Abstract
Recently, skeleton-based action recognition has modeled the human skeleton as a graph convolution network (GCN), and has achieved remarkable results. However, most of the methods convolute directly on the whole graph, neglecting that the human skeleton is made up of multiple body parts, which cannot accomplish the task well. We recognize that the physical property of bones (i.e., length and direction) can provide identifiable information which helps effectively to build the multi-level network structure. As the existing methods treat the channel domain and the spatial domain with equal importance, many computing resources are wasted on neglectable features. In our paper, we modify the Convolution Block Attention Module (CBAM) and apply it to the adaptive network. By capturing the implicit weighted information in the channel domain and spatial domain, the network can focus more attention on the key channels and nodes. A new two-stream adaptive-attentional subgraph convolution network (2s-AASGCN) is proposed to extract features in the spatio-temporal domain. We validate 2s-AASGCN on two skeleton datasets, i.e., NTU-RGB+D60 and NTU-RGB+D120. Our model achieves excellent results on these two datasets.
Similar content being viewed by others
References
Bo L, Dai Y, Cheng X, Chen H, Yi L, He M (2017) Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN. In: 2017 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp 601–604
Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. In: Computer Vision and Pattern Recognition IEEE
Fernando B, Gavves E, Oramas JM, Ghodrati A, Tuytelaars T (2015) Modeling video evolution for action recognition. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) IEEE Computer Society, pp 5378–5387
Gao X, Hu W, Tang J, Liu J, Guo Z-M (2019) Optimized Skeleton-based action recognition via sparsified graph regression. the 27th ACM International Conference ACM
Gaur U, Zhu Y, Song B, Roy-Chowdhury A (2011) A string of feature graphs model for recognition of complex activities in natural videos. In: 2011 International Conference on Computer Vision, pp 2595–2602
Jie H, Li S, Albanie S, Sun G, Vedaldi A (2018) Gather-excite: exploiting feature context in convolutional neural networks. In: Advances in neural information processing systems, pp 9401–9411
Ke Q, Bennamoun M, An S (2017) A new representation of skeleton sequences for 3d action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3288–3297
Ke Q, Bennamoun M, An S, Sohel F, Boussaid F (2018) Learning clip representations for skeleton-based 3d action recognition. IEEE Trans Image Process, pp 2842–2855
Ke C, Zhang Y, He X, Chen W, Cheng J, Hangqing L (2020) Skeleton-based action recognition with shift graph convolutional network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 183–192
Kim TS, Reiter A (2017) Interpretable 3d human action analysis with temporal convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW), pp 1623–1631
Li M, Chen S, Chen X, Ya Z, Wang Y, Qi T (2019) Actional-structural graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3595–3603
Li S, Li W, Cook C, Ce Z, Gao Y (2018) Independently recurrent neural network (indrnn): building a longer and deeper rnn. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5457–5466
Liao S, Lyons TJ, Yang W, Ni H (2019) Learning stochastic differential equations using RNN with log signature features. arXiv preprint arXiv
Liu H, Juanhui T, Liu M (2017) Two-stream 3d convolutional neural network for skeleton-based action recognition. arXiv preprint arXiv:1705.08106
Liu M, Liu H, Chen C (2017) Enhanced skeleton visualization for view invariant human action recognition Pattern Recogn, pp 346–362
Liu J, Shahroudy A, Dong X, Wang G (2016) Spatio-temporal lstm with trust gates for 3d human action recognition. In: European conference on computer vision, pp 816–833
Liu J, Shahroudy A, Perez ML, Wang G, Duan L-Y, Chichung AK (2019) A large-scale benchmark for 3d human activity understanding. IEEE transactions on pattern analysis and machine intelligence
Liu J, Wang G, Duan L-Y (2017) Skeleton-based human action recognition with global context-aware attention LSTM networks. IEEE Trans Image Process, pp 1586–1599
Liu J, Wang G, Hu P, Duan L-Y, CKot A (2017) Global context-aware attention LSTM Networks for 3D action recognition. IEEE Conference on Computer Vision and Pattern Recognition IEEE
