Efficient convolutional hierarchical autoencoder for human motion prediction

• Published in: The Visual computer Vol. 35; no. 6-8; pp. 1143 - 1156
• Main Authors: Li, Yanran, Wang, Zhao, Yang, Xiaosong, Wang, Meili, Poiana, Sebastian Iulian, Chaudhry, Ehtzaz, Zhang, Jianjun
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2019; Springer Nature B.V
• Subjects: Artificial Intelligence; Computer Graphics; Computer Science; Datasets; Deep learning; Design; Human body; Human motion; Image Processing and Computer Vision; Machine learning; Machine translation; Neural networks; Original Article; Time series; Topology; Deep learning; Hierarchical networks; Motion prediction; Autoencoder
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-019-01692-9

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.