Skip to main content

Efficient convolutional hierarchical autoencoder for human motion prediction.

Liu, Y., Wang, Z., Yang, X., Wang, M., Poiana, S.I., Chaudhry, E. and Zhang, J. J., 2019. Efficient convolutional hierarchical autoencoder for human motion prediction. Visual Computer, 35 (6-8), 1143-1156.

Full text available as:

[img]
Preview
PDF (OPEN ACCESS ARTICLE)
Li2019_Article_EfficientConvolutionalHierarch.pdf - Published Version
Available under License Creative Commons Attribution.

1MB

DOI: 10.1007/s00371-019-01692-9

Abstract

© 2019, The Author(s). Human motion prediction is a challenging problem due to the complicated human body constraints and high-dimensional dynamics. Recent deep learning approaches adopt RNN, CNN or fully connected networks to learn the motion features which do not fully exploit the hierarchical structure of human anatomy. To address this problem, we propose a convolutional hierarchical autoencoder model for motion prediction with a novel encoder which incorporates 1D convolutional layers and hierarchical topology. The new network is more efficient compared to the existing deep learning models with respect to size and speed. We train the generic model on Human3.6M and CMU benchmark and conduct extensive experiments. The qualitative and quantitative results show that our model outperforms the state-of-the-art methods in both short-term prediction and long-term prediction.

Item Type:Article
ISSN:0178-2789
Uncontrolled Keywords:Motion prediction; Deep learning; Autoencoder; Hierarchical networks
Group:Faculty of Media & Communication
ID Code:32364
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:05 Jun 2019 13:27
Last Modified:24 Jun 2019 14:22

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -