arbiter
JournalsPricingAccount

Research on Recognition Method of Non-Legacy Dance Action Based on Multi-Feature Fusion

Jing Yang et al.

International Journal of Intelligent Information Technologies2025https://doi.org/10.4018/ijiit.380511article
ABDC C
Weight
0.37

What the paper says

Intangible Cultural Heritage (ICH) dances, with their richness in historical and cultural value, reflect the diversity of human society. However, many traditional dances face challenges with their transmission and protection. This paper proposes a multi-feature fusion-based motion recognition method to address insufficient feature extraction and inadequate model adaptability for ICH dance movement recognition. The method integrates skeletal, spatiotemporal, and deep features, enhancing their expression through an optimised fusion strategy and using an improved 3D convolutional neural network for efficient recognition. Validation on a dataset of 60 typical movements from various ICH dances including Dai peacock dance, Tibetan Guozhuang dance, Mongolian Andai dance, and Uyghur sainaim dance demonstrated superior performance of this method in accuracy, recall, and F1 score compared to traditional methods. This research provides a robust solution for ICH dance movement recognition and offers insights towards broader technological applications for cultural preservation.

1 citation

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.4018/ijiit.380511

Or copy a formatted citation

@article{jing2025,
  title        = {{Research on Recognition Method of Non-Legacy Dance Action Based on Multi-Feature Fusion}},
  author       = {Jing Yang et al.},
  journal      = {International Journal of Intelligent Information Technologies},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.4018/ijiit.380511},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Research on Recognition Method of Non-Legacy Dance Action Based on Multi-Feature Fusion

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.37

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.16 × 0.4 = 0.06
M · momentum0.53 × 0.15 = 0.08
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.