Imitation Learning for Human Pose Prediction

Borui Wang, Ehsan Adeli, Hsu-kuang Chiu, De-An Huang, Juan Carlos Niebles; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 7124-7133

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 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.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Wang_2019_ICCV,
author = {Wang, Borui and Adeli, Ehsan and Chiu, Hsu-kuang and Huang, De-An and Niebles, Juan Carlos},
title = {Imitation Learning for Human Pose Prediction},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}