Efficient convolutional hierarchical autoencoder for human motion prediction

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

Journal: Visual Computer

Volume: 35

Issue: 6-8

Pages: 1143-1156

ISSN: 0178-2789

DOI: 10.1007/s00371-019-01692-9

Abstract:

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.

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

Source: Scopus

Efficient convolutional hierarchical autoencoder for human motion prediction

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

Journal: VISUAL COMPUTER

Volume: 35

Issue: 6-8

Pages: 1143-1156

eISSN: 1432-2315

ISSN: 0178-2789

DOI: 10.1007/s00371-019-01692-9

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

Source: Web of Science (Lite)

Efficient convolutional hierarchical autoencoder for human motion prediction

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

Journal: Visual Computer

Volume: 35

Issue: 6-8

Pages: 1143-1156

ISSN: 0178-2789

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.

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

Source: BURO EPrints