Skeleton-based Action Recognition Using Two-stream Graph Convolutional Network with Pose Refinement

Biao Zheng; Luefeng Chen; Min Wu; Witold Pedrycz; Kaoru Hirota

doi:10.23919/CCC55666.2022.9901587

Skeleton-based Action Recognition Using Two-stream Graph Convolutional Network with Pose Refinement

Biao Zheng, Luefeng Chen^*, Min Wu, Witold Pedrycz, Kaoru Hirota

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

With the development of science and technology, graph convolutional network has made great progress in improving the accuracy of action recognition. However, there still exists some deficiencies in current methods. Firstly, the human skeleton point coordinates entering into the network are barely refined, which may cause large error. Secondly, the second-order infor-mation(the length and direction of bones), which can reflect action characteristics discriminatively, is rarely used. To solve the above issues, a two stream graph convolutional network with pose refinement for skeleton based action recognition is proposed. Besides, we use an adaptive block to to help improve the accuracy. We test our method on Kinetics dataset and the experiment show it can get better results than some recent methods, which plays a positive role in future research.

Original language	English
Title of host publication	Proceedings of the 41st Chinese Control Conference, CCC 2022
Editors	Zhijun Li, Jian Sun
Publisher	IEEE Computer Society
Pages	6353-6356
Number of pages	4
ISBN (Electronic)	9789887581536
DOIs	https://doi.org/10.23919/CCC55666.2022.9901587
Publication status	Published - 2022
Externally published	Yes
Event	41st Chinese Control Conference, CCC 2022 - Hefei, China Duration: 25 Jul 2022 → 27 Jul 2022

Publication series

Name	Chinese Control Conference, CCC
Volume	2022-July
ISSN (Print)	1934-1768
ISSN (Electronic)	2161-2927

Conference

Conference	41st Chinese Control Conference, CCC 2022
Country/Territory	China
City	Hefei
Period	25/07/22 → 27/07/22

Keywords

Adaptive block
Graph convolutional network
Pose refinement
Skeleton based action recognition

Access to Document

10.23919/CCC55666.2022.9901587

Cite this

Zheng, B., Chen, L., Wu, M., Pedrycz, W., & Hirota, K. (2022). Skeleton-based Action Recognition Using Two-stream Graph Convolutional Network with Pose Refinement. In Z. Li, & J. Sun (Eds.), Proceedings of the 41st Chinese Control Conference, CCC 2022 (pp. 6353-6356). (Chinese Control Conference, CCC; Vol. 2022-July). IEEE Computer Society. https://doi.org/10.23919/CCC55666.2022.9901587

@inproceedings{7490ec5339e948aabb872856a77e1813,

title = "Skeleton-based Action Recognition Using Two-stream Graph Convolutional Network with Pose Refinement",

abstract = "With the development of science and technology, graph convolutional network has made great progress in improving the accuracy of action recognition. However, there still exists some deficiencies in current methods. Firstly, the human skeleton point coordinates entering into the network are barely refined, which may cause large error. Secondly, the second-order infor-mation(the length and direction of bones), which can reflect action characteristics discriminatively, is rarely used. To solve the above issues, a two stream graph convolutional network with pose refinement for skeleton based action recognition is proposed. Besides, we use an adaptive block to to help improve the accuracy. We test our method on Kinetics dataset and the experiment show it can get better results than some recent methods, which plays a positive role in future research.",

keywords = "Adaptive block, Graph convolutional network, Pose refinement, Skeleton based action recognition",

author = "Biao Zheng and Luefeng Chen and Min Wu and Witold Pedrycz and Kaoru Hirota",

note = "Publisher Copyright: {\textcopyright} 2022 Technical Committee on Control Theory, Chinese Association of Automation.; 41st Chinese Control Conference, CCC 2022 ; Conference date: 25-07-2022 Through 27-07-2022",

year = "2022",

doi = "10.23919/CCC55666.2022.9901587",

language = "English",

series = "Chinese Control Conference, CCC",

publisher = "IEEE Computer Society",

pages = "6353--6356",

editor = "Zhijun Li and Jian Sun",

booktitle = "Proceedings of the 41st Chinese Control Conference, CCC 2022",

address = "United States",

}

Zheng, B, Chen, L, Wu, M, Pedrycz, W & Hirota, K 2022, Skeleton-based Action Recognition Using Two-stream Graph Convolutional Network with Pose Refinement. in Z Li & J Sun (eds), Proceedings of the 41st Chinese Control Conference, CCC 2022. Chinese Control Conference, CCC, vol. 2022-July, IEEE Computer Society, pp. 6353-6356, 41st Chinese Control Conference, CCC 2022, Hefei, China, 25/07/22. https://doi.org/10.23919/CCC55666.2022.9901587

Skeleton-based Action Recognition Using Two-stream Graph Convolutional Network with Pose Refinement. / Zheng, Biao; Chen, Luefeng; Wu, Min et al.
Proceedings of the 41st Chinese Control Conference, CCC 2022. ed. / Zhijun Li; Jian Sun. IEEE Computer Society, 2022. p. 6353-6356 (Chinese Control Conference, CCC; Vol. 2022-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Skeleton-based Action Recognition Using Two-stream Graph Convolutional Network with Pose Refinement

AU - Zheng, Biao

AU - Chen, Luefeng

AU - Wu, Min

AU - Pedrycz, Witold

AU - Hirota, Kaoru

PY - 2022

Y1 - 2022

N2 - With the development of science and technology, graph convolutional network has made great progress in improving the accuracy of action recognition. However, there still exists some deficiencies in current methods. Firstly, the human skeleton point coordinates entering into the network are barely refined, which may cause large error. Secondly, the second-order infor-mation(the length and direction of bones), which can reflect action characteristics discriminatively, is rarely used. To solve the above issues, a two stream graph convolutional network with pose refinement for skeleton based action recognition is proposed. Besides, we use an adaptive block to to help improve the accuracy. We test our method on Kinetics dataset and the experiment show it can get better results than some recent methods, which plays a positive role in future research.

AB - With the development of science and technology, graph convolutional network has made great progress in improving the accuracy of action recognition. However, there still exists some deficiencies in current methods. Firstly, the human skeleton point coordinates entering into the network are barely refined, which may cause large error. Secondly, the second-order infor-mation(the length and direction of bones), which can reflect action characteristics discriminatively, is rarely used. To solve the above issues, a two stream graph convolutional network with pose refinement for skeleton based action recognition is proposed. Besides, we use an adaptive block to to help improve the accuracy. We test our method on Kinetics dataset and the experiment show it can get better results than some recent methods, which plays a positive role in future research.

KW - Adaptive block

KW - Graph convolutional network

KW - Pose refinement

KW - Skeleton based action recognition

UR - http://www.scopus.com/inward/record.url?scp=85140448542&partnerID=8YFLogxK

U2 - 10.23919/CCC55666.2022.9901587

DO - 10.23919/CCC55666.2022.9901587

M3 - Conference contribution

AN - SCOPUS:85140448542

T3 - Chinese Control Conference, CCC

SP - 6353

EP - 6356

BT - Proceedings of the 41st Chinese Control Conference, CCC 2022

A2 - Li, Zhijun

A2 - Sun, Jian

PB - IEEE Computer Society

T2 - 41st Chinese Control Conference, CCC 2022

Y2 - 25 July 2022 through 27 July 2022

ER -

Skeleton-based Action Recognition Using Two-stream Graph Convolutional Network with Pose Refinement

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this