Disentangling audio content and emotion with adaptive instance normalization for expressive facial animation synthesis.
Che-Jui ChangLong ZhaoSen ZhangMubbasir KapadiaPublished in: Comput. Animat. Virtual Worlds (2022)
Keyphrases
- facial animation
- facial expressions
- facial expression recognition
- audio content
- human faces
- facial images
- face recognition
- video sequences
- active appearance models
- temporal coherence
- head motion
- multimedia content
- motion capture data
- content based retrieval
- video retrieval
- computer vision
- image classification
- spatio temporal
- multimedia