Abstract
Human motion prediction is a classic computer vision task that has numerous applications in the field of autonomous driving, human-computer interaction and motion synthesis. Recently, a large number of motion prediction methods employ graph convolutional networks to encode the spatial relationships among joints within a pose, which ignore the impact of adjacent poses in the encoding process, resulting in unsatisfactory extraction of spatial information. Moreover, the recurrent neural network is difficult to capture long-term temporal dependencies. To solve these challenges, we design a prediction model that consists of two crucial components. Firstly, A novel spatio-temporal graph convolution module utilizes multi-graph convolution layers to capture the spatial correlation information of the current frame and adjacent frames simultaneously. Secondly, a multiscale temporal encoding module consists of a series of temporal convolutions with different dilation rates to establish various temporal relationships between poses at both short-term and long-term temporal distance. We evaluate the proposed method on the largest 3D human motion capture dataset (i.e., Human 3.6 Million). Extensive experimental results show that our model achieves state-of-the-art performance in both short and long-term predictions compared with existing methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akhter, I., Simon, T., Khan, S., Matthews, I.A., Sheikh, Y.: Bilinear spatiotemporal basis models. ACM Trans. Graph. 31(2), 1–12 (2012)
Barsoum, E., Kender, J., Liu, Z.: HP-GAN: probabilistic 3D human motion prediction via GAN. In: International Conference on Computer Vision and Pattern Recognition, pp. 1418–1427 (2018)
Cai, Y., et al.: Learning Progressive Joint Propagation for Human Motion Prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision – ECCV 2020. LNCS, vol. 12352, pp. 226–242. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58571-6_14
Chopin, B., Otberdout, N., Daoudi, M., Bartolo, A.: Human motion prediction using manifold-aware Wasserstein GAN. In: FG, pp. 1–8 (2021)
Cui, Q., Sun, H.: Towards accurate 3D human motion prediction from incomplete observations. In: International Conference on Computer Vision and Pattern Recognition, pp. 4801–4810 (2021)
Cui, Q., Sun, H., Kong, Y., Zhang, X., Li, Y.: Efficient human motion prediction using temporal convolutional generative adversarial network. Inf. Sci. 545, 427–447 (2021)
Cui, Q., Sun, H., Yang, F.: Learning dynamic relationships for 3D human motion prediction. In: International Conference on Computer Vision and Pattern Recognition, pp. 6518–6526 (2020)
Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: International Conference on Computer Vision, pp. 4346–4354 (2015)
Jiao, Y., Chen, H., Yao, C., Su, P., Fu, C., Wang, X.: Spatial-temporal correlation modeling for motion prediction. In: International Conference on Multimedia and Expo, pp. 1–6 (2022)
Kundu, J.N., Gor, M., Babu, R.V.: BiHMP-GAN: bidirectional 3D human motion prediction GAN. In: The Thirty-First Innovative Applications of Artificial Intelligence Conference, pp. 8553–8560 (2019)
Lehrmann, A.M., Gehler, P.V., Nowozin, S.: Efficient nonlinear Markov models for human motion. In: International Conference on Computer Vision and Pattern Recognition, pp. 1314–1321 (2014)
Li, C., Zhang, Z., Lee, W.S., Lee, G.H.: Convolutional sequence to sequence model for human dynamics. In: Conference on Computer Vision and Pattern Recognition, pp. 5226–5234 (2018)
Li, M., Chen, S., Zhao, Y., Zhang, Y., Wang, Y., Tian, Q.: Dynamic multiscale graph neural networks for 3D skeleton based human motion prediction. In: International Conference on Computer Vision and Pattern Recognition, pp. 211–220 (2020)
Li, Q., Chalvatzaki, G., Peters, J., Wang, Y.: Directed acyclic graph neural network for human motion prediction. In: International Conference on Robotics and Automation, pp. 3197–3204 (2021)
Liu, Z., et al.: Motion prediction using trajectory cues. In: International Conference on Computer Vision, pp. 13299–13308 (2021)
Liu, Z., et al.: Towards natural and accurate future motion prediction of humans and animals. In: International Conference on Computer Vision and Pattern Recognition, pp. 10004–10012 (2019)
Mao, W., Liu, M., Salzmann, M., Li, H.: Learning trajectory dependencies for human motion prediction. In: International Conference on Computer Vision, pp. 9488–9496 (2019)
Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: International Conference on Computer Vision and Pattern Recognition, pp. 4674–4683 (2017)
Su, P., Liu, Z., Wu, S., Zhu, L., Yin, Y., Shen, X.: Motion prediction via joint dependency modeling in phase space. In: ACM Multimedia Conference, pp. 713–721 (2021)
Su, P., Shen, X., Shi, Z., Liu, W.: Adaptive multi-order graph neural networks for human motion prediction. In: International Conference on Multimedia and Expo, pp. 1–6 (2022)
Taylor, G.W., Hinton, G.E.: Factored conditional restricted Boltzmann machines for modeling motion style. Int. Conf. Mach. Learn. 382, 1025–1032 (2009)
Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models. In: Advances in Neural Information Processing Systems, pp. 1441–1448 (2005)
Zhou, H., Guo, C., Zhang, H., Wang, Y.: Learning multiscale correlations for human motion prediction. In: International Conference on Development and Learning, pp. 1–7 (2021)
Acknowledgements
This research is supported by the National Key Research and Development Program of China (2018YFB0804202, 2018YFB0804203), Regional Joint Fund of NSFC(U19A2057), and the National Natural Science Foundation of China (61876070).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Su, P., Shen, X., Chen, H. (2022). Multiscale Spatial and Temporal Learning for Human Motion Prediction. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13530. Springer, Cham. https://doi.org/10.1007/978-3-031-15931-2_49
Download citation
DOI: https://doi.org/10.1007/978-3-031-15931-2_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15930-5
Online ISBN: 978-3-031-15931-2
eBook Packages: Computer ScienceComputer Science (R0)