VAST: Vivify Your Talking Avatar via Zero-Shot Expressive Facial Style Transfer.
Liyang ChenZhiyong WuRunnan LiWeihong BaoJun LingXu TanSheng ZhaoPublished in: ICCV (Workshops) (2023)
Keyphrases
- facial animation
- facial expressions
- virtual world
- facial motion
- human faces
- landmark detection
- face recognition
- facial images
- facial features
- transfer learning
- face images
- human computer interaction
- age estimation
- cross domain
- active appearance models
- behavior recognition
- knowledge transfer
- multiscale
- expression classification
- facial expression recognition
- image sequences
- real time
- emotion recognition
- three dimensional
- active learning
- computer vision
- constantly growing
- genetic algorithm