Efficient convolutional hierarchical autoencoder for human motion prediction

This data was imported from Scopus:

Authors: Li, Y., Wang, Z., Yang, X., Wang, M., Poiana, S.I., Chaudhry, E. and Zhang, J.

http://eprints.bournemouth.ac.uk/32364/

Journal: Visual Computer

Volume: 35

Issue: 6-8

Pages: 1143-1156

ISSN: 0178-2789

DOI: 10.1007/s00371-019-01692-9

© 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.

The data on this page was last updated at 05:16 on February 19, 2020.