A high speed inference architecture for multimodal emotion recognition based on sparse cross modal encoder.
Lin CuiYuanbang ZhangYingkai CuiBoyan WangXiaodong SunPublished in: J. King Saud Univ. Comput. Inf. Sci. (2024)
Keyphrases
- cross modal
- emotion recognition
- multi modal
- audio visual
- visual data
- multimedia retrieval
- high dimensional
- human computer interaction
- facial expressions
- visual recognition
- sentiment analysis
- image retrieval
- multimedia databases
- visual similarity
- visual information
- information fusion
- human motion
- emotional state
- web pages
- co occurrence
- multimedia