Liu M, Yuan J (2018) Recognizing human actions as the evolution of pose estimation maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1159–1168
Liu Z, Zhang H, Chen Z, Wang Z, Ouyang W (2020) Disentangling and unifying graph convolutions for skeleton-based action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 143–152
Peng W, Hong X, Chen H, Zhao G (2020) Learning graph convolutional network for skeleton-based human action recognition by neural searching. In: AAAI, pp 2669–2676
Shahroudy A, Liu J, Ng T-T, Wang G (2016) Ntu rgb+ d: a large scale dataset for 3d human activity analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1010–1019
Shi H, Meng X, Hwang K-S, Cai B-Y (2020) Behavior fusion for deep reinforcement learning. ISA transactions, pp. 434–444
Shi H, Wu H, Hwang K-S (2020) Adaptive image-based visual servoing using reinforcement learning with fuzzy state coding. IEEE Transactions on Fuzzy Systems
Shi L, Zhang Y, Cheng J, Hanqing L (2019) Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 12026–12035
Shi L, Zhang Y, Cheng J, Hanqing LS (2019) Skeleton-based action recognition with directed graph neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7912–7921
Shi L, Zhang Y, Cheng J, Hanqing L (2019) Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. IEEE Trans Image Process, pp 9532–9545
Si C, Chen W, Wang W, Wang L, Tan T (2019) An attention enhanced graph convolutional lstm network for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1227–1236
Song S, Lan C, Xing J, Zeng W, Liu J (2015) An end-to-end spatio-temporal attention model for human action recognition from skeleton data. arXiv preprint arXiv:1611.06067
Sudha MR, Sriraghav K, Abisheck SS, Jacob SG, Manisha S (2017) Approaches and applications of virtual reality and gesture recognition: a review. International Journal of Ambient Computing and Intelligence (IJACI), pp. 1–18
Tang Y, Yi T, Jiwen L, Li P, Zhou J (2018) Deep progressive reinforcement learning for skeleton-based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5323–5332
Thakkar K, Narayanan PJ (2018) Part-based graph convolutional network for action recognition. arXiv preprint arXiv:180.04983
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998–6008
Vemulapalli R, Arrate F, Chellappa R (2014) Human action recognition by representing 3d skeletons as points in a lie group. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 588–595
Wang F, Jiang M, Qian C, Yang S, Li C, Zhang H, Wang X, Tang X (2017) Residual attention network for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156–3164
Woo S, Park J, Lee J-Y, In SK (2018) Cbam: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3–19
Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. arXiv preprint arXiv:1801.07455
Zhang Xikun, Chang X u, Tao Dacheng (2020) Context aware graph convolution for skeleton-based action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 14333–14342
Zhang P, Lan C, Xing J, Zeng W (2018) View adaptive neural networks for high performance skeleton-based human action recognition. In: IEEE Transactions on Pattern Analysis and Machine Intelligence
Zhang P, Lan C, Xing J, Zeng W, Xue J, Zheng N (2017) View adaptive recurrent neural networks for high performance human action recognition from skeleton data
Zhang P, Lan C, Zeng W, Xing J, Xue J, Zheng N (2020) Semantics-guided neural networks for efficient skeleton-based human action recognition. In: Proc IEEE Conf. Comput. Vis. Pattern Recognit, pp 1112–1121
Acknowledgment
This work was supported by the Natural Science Foundation of Hebei Province Grant No. F2018203390, Qinhuangdao City Science and Technology Research and Development Plan Grant No.202003B043 and Xinjiang Uygur Autonomous Region University Scientific Research Project (Key Natural Science Project) XJEDU2021I029. The authors also gratefully acknowledge the helpful comments and suggestions of the reviewers, which have improved the paper.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, X., Meng, F., Zhao, F. et al. Two-stream adaptive-attentional subgraph convolution networks for skeleton-based action recognition. Multimed Tools Appl 81, 4821–4838 (2022). https://doi.org/10.1007/s11042-021-11026-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11026-4