feature Alignment for Multimodal Emotion Recognition in Conversation
topic Multimedia
url https://arxiv.org/abs/2511.22463