MTGA: Multi-view Temporal Granularity aligned Aggregation for Event-based Lip-reading.

Wenhao Zhang Jun Wang Yong Luo Lei Yu Wei Yu Zheng He

Published in: CoRR (2024)

Keyphrases

multi view
lip reading
single view
multiple views
d objects
depth map
three dimensional
camera calibration
dynamic scenes
multiple cameras
active appearance models
spatio temporal
face tracking
semi supervised
super resolution
active learning
object recognition
computational complexity