Speech-driven facial animation with spectral gathering and temporal attention.

Yujin Chai Yanlin Weng Lvdi Wang Kun Zhou

Published in: Frontiers Comput. Sci. (2022)

Keyphrases

facial animation
temporal coherence
facial expressions
human faces
head motion
facial images
spatio temporal
motion capture data
active appearance models
dynamic scenes
facial expression recognition
facial motion
motion tracking
video frames
multi frame
geometric structure
visual attention
space time
optical flow