Audio-to-Facial Landmarks Generator for Talking Face Video Synthesis.
Dasol JeongInjae LeeJoonki PaikPublished in: ICEIC (2023)
Keyphrases
- facial landmarks
- facial images
- human faces
- shape model
- facial expressions
- active shape model
- appearance features
- subject specific
- automatically detected
- coarse to fine
- video sequences
- global context
- video data
- facial features
- texture information
- face detection
- face images
- facial expression recognition
- image database
- video frames
- image classification
- active appearance models
- computer vision
- object boundaries
- information extraction
- training set