Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss.

Lele Chen Ross K. Maddox Zhiyao Duan Chenliang Xu

Published in: CoRR (2019)

Keyphrases

pixel wise
cross modal
multi modal
multimedia retrieval
pixel level
video sequences
face images
spatial information
template matching
visual recognition
computer vision
high dimensional
image retrieval
visual data