Imitation Learning for Human Pose Prediction

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.

arXiv comment10 pages, 7 figures, accepted to ICCV 2019

References in corpus (9)

• Sequence to Sequence Learning with Neural Networks
• Continuous control with deep reinforcement learning
• Playing Atari with Deep Reinforcement Learning
• Trust Region Policy Optimization
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• Learning Human Motion Models for Long-term Predictions
• Forecasting Human Dynamics from Static Images

Cited by in corpus (1)

• Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks