Home > Research > Publications & Outputs > Attention module-based spatial-temporal graph c...

Electronic data

  • Attention module paper

    Rights statement: Yinghui Kong, Li Li, Ke Zhang, Qiang Ni, and Jungong Han "Attention module-based spatial–temporal graph convolutional networks for skeleton-based action recognition," Journal of Electronic Imaging 28(4), 043032 (30 August 2019). https://doi.org/10.1117/1.JEI.28.4.043032 Copyright notice format: Copyright 2019 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.

    Accepted author manuscript, 2.47 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Attention module-based spatial-temporal graph convolutional networks for skeleton-based action recognition

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Attention module-based spatial-temporal graph convolutional networks for skeleton-based action recognition. / Kong, Y.; Li, L.; Zhang, K. et al.

In: Journal of Electronic Imaging, Vol. 28, No. 4, 043032, 30.08.2019.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Kong Y, Li L, Zhang K, Ni Q, Han J. Attention module-based spatial-temporal graph convolutional networks for skeleton-based action recognition. Journal of Electronic Imaging. 2019 Aug 30;28(4):043032. doi: 10.1117/1.JEI.28.4.043032

Author

Kong, Y. ; Li, L. ; Zhang, K. et al. / Attention module-based spatial-temporal graph convolutional networks for skeleton-based action recognition. In: Journal of Electronic Imaging. 2019 ; Vol. 28, No. 4.

Bibtex

@article{34523f6a2669498dbedaea6b373d7d57,
title = "Attention module-based spatial-temporal graph convolutional networks for skeleton-based action recognition",
abstract = "Skeleton-based action recognition is a significant direction of human action recognition, because the skeleton contains important information for recognizing action. The spatial-temporal graph convolutional networks (ST-GCN) automatically learn both the temporal and spatial features from the skeleton data and achieve remarkable performance for skeleton-based action recognition. However, ST-GCN just learns local information on a certain neighborhood but does not capture the correlation information between all joints (i.e., global information). Therefore, we need to introduce global information into the ST-GCN. We propose a model of dynamic skeletons called attention module-based-ST-GCN, which solves these problems by adding attention module. The attention module can capture some global information, which brings stronger expressive power and generalization capability. Experimental results on two large-scale datasets, Kinetics and NTU-RGB+D, demonstrate that our model achieves significant improvements over previous representative methods. {\textcopyright} 2019 SPIE and IS&T.",
keywords = "action recognition, attention module, nonlocal neural network, spatial-temporal graph convolution network, Convolution, Large dataset, Action recognition, Convolutional networks, Generalization capability, Human-action recognition, Large-scale datasets, Nonlocal, Spatial temporals, Musculoskeletal system",
author = "Y. Kong and L. Li and K. Zhang and Q. Ni and J. Han",
note = "Yinghui Kong, Li Li, Ke Zhang, Qiang Ni, and Jungong Han {"}Attention module-based spatial–temporal graph convolutional networks for skeleton-based action recognition,{"} Journal of Electronic Imaging 28(4), 043032 (30 August 2019). https://doi.org/10.1117/1.JEI.28.4.043032 Copyright notice format: Copyright 2019 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. DOI abstract link format: http://dx.doi.org/DOI# (Note: The DOI can be found on the title page or online abstract page of any SPIE article.) ",
year = "2019",
month = aug,
day = "30",
doi = "10.1117/1.JEI.28.4.043032",
language = "English",
volume = "28",
journal = "Journal of Electronic Imaging",
issn = "1017-9909",
publisher = "SPIE",
number = "4",

}

RIS

TY - JOUR

T1 - Attention module-based spatial-temporal graph convolutional networks for skeleton-based action recognition

AU - Kong, Y.

AU - Li, L.

AU - Zhang, K.

AU - Ni, Q.

AU - Han, J.

N1 - Yinghui Kong, Li Li, Ke Zhang, Qiang Ni, and Jungong Han "Attention module-based spatial–temporal graph convolutional networks for skeleton-based action recognition," Journal of Electronic Imaging 28(4), 043032 (30 August 2019). https://doi.org/10.1117/1.JEI.28.4.043032 Copyright notice format: Copyright 2019 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. DOI abstract link format: http://dx.doi.org/DOI# (Note: The DOI can be found on the title page or online abstract page of any SPIE article.)

PY - 2019/8/30

Y1 - 2019/8/30

N2 - Skeleton-based action recognition is a significant direction of human action recognition, because the skeleton contains important information for recognizing action. The spatial-temporal graph convolutional networks (ST-GCN) automatically learn both the temporal and spatial features from the skeleton data and achieve remarkable performance for skeleton-based action recognition. However, ST-GCN just learns local information on a certain neighborhood but does not capture the correlation information between all joints (i.e., global information). Therefore, we need to introduce global information into the ST-GCN. We propose a model of dynamic skeletons called attention module-based-ST-GCN, which solves these problems by adding attention module. The attention module can capture some global information, which brings stronger expressive power and generalization capability. Experimental results on two large-scale datasets, Kinetics and NTU-RGB+D, demonstrate that our model achieves significant improvements over previous representative methods. © 2019 SPIE and IS&T.

AB - Skeleton-based action recognition is a significant direction of human action recognition, because the skeleton contains important information for recognizing action. The spatial-temporal graph convolutional networks (ST-GCN) automatically learn both the temporal and spatial features from the skeleton data and achieve remarkable performance for skeleton-based action recognition. However, ST-GCN just learns local information on a certain neighborhood but does not capture the correlation information between all joints (i.e., global information). Therefore, we need to introduce global information into the ST-GCN. We propose a model of dynamic skeletons called attention module-based-ST-GCN, which solves these problems by adding attention module. The attention module can capture some global information, which brings stronger expressive power and generalization capability. Experimental results on two large-scale datasets, Kinetics and NTU-RGB+D, demonstrate that our model achieves significant improvements over previous representative methods. © 2019 SPIE and IS&T.

KW - action recognition

KW - attention module

KW - nonlocal neural network

KW - spatial-temporal graph convolution network

KW - Convolution

KW - Large dataset

KW - Action recognition

KW - Convolutional networks

KW - Generalization capability

KW - Human-action recognition

KW - Large-scale datasets

KW - Nonlocal

KW - Spatial temporals

KW - Musculoskeletal system

U2 - 10.1117/1.JEI.28.4.043032

DO - 10.1117/1.JEI.28.4.043032

M3 - Journal article

VL - 28

JO - Journal of Electronic Imaging

JF - Journal of Electronic Imaging

SN - 1017-9909

IS - 4

M1 - 043032

ER -