An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos.
Sicheng ZhaoYunsheng MaYang GuJufeng YangTengfei XingPengfei XuRunbo HuHua ChaiKurt KeutzerPublished in: CoRR (2020)
Keyphrases
- end to end
- user generated
- emotion recognition
- sentiment analysis
- congestion control
- audio visual
- visual information
- social media
- human computer interaction
- facial expressions
- web content
- video sharing
- visual data
- visual features
- text classification
- computer networks
- information fusion
- user interests
- video sequences
- text mining
- social networks
- natural language processing
- facial images
- low level
- emotional state
- website
- search engine