Abstract
Most previous skeleton-based action recognition methods ignore weight information of joints and data features beyond labels, which is harmful to action recognition. In this paper, we propose a skeleton-based action recognition with improved Graph Convolution Network, which is based on Spatial Temporal Graph Convolutional Network (STGCN). And we add a predictive cluster network, weight generation networks on it. The model uses K-means algorithm to cluster and get the data information beyond the labels. Besides, each cluster traines weight generation networks independently. To find the best clusters, we propose a evaluation criterion with less computational effort. We perform extensive experiments on the Kinetics dataset and the NTU RGB+D dataset to verify the effectiveness of each network of our model. The comparison results show that our approach achieves satisfactory results.
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
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems 1 (2014)
Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1110–1118 (2015)
Du, W., Wang, Y., Qiao, Y.: RPAN: an end-to-end recurrent pose-attention network for action recognition in videos. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)
Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition (2018)
Si, C., Chen, W., Wang, W., Wang, L., Tan, T.: An attention enhanced graph convolutional LSTM network for skeleton-based action recognition (2019)
Silhouettes, R.P.J.: A graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53–65 (2021)
Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3d skeletons as points in a lie group. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 588–595 (2014)
Shahroudy, A., Liu, J., Ng, T., Wang, G.: NTU RGB+D: a large scale dataset for 3d human activity analysis. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1010–1019 (2016)
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
Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., Zheng, N.: View adaptive recurrent neural networks for high performance human action recognition from skeleton data (2017)
Zheng, W., Li, L., Zhang, Z., Huang, Y., Wang, L.: Relational network for skeleton-based action recognition (2019)
Li, S., Li, W., Cook, C., Zhu, C., Gao, Y.: Independently recurrent neural network (INDRNN): building a longer and deeper RNN. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5457–5466 (2018)
Liu, H., Tu, J., Liu, M.: Two-stream 3d convolutional neural network for skeleton-based action recognition, May 2017
Liu, M., Liu, H., Chen, C.: Enhanced skeleton visualization for view invariant human action recognition. Pattern Recogn. 68, 346–362 (2017)
Li, B., Dai, Y., Cheng, X., Chen, H., Lin, Y., He, M.: Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN. In: 2017 IEEE International Conference on Multimedia Expo Workshops (ICMEW), pp. 601–604 (2017)
Tang, Y., Tian, Y., Lu, J., Li, P., Zhou, J.: Deep progressive reinforcement learning for skeleton-based action recognition. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5323–5332 (2018)
Kim, T.S., Reiter, A.: Interpretable 3d human action analysis with temporal convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1623–1631 (2017)
Acknowledgments
The work described in this paper was partially supported by the National Natural Science Foundation of China (Grant no. 61772093), Chongqing Research Program of Basic Science and Frontier Technology (Grant no. cstc2018jcyjAX0410), and the Fundamental Research Funds for the Central Universities (Grant no. 2021CDJQY-018).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, X. et al. (2021). Skeleton-Based Action Recognition with Improved Graph Convolution Network. In: Feng, J., Zhang, J., Liu, M., Fang, Y. (eds) Biometric Recognition. CCBR 2021. Lecture Notes in Computer Science(), vol 12878. Springer, Cham. https://doi.org/10.1007/978-3-030-86608-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-86608-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86607-5
Online ISBN: 978-3-030-86608-2
eBook Packages: Computer ScienceComputer Science (R0)