Accès libre

Data-driven Optimization of Folk Dance Inheritance and Protection Strategies and Their Realization Paths

Wenjing Zhou

Wenjing Zhou

Dance Academy of Nanjing University of ArtsNanjing, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Zhou, Wenjing
  
26 sept. 2025
Data-driven Optimization of Folk Dance Inheritance and Protection Strategies and Their Realization Paths's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Télécharger la couverture
Publié en ligne: 26 sept. 2025
Reçu: 12 janv. 2025
Accepté: 27 avr. 2025
DOI: https://doi.org/10.2478/amns-2025-1056
Mots clés
© 2025 Wenjing Zhou, published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

MTSGCN single-flow human action recognition framework
MTSGCN single-flow human action recognition framework

Figure 2.

MTSGCN network structure
MTSGCN network structure

Figure 3.

Data set 1 accuracy changes
Data set 1 accuracy changes

Figure 4.

Data set 2 accuracy changes
Data set 2 accuracy changes

Figure 5.

Data set 1 identifies the confusion matrix of the result
Data set 1 identifies the confusion matrix of the result

Figure 6.

Data set 2 identifies the confusion matrix of the result
Data set 2 identifies the confusion matrix of the result

Figure 7.

The accuracy of the 9 types of individual folk dancing
The accuracy of the 9 types of individual folk dancing

Figure 8.

The results of the action recognition accuracy of nine pairs of pairs
The results of the action recognition accuracy of nine pairs of pairs

Results of the effectiveness of the overall network structure

Model top-1 Model size(MB)
Baseline model 83.46 65.92
MTSGCN 92.21 252.23

The accuracy of three input modes on two data sets

Data set Network model Rgb(%) Flow(%) Rgb+Flow(%)
Data set 1 Network model 1 82.84 86.11 88.37
Network model 2 83.78 87.46 93.81
Network model 3 86.44 91.75 97.41
Data set 2 Network model 1 59.12 61.08 72.09
Network model 2 61.62 64.13 73.05
Network model 3 65.95 66.05 77.39

Different methods are based on data set 1 and number 2

Model Data set 1 Data set 2
ST-ResNet 87.81 80.55
KVMF 84.23 74.08
TBN 91.16 72.11
ActionVLAD 85.62 73.32
STRA-Net 78.21 71.73
MTSGCN 97.06 89.01
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