Abstract
This paper is mainly about addressing the problem of skeleton-based human activity recognition: ignoring the structure and relationship between skeleton joints and body-parts, the existence of a large amount of useless information in the activity data, and poor generalization ability. In order to solve the shortcomings of existing mainstream methods used for human action recognition, we propose a novel method named Action Tree Convolutional Networks (ATCNs). This method uses a data based auto-designed Action Tree network to dynamically generate a tree of nodes/body-parts and a semantic attention center, profoundly emphasizing the relations and semantics of nodes/body-parts. This method we introduced has a great improvement on the previous algorithm’s neglect of the importance of nodes/body-parts relation, and improves the generalization ability of the algorithm. Through experiments on Kinetics and NTU-RGB+D datasets, our method achieves better performance improvements over other state-of-the-art methods.
Z. Zhang, B. Han and C. Zhu—These authors contributed equally to this work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Karpathy, A., Toderici, G., Shetty, et al.: Large-scale video classification with convolutional neural networks. In: CVPR, pp. 1725–1732 (2014)
Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV, pp. 4489–4497. IEEE, Washington (2015)
Baradel, F., Wolf, C., Mille, J., Taylor, G.W.: Glimpse clouds: human activity recognition from unstructured feature points. arXiv preprint arXiv:1802.07898 (2018)
Amir, S., Jun, L., Tian-Tsong, N., Gang, W.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: CVPR (2016)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI (2018)
Lin, L., Wang, G., Zhang, R., et al.: Deep structured scene parsing by learning with image descriptions. In: Computer Vision and Pattern Recognition, pp. 2276–2284. IEEE, Washington (2016)
Kay, W., Carreira, J., Simonyan, K., et al.: The kinetics human action video dataset. In: arXiv preprint arXiv:1705.06950 (2017)
Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR, vol. 1, no. 2, p. 7 (2017, July)
Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: CVPR, vol. 2, July 2017
Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR, pp. 4724–4732 (2016)
Kim, T.S., Reiter, A.: Interpretable 3D human action analysis with temporal convolutional networks. In: CVPRW, pp. 1623–1631. IEEE, Washington, July 2017
Veeriah, V., Zhuang, N., Qi, G.J.: Differential recurrent neural networks for action recognition. In: Computer Vision (ICCV), pp. 4041–4049. IEEE, Washington, December 2015
Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: CVPR, pp. 1110–1118 (2015)
Liu, J., Shahroudy, A., Xu, D., Wang, G.: Spatio-temporal LSTM with trust gates for 3D human action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 816–833. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_50
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, W., Zhang, Z., Han, B., Zhu, C. (2018). Action Tree Convolutional Networks: Skeleton-Based Human Action Recognition. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11166. Springer, Cham. https://doi.org/10.1007/978-3-030-00764-5_72
Download citation
DOI: https://doi.org/10.1007/978-3-030-00764-5_72
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00763-8
Online ISBN: 978-3-030-00764-5
eBook Packages: Computer ScienceComputer Science (R0)