MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition.
Peihao XiangChaohao LinKaida WuOu BaiPublished in: CoRR (2024)
Keyphrases
- emotion recognition
- audio visual
- multi modal
- multi stream
- emotional speech
- dynamic environments
- human computer interaction
- facial expressions
- high dimensional
- neural network
- autonomous agents
- intelligent tutoring systems
- multimedia data
- information fusion
- multimedia
- feature selection
- computer vision
- emotion classification
- machine learning