Imitation Learning for Human Pose Prediction

international conference on computer vision, pp. 7124-7133, 2019.

Cited by: 5|Bibtex|Views36
Other Links: academic.microsoft.com|arxiv.org

Abstract:

Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks. Inspired by the recent success of deep reinforcement learning methods, in this paper we propose a new reinfor...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments