Vector Quantized Diffusion Model with CodeUnet for Text-to-Sign Pose Sequences Generation.

Pan Xie Qipeng Zhang Zexian Li Hao Tang Yao Du Xiaohui Hu

Published in: CoRR (2022)

Keyphrases

diffusion model
vector quantized
anisotropic diffusion
information diffusion
vector quantization
diffusion process
diffusion tensor
image compression
multiscale
image features
text mining
visual words
variable length
text graphics