Imitation Learning for Human Pose Prediction
ICCV, pp. 7123-7132, 2019.
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
PPT (Upload PPT)