Research Progress in Skeleton-Based Human Action Recognition

被引：0
|
作者：
Liu B. [1 ,2 ]
Zhou S. [3 ]
Dong J. [1 ]
Xie M. [3 ]
Zhou S. [3 ]
Zheng T. [1 ]
Zhang S. [5 ]
Ye X. [6 ]
Wang X. [1 ]
机构：
[1] School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou
[2] Key Laboratory of Public Security Informatization Application Based on Big Data Architecture, Ministry of Public Security, Hangzhou
[3] School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou
[4] Department of Computer and Information Security, Zhejiang Police College, Hangzhou
[5] College of Computer Science and Technology, Zhejiang University, Hangzhou
[6] Institute of Big Data and Information Technology, Wenzhou University, Wenzhou
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2023年 / 35卷 / 09期
关键词：
action recognition; deep learning; graph convolutional network; skeleton feature extraction;
D O I：
10.3724/SP.J.1089.2023.19640
中图分类号：
学科分类号：
摘要：
In recent years, with the development of deep learning technology, many novel skeleton-based human action recognition algorithms have been proposed, which has greatly promoted the development of this field. This paper aims to give a comprehensive and detailed summary of the main datasets and algorithms in the skeleton-based human action recognition field. Firstly, the main skeleton-related datasets such as NTU, Kinetics-Skeleton, and SYSU 3DHOI are reviewed. Secondly, the skeleton-based human action recognition algorithms are summarized into three categories, i.e., supervised learning-based, semi-supervised learning-based, and unsupervised learning-based, the main algorithms of each category are further introduced and compared. Finally, challenges that the field is currently facing, i.e., over-reliance on big data, large computing power, and large models, are concluded, and three future development directions are proposed to alleviate the above challenges: high-precision skeleton dataset construction, fine-grained skeleton-based action recognition, and skeleton-based action recognition with data-efficient learning. © 2023 Institute of Computing Technology. All rights reserved.
引用
收藏
页码：1299 / 1322
页数：23
相关论文
共 132 条
  • [1] Zhu Yu, Zhao Jiangkun, Wang Yining, Et al., A review of human action recognition based on deep learning, Acta Automatica Sinica, 42, 6, pp. 848-857, (2016)
  • [2] Donahue J, Hendricks L A, Guadarrama S, Et al., Long-term recurrent convolutional networks for visual recognition and description, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625-2634, (2015)
  • [3] Feichtenhofer C, Pinz A, Zisserman A., Convolutional two-stream network fusion for video action recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933-1941, (2016)
  • [4] Sharma S, Kiros R, Salakhutdinov R., Action recognition using visual attention
  • [5] Tran D, Bourdev L, Fergus R, Et al., Learning spatiotemporal features with 3D convolutional networks, Proceedings of the IEEE International Conference on Computer Vision, pp. 4489-4497, (2015)
  • [6] Yang C Y, Xu Y H, Shi J P, Et al., Temporal pyramid network for action recognition, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 588-597, (2020)
  • [7] Yang X D, Zhang C Y, Tian Y L., Recognizing actions using depth motion maps-based histograms of oriented gradients, Proceedings of the 20th ACM International Conference on Multimedia, pp. 1057-1060, (2012)
  • [8] Yang X D, Tian Y L., Super normal vector for activity recognition using depth sequences, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 804-811, (2014)
  • [9] Chen C, Jafari R, Kehtarnavaz N., Action recognition from depth sequences using depth motion maps-based local binary patterns, Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 1092-1099, (2015)
  • [10] Yan S J, Xiong Y J, Lin D H., Spatial temporal graph convolutional networks for skeleton-based action recognition, Proceedings of the 32nd AAAI Conference on Artificial Intelligence, pp. 7444-7452, (2018)
12345678910