Towards Natural and Accurate Future Motion Prediction of Humans and Animals

Zhenguang Liu, Shuang Wu, Shuyuan Jin, Qi Liu, Shijian Lu, Roger Zimmermann, Li Cheng; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 10004-10012

Abstract


Anticipating the future motions of 3D articulate objects is challenging due to its non-linear and highly stochastic nature. Current approaches typically represent the skeleton of an articulate object as a set of 3D joints, which unfortunately ignores the relationship between joints, and fails to encode fine-grained anatomical constraints. Moreover, conventional recurrent neural networks, such as LSTM and GRU, are employed to model motion contexts, which inherently have difficulties in capturing long-term dependencies. To address these problems, we propose to explicitly encode anatomical constraints by modeling their skeletons with a Lie algebra representation. Importantly, a hierarchical recurrent network structure is developed to simultaneously encodes local contexts of individual frames and global contexts of the sequence. We proceed to explore the applications of our approach to several distinct quantities including human, fish, and mouse. Extensive experiments show that our approach achieves more natural and accurate predictions over state-of-the-art methods.

Related Material


[pdf]
[bibtex]
@InProceedings{Liu_2019_CVPR,
author = {Liu, Zhenguang and Wu, Shuang and Jin, Shuyuan and Liu, Qi and Lu, Shijian and Zimmermann, Roger and Cheng, Li},
title = {Towards Natural and Accurate Future Motion Prediction of Humans and Animals},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}