A vector quantized masked autoencoder for audiovisual speech emotion recognition

An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoencoders to learn representations of audiovisual speech without labels. The model...

Full description

Bibliographic Details

Published in:	Computer vision and image understanding Vol. 257; p. 104362
Main Authors:	Sadok, Samir, Leglaive, Simon, Séguier, Renaud
Format:	Journal Article
Language:	English
Published:	Elsevier Inc 01.06.2025 Elsevier
Subjects:	Audiovisual speech representation learning Computer Science Computer Vision and Pattern Recognition Emotion recognition Machine Learning Masked autoencoder Multimedia Self-supervised learning Signal and Image Processing Sound Emotion recognition Audiovisual speech representation learning Masked autoencoder Self-supervised learning
ISSN:	1077-3142, 1090-235X
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!