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 reinforcement learning formulation for the problem of human pose prediction, and develop an imitation learning algorithm for predicting future poses under this formulation through a combination of behavioral cloning and generative adversarial imitation learning. Our experiments show that our proposed method outperforms all existing state-of-the-art baseline models by large margins on the task of human pose prediction in both short-term predictions and long-term predictions, while also enjoying huge advantage in training speed.
@article{arxiv.1909.03449,
title = {Imitation Learning for Human Pose Prediction},
author = {Borui Wang and Ehsan Adeli and Hsu-kuang Chiu and De-An Huang and Juan Carlos Niebles},
journal= {arXiv preprint arXiv:1909.03449},
year = {2019}
}