Audio-Video Based Multimodal Emotion Recognition Using SVMs and Deep Learning.
Bo SunQihua XuJun HeLejun YuLiandong LiQinglan WeiPublished in: CCPR (2) (2016)
Keyphrases
- deep learning
- multimodal fusion
- audio visual
- support vector
- emotion recognition
- machine learning
- unsupervised learning
- multimodal interfaces
- feature selection
- unsupervised feature learning
- multi class
- multi modal
- mental models
- support vector machine
- feature vectors
- training data
- weakly supervised
- higher order
- viewpoint
- training set
- pattern recognition
- decision making
- computer vision