MSA-GCN: Multiscale Adaptive Graph Convolution Network for gait emotion recognition

被引:15
作者
Yin, Yunfei [1 ]
Jing, Li [1 ]
Huang, Faliang [2 ]
Yang, Guangchao [1 ]
Wang, Zhuowei [3 ]
机构
[1] Chongqing Univ, Chongqing, Peoples R China
[2] Nanning Normal Univ, Guangxi Key Lab Human Machine Interact & Intellige, Nanning, Peoples R China
[3] CSIRO, Space & Astron, Marshfield, Australia
关键词
Emotion recognition; Gait emotion recognition; Graph convolutional network; Multiscale mapping;
D O I
10.1016/j.patcog.2023.110117
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Gait emotion recognition plays a crucial role in the intelligent system. Most existing approaches identify emotions by focusing on local actions over time. However, some valuable observational facts that the effective distances of different emotions in the time domain are different, and the local actions during walking are quite similar, are put aside in those methods. And this ignorance often ends up impairing performance of emotion recognition. To address the issues, a novel model, named MSA-GCN (MultiScale Adaptive Graph Convolution Network), is proposed to utilize the valuable observational knowledge for improving emotion recognition performance. In the proposed model, an adaptive spatio-temporal graph convolution is designed to dynamically select convolution kernels to learn the spatio-temporal features of different emotions. Moreover, a Cross-Scale Mapping Interaction mechanism (CSMI) is proposed to construct an adaptive adjacency matrix for high-quality aggregation of the multiscale information. Extensive experimental results on public datasets indicate that, compared with the state-of-the-art methods, the proposed approach achieves better performance in terms of emotion recognition accuracy, and shows the proposed approach is promising.
引用
收藏
页数:11
相关论文
共 50 条
[1]  
Arunnehru J, 2017, STUD COMPUT INTELL, V660, P321, DOI 10.1007/978-3-319-44790-2_15
[2]  
Bhatia Yajurv, 2021, 2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)., P214, DOI 10.1109/ICCICC53683.2021.9811330
[3]  
Bhattacharya U, 2020, Img Proc Comp Vis Re, V12355, P145, DOI 10.1007/978-3-030-58607-2_9
[4]  
Bhattacharya U, 2020, AAAI CONF ARTIF INTE, V34, P1342
[5]  
Chao HQ, 2019, AAAI CONF ARTIF INTE, P8126
[6]   Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition [J].
Chen, Yuxin ;
Zhang, Ziqi ;
Yuan, Chunfeng ;
Li, Bing ;
Deng, Ying ;
Hu, Weiming .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :13339-13348
[7]  
Crenn A, 2016, INT CONF 3D IMAG
[8]   Prediction of externalizing behavior problems from early to middle childhood: The role of parental socialization and emotion expression [J].
Denham, SA ;
Workman, E ;
Cole, PM ;
Weissbrod, C ;
Kendziora, KT ;
Zahn-Waxler, C .
DEVELOPMENT AND PSYCHOPATHOLOGY, 2000, 12 (01) :23-45
[9]  
Fan C, 2020, PROC CVPR IEEE, P14213, DOI 10.1109/CVPR42600.2020.01423
[10]  
Gavrilova M.L., 2021, Research anthology on rehabilitation practices and therapy, P653