TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts.

Chuan Guo Xinxin Zuo Sen Wang Li Cheng

Published in: ECCV (35) (2022)

Keyphrases

human motion
stochastic models
neural network
image sequences
body parts
motion sequences
text generation
machine learning
computer vision
multimedia
video sequences
motion estimation
multi modal