T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text.

Aoxiong Yin Haoyuan Li Kai Shen Siliang Tang Yueting Zhuang

Published in: CoRR (2024)

Keyphrases

vector quantization
autoregressive
sign language
image compression
non stationary
vector quantizer
gesture recognition
sign recognition
random fields
distortion measure
hand gestures
sar images
english text
face recognition
model selection
natural images
denoising
motion estimation
information extraction
multiscale