Multi-scale Dilated Attention Graph Convolutional Network for Skeleton-Based Action Recognition

被引:1
作者
Shu, Yang [1 ]
Li, Wanggen [1 ]
Li, Doudou [1 ]
Gao, Kun [1 ]
Jie, Biao [1 ]
机构
[1] Anhui Normal Univ, Wuhu, Peoples R China
来源
PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT I | 2024年 / 14425卷
基金
中国国家自然科学基金;
关键词
Action Recognition; Multi-scale; Semantic Information; Dilated Attention; Lightweight;
D O I
10.1007/978-981-99-8429-9_2
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Due to the small size, anti-interference and strong robustness of skeletal data, research on human skeleton-based action recognition has become a mainstream. However, due to the incomplete utilization of semantic information and insufficient time modeling, most methods may not be able to fully explore the connections between non-adjacent joints in the spatial or temporal dimensions. Therefore, we propose a Multiscale Dilated Attention Graph Convolutional Network for Skeleton-Based Action Recognition (MDKA-GCN) to solve the above problems. In the spatial configuration, we explicitly introduce the channel graph composed of high-level semantics (joint type and frame index) of joints into the network to enhance the representation ability of spatiotemporal features. MDKA-GCN uses joint-level, velocity-level and bone-level graphs to more deeply mine the hidden features of human skeletons. In the time configuration, two lightweight multi-scale strategies are proposed, which can be more robust to time changes. Extensive experiments on NTUR-GB+D 60 datasets and NTU-RGB+D 120 datasets show that MDKA-GCN has reached an advanced level, and surpasses the performance of most lightweight SOTA methods.
引用
收藏
页码:16 / 28
页数:13
相关论文
共 24 条
[1]   Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset [J].
Carreira, Joao ;
Zisserman, Andrew .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :4724-4733
[2]   Extremely Lightweight Skeleton-Based Action Recognition With ShiftGCN plus [J].
Cheng, Ke ;
Zhang, Yifan ;
He, Xiangyu ;
Cheng, Jian ;
Lu, Hanqing .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 :7333-7348
[3]   Skeleton-Based Action Recognition with Shift Graph Convolutional Network [J].
Cheng, Ke ;
Zhang, Yifan ;
He, Xiangyu ;
Chen, Weihan ;
Cheng, Jian ;
Lu, Hanqing .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :180-189
[4]   PYSKL: Towards Good Practices for Skeleton Action Recognition [J].
Duan, Haodong ;
Wang, Jiaqi ;
Chen, Kai ;
Lin, Dahua .
PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, :7351-7354
[5]  
Howard AG, 2017, Arxiv, DOI arXiv:1704.04861
[6]  
Guo MH, 2022, Arxiv, DOI [arXiv:2202.09741, 10.48550/arXiv.2202.09741]
[7]  
Hu J, 2018, PROC CVPR IEEE, P7132, DOI [10.1109/TPAMI.2019.2913372, 10.1109/CVPR.2018.00745]
[8]   Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction [J].
Li, Maosen ;
Chen, Siheng ;
Chen, Xu ;
Zhang, Ya ;
Wang, Yanfeng ;
Tian, Qi .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (06) :3316-3333
[9]   NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding [J].
Liu, Jun ;
Shahroudy, Amir ;
Perez, Mauricio ;
Wang, Gang ;
Duan, Ling-Yu ;
Kot, Alex C. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2020, 42 (10) :2684-2701
[10]   Skeleton-based Human Action Recognition via Large-kernel Attention Graph Convolutional Network [J].
Liu, Yanan ;
Zhang, Hao ;
Li, Yanqiu ;
He, Kangjian ;
Xu, Dan .
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2023, 29 (05) :2575-2585