Accès libre

Spatial–temporal graph neural network based on node attention

Qiang Li

Qiang Li

School of Electronic and Information Engineering, South China University of TechnologyGuangzhou, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Li, Qiang
, 
Jun Wan

Jun Wan

Midea Intelligent Life Research Institute, Midea Real Estate Holding LimitedFoshan, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Wan, Jun
, 
Wucong Zhang

Wucong Zhang

Midea Intelligent Life Research Institute, Midea Real Estate Holding LimitedFoshan, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Zhang, Wucong
 et 
Qian Long Kweh

Qian Long Kweh

Canadian University Dubai
Recherchez cet auteur sur
Sciendo|Google Scholar
Kweh, Qian Long
  
08 avr. 2022
Spatial–temporal graph neural network based on node attention's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Télécharger la couverture
Publié en ligne: 08 avr. 2022
Pages: 703 - 712
Reçu: 23 mai 2021
Accepté: 27 sept. 2021
DOI: https://doi.org/10.2478/amns.2022.1.00005
Mots clés
© 2021 Qiang Li et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Fig. 1

(a) Spatial–temporal skeletal graph. (b) Partitioning strategy graph.
(a) Spatial–temporal skeletal graph. (b) Partitioning strategy graph.

Fig. 2

Structure diagram of NA-STGCN. GCN, graph convolutional neural network; NA-STGCN, node attention spatial–temporal graph convolutional neural network.
Structure diagram of NA-STGCN. GCN, graph convolutional neural network; NA-STGCN, node attention spatial–temporal graph convolutional neural network.

Fig. 3

Change curve of loss values. NA-STGCN, node attention spatial–temporal graph convolutional neural network; ST-GCN, spatial–temporal graph convolutional neural network.
Change curve of loss values. NA-STGCN, node attention spatial–temporal graph convolutional neural network; ST-GCN, spatial–temporal graph convolutional neural network.

Fig. 4

Node activation response maps: (a) top left: ST-GCN clapping action; (b) top right: NA-STGCN clapping action; (c) bottom left: ST-GCN brushing action; (d) bottom right: NA-STGCN brushing action. NA-STGCN, node attention spatial–temporal graph convolutional neural network; ST-GCN, spatial–temporal graph convolutional neural network.
Node activation response maps: (a) top left: ST-GCN clapping action; (b) top right: NA-STGCN clapping action; (c) bottom left: ST-GCN brushing action; (d) bottom right: NA-STGCN brushing action. NA-STGCN, node attention spatial–temporal graph convolutional neural network; ST-GCN, spatial–temporal graph convolutional neural network.

Comparison with representative methods (%)_

Model CS CV
Two-Stream 3DCNN [8] 66.8 72.6
TCN [22] 74.3 83.1
Clip + CNN + MTLN [23] 79.6 84.8
VA-LSTM [10] 79.4 87.6
ST-GCN [13] 81.5 88.3
NA-STGCN (ours) 85.8 89.3
Langue:
Anglais
Périodicité:
1 fois par an
Sujets de la revue:
Sciences de la vie, Sciences de la vie, autres, Mathématiques, Mathématiques appliquées, Mathématiques générales, Physique, Physique, autres
RSS Feed de la revue