HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition.

Licai Sun Zheng Lian Bin Liu Jianhua Tao

Published in: CoRR (2024)

Keyphrases

audio visual
emotion recognition
multi modal
speaker verification
visual information
visual data
multimedia
multi stream
information retrieval
data sets
user interface
human computer interaction
sentiment analysis