Skeleton-Based Emotion Recognition Based on Two-Stream Self-Attention Enhanced Spatial-Temporal Graph Convolutional Network.
Jiaqi ShiChaoran LiuCarlos Toshinori IshiHiroshi IshiguroPublished in: Sensors (2021)
Keyphrases
- spatial temporal
- emotion recognition
- convolutional network
- human computer interaction
- spatial and temporal
- audio visual
- convolutional neural networks
- spatio temporal
- action recognition
- temporal information
- sentiment analysis
- facial expressions
- emotional state
- video shots
- feature selection
- image processing
- coarse to fine
- affective states
- multi modal