Invariant Motion Representation Learning for 3D Talking Face Synthesis.

Jiyuan Liu Wenping Wei Zhendong Li Guanfeng Li Hao Liu

Published in: ICASSP (2024)

Keyphrases

learning process
online learning
prior knowledge
learning systems
learning tasks
face images
active learning
motion estimation
affine transformation
fourier domain
multiple representations
recognizing human actions