Abstract
The static relationship between joints and the dynamic importance of joints leads to high accuracy in skeletal action recognition. Nevertheless, existing methods define the graph structure beforehand by skeletal patterns, so they cannot capture features considering the relationship between joints specific to actions. Moreover, the importance of joints is expected to be different for each action. We propose spatial-temporal attention graph convolutional networks (STA-GCN). It acquires an attention edge that represents a static relationship between joints for each action and an attention node that represents the dynamic importance of joints for each time. STA-GCN is the first method to consider joint importance and relationship at the same time. The proposed method consists of multiple networks, that reflect the difference of spatial (coordinates) and temporal (velocity and acceleration) characteristics as mechanics-stream. We aggregate these network predictions as final result. We show the potential that the attention edge and node can be easily applied to existing methods and improve the performance. Experimental results with NTU-RGB+D and NTU-RGB+D120 demonstrate that it is possible to obtain a attention edge and node specific to the action that can explain behavior and achieves state-of-the-art performances.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Soo Kim, T., Reiter, A.: Interpretable 3D human action analysis with temporal convolutional networks. In: Computer Vision and Pattern Recognition Workshop (CVPRW) (2017)
Mengyuan, L., Hong, L., Chen, C.: Enhanced skeleton visualization for view invariant human action recognition. Pattern Recogn. 68, 346–362 (2017)
Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: A new representation of skeleton sequences for 3D action recognition. In: Computer Vision and Pattern Recognition (CVPR) (2017)
Jun, L., Amir, S., Gang, W., Ling-Yu, D., Alex, K.: Skeleton-based online action prediction using scale selection network. Trans. Pattern Anal. Mach. Intell. (TPAMI) 42, 1453–1467 (2019)
Qiuhong, K., Mohammed, B., Senjian, A., Ferdous, S., Boussaid, F.: Learning clip representations for skeleton-based 3D action recognition. Trans. Image Process. (TIP) 27, 2842–2855 (2018)
Caetano, C., Sena, J., Brémond, F., dos Santos, J.A., Schwartz, W.R.: SkeleMotion: a new representation of skeleton joint sequences based on motion information for 3D action recognition. In: Advanced Video and Signal-based Surveillance (AVSS) (2019)
Yong, D., Wei, W., Liang, W.: Hierarchical recurrent neural network for skeleton based action recognition. In: Computer Vision and Pattern Recognition (CVPR) (2015)
Amir, S., Jun, L., Tian-Tsong, N., Gang, W.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: Computer Vision and Pattern Recognition (CVPR) (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
Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Association for the Advancement of Artificial Intelligence (AAAI) (2017)
Jun, L., Amir, S., Dong, X., Alex, K., Gang, W.: Skeleton-based action recognition using spatio-temporal LSTM network with trust gates. Trans. Pattern Anal. Mach. Intell. (TPAMI) 40, 3007–3021 (2018)
Liu, J., Wang, G., Hu, P., Duan, L.Y., Kot, A.C.: Global context-aware attention LSTM networks for 3D action recognition. In: Computer Vision and Pattern Recognition (CVPR) (2017)
Jun, L., Gang, W., Duan, L.-Y., Abdiyeva, K., Kot, A.C.: Skeleton-based human action recognition with global context-aware attention LSTM networks. Trans. Image Process. (TIP) 27, 1586–1599 (2018)
Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Association for the Advancement of Artificial Intelligence (AAAI) (2018)
Si, C., Jing, Y., Wang, W., Wang, L., Tan, T.: Skeleton-based action recognition with spatial reasoning and temporal stack learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 106–121. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_7
Thakkar, K., Narayanan, P.J.: Part-based graph convolutional network for action recognition. In: The British Machine Vision Conference (BMVC) (2018)
Maosen, L., Siheng, C., Xu, C., Ya, Z., Yanfeng, W., Tian, Q.: Actional-structural graph convolutional networks for skeleton-based action recognition. In: Computer Vision and Pattern Recognition (CVPR) (2019)
Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Computer Vision and Pattern Recognition (CVPR) (2019)
Si, C., Chen, W., Wang, W., Wang, L., Tan, T.: An attention enhanced graph convolutional LSTM network for skeleton-based action recognition. In: Computer Vision and Pattern Recognition (CVPR) (2019)
Lei, S., Yifan, Z., Jian, C., Hanqing, L.: Skeleton-based action recognition with directed graph neural networks. In: Computer Vision and Pattern Recognition (CVPR) (2019)
Hussein, M.E., Torki, M., Gowayyed, M.A., El-Saban, M.: Human action recognition using a temporal hierarchy of covariance descriptors on 3D joint locations. In: International Joint Conference on Artificial Intelligence (IJCAI) (2013)
Raviteja, V., Felipe, A., Rama, C.: Human action recognition by representing 3D skeletons as points in a lie group. In: Computer Vision and Pattern Recognition (CVPR) (2014)
Basura, F., Gavves, E., Oramas, M.J., Amir, G., Tinne, T.: Modeling video evolution for action recognition. In: Computer Vision and Pattern Recognition (CVPR) (2015)
Joan, B., Wojciech, Z., Arthur, S., Yann, L.: Spectral networks and locally connected networks on graphs. In: International Conference on Learning Representations (ICLR) (2014)
Michaël, D., Xavier, B., Pierre, V.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems (NIPS) (2016)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR) (2017)
Duvenaud, D., et al.: Convolutional networks on graphs for learning molecular fingerprints. In: Advances in Neural Information Processing Systems (NIPS) (2015)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: International Conference on Machine Learning (ICML) (2017)
Yao, L., Mao, C., Luo, Y.: Graph convolutional networks for text classification. In: Association for the Advancement of Artificial Intelligence (AAAI) (2019)
Xiang, Z., Junbo, Z., Yann, L.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems (NIPS) (2015)
Wang, X., Gupta, A.: Videos as space-time region graphs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 413–431. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_25
Qi, S., Wang, W., Jia, B., Shen, J., Zhu, S.-C.: Learning human-object interactions by graph parsing neural networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 407–423. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_25
Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 711–727. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_42
Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: Computer Vision and Pattern Recognition (CVPR) (2019)
Hiroshi, F., Tsubasa, H., Takayoshi, Y., Hironobu, F.: Attention branch network: learning of attention mechanism for visual explanation. In: Computer Vision and Pattern Recognition (CVPR) (2019)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Computer Vision and Pattern Recognition (CVPR) (2016)
R., S.R., Michael, C., Abhishek, D., Ramakrishna, V., Devi, P., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: International Conference on Computer Vision (ICCV) (2017)
Chattopadhyay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks. In: Winter Conference on Applications of Computer Vision (WACV) (2017)
Jun, L., Amir, S., Mauricio, P., Gang, W., Duan, L.Y., Kot, A.C.: NTU RGB+D 120: a large-scale benchmark for 3D human activity understanding. Trans. Pattern Anal. Mach. Intell. (TPAMI) 42, 1–18 (2019)
Hu, J.F., Zheng, W.S., Ma, L., Wang, G., Lai, J., Zhang, J.: Early action prediction by soft regression. Trans. Pattern Anal. Mach. Intell. (TPAMI) 41, 2568–2583 (2019)
Jianfang, H., Wei-Shi, Z., Jian-Huang, L., Jianguo, Z.: Jointly learning heterogeneous features for RGB-D activity recognition. In: Computer Vision and Pattern Recognition (CVPR) (2015)
Liu, M., Yuan, J.: Recognizing human actions as the evolution of pose estimation maps. In: Computer Vision and Pattern Recognition (CVPR) (2018)
Caetano, C., Brémond, F., Schwartz, W.R.: Skeleton image representation for 3D action recognition based on tree structure and reference joints. In: Conference on Graphics, Patterns and Images (SIBGRAPI) (2019)
Acknowledgement
This paper is based on results obtained from a project, JPNP20006, commissioned by the New Energy and Industrial Technology Development Organization (NEDO).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Shiraki, K., Hirakawa, T., Yamashita, T., Fujiyoshi, H. (2021). Spatial Temporal Attention Graph Convolutional Networks with Mechanics-Stream for Skeleton-Based Action Recognition. In: Ishikawa, H., Liu, CL., Pajdla, T., Shi, J. (eds) Computer Vision – ACCV 2020. ACCV 2020. Lecture Notes in Computer Science(), vol 12626. Springer, Cham. https://doi.org/10.1007/978-3-030-69541-5_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-69541-5_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69540-8
Online ISBN: 978-3-030-69541-5
eBook Packages: Computer ScienceComputer Science (R0)