{"id":12961,"date":"2026-10-09T14:35:05","date_gmt":"2026-10-09T06:35:05","guid":{"rendered":"\/jase\/?post_type=tkuisotope&p=12961"},"modified":"2026-10-09T22:02:41","modified_gmt":"2026-10-09T14:02:41","slug":"jase-202701-36-021","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=jase-202701-36-021","title":{"rendered":"Deep Learning-based Human Motion Analysis for Intelligent Dance Movement Recognition and Performance Evaluation"},"content":{"rendered":"\n
\n
\n

<\/i> 2027<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 36<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Xiuli Sun<\/i><\/a><\/p>\n\n\n\n

School of Art, PingDingShan Vocational and Technical College, Pingdingshan 467000, Henan, China<\/p>\n<\/div>\n\n\n\n

\n

Received: June 2, 2026
Accepted: August 14, 2026
Publication Date: October 09, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

Proposed block diagram<\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/i> Copyright <\/strong>The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0)<\/a>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.<\/p>\n\n\n\n

Download Citation: BibTeX <\/a>| http:\/\/dx.doi.org\/10.6180\/jase.202701_36.021<\/a> <\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

Human motion understanding has become an important research area for choreography analysis, automated dance teaching, virtual performance assessment, and interactive entertainment systems. However, existing dance movement recognition methods often struggle to capture complex spatial skeletal relationships and long-range temporal motion dependencies, reducing recognition accuracy for intricate dance movements. To address this limitation, this study proposes a deep learning framework that integrates a Spatial-Temporal Graph Convolutional Network (ST-GCN) with a Bidirectional Long Short-Term Memory (Bi-LSTM) network to jointly learn spatial structural information and temporal motion dynamics for dance movement recognition and performance evaluation. The framework constructs a spatio-temporal graph in which body joints are graph vertices, bone connections are spatial edges, and inter-frame joint relationships are temporal edges to preserve motion continuity. Experimental evaluation was conducted using the Dance Motion Capture Dataset comprising 100 selected dance video sequences. The motion sequences were preprocessed through missing value removal, Gaussian filtering, Min-Max normalization, and temporal sequence alignment before model training and evaluation. Spatial features extracted by the ST-GCN were combined with temporal representations learned by the Bi-LSTM and classified using a fully connected SoftMax layer. The framework was evaluated using precision, recall, F1-score, and accuracy metrics and compared with K-Nearest Neighbors (KNN), Boost, and Random Forest. Experimental results achieved 97.14% precision, 96.67% recall, 96.64% F1-score, and 96.67% accuracy, demonstrating superior recognition performance. The proposed framework provides an effective approach for dance movement recognition and supports applications in automated dance assessment, virtual training systems, and human motion analysis.<\/p>\n\n\n\n

Keywords: Bidirectional Long Short-Term Memory, Dance Movement Recognition, Deep Learning, Performance Evaluation, Skeletal Joint Sequences, Spatial-Temporal Graph Convolutional Network, Temporal Sequence Alignment<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
\n
\n
    \n
  1. [1] J. R. Challapalli and N. Devarakonda, (2022) “A Novel Approach for Optimization of Convolution Neural Network with Hybrid Particle Swarm and Grey Wolf Algorithm for Classification of Indian Classical Dances” Knowledge and Information Systems 64(9): 2411-2434. DOI: https:\/\/doi.org\/10.1007\/s10115-022-01707-3.<\/li>\n
  2. [2] N. Jain, V. Bansal, D. Virmani, V. Gupta, L. Salas-Morera, and L. Garc\u00eda-Hern\u00e1ndez, (2021) “An Enhanced Deep Convolutional Neural Network for Classifying Indian Classical Dance Forms” Applied Sciences 11(14): 6253. DOI: https:\/\/doi.org\/10.3390\/app11146253.<\/li>\n
  3. [3] Z. Wang, (2024) “Artificial Intelligence in Dance Education: Using Immersive Technologies for Teaching Dance Skills” Technology in Society 77: 102579. DOI: https:\/\/doi.org\/10.1016\/j.techsoc.2024.102579.<\/li>\n
  4. [4] J. Rudd, T. Buszard, S. Spittle, L. O’Callaghan, and L. Oppici, (2021) “Comparing the Efficacy (RCT) of Learning a Dance Choreography and Practicing Creative Dance on Improving Executive Functions and Motor Competence in 6-7-Year-Old Children” Psychology of Sport and Exercise 53: 101846. DOI: https:\/\/doi.org\/10.1016\/j.psychsport.2020.101846.<\/li>\n
  5. [5] Z. Huang et al. “Beat-It: Beat-Synchronized Multi-Condition 3D Dance Generation”. In: 273. 2024, 273-290. DOI: https:\/\/doi.org\/10.1007\/978-3-031-72655-2_16.<\/li>\n
  6. [6] H. Guo et al., (2022) “DanceVis: Toward Better Understanding of Online Cheer and Dance Training” Journal of Visualization 25(1): 159-174. DOI: https:\/\/doi.org\/10.1007\/s12650-021-00783-x.<\/li>\n
  7. [7] M. Skublewska-Paszkowska et al., (2021) “Methodology of 3D Scanning of Intangible Cultural Heritage-The Example of Lazgi Dance” Applied Sciences 11(23): 11568. DOI: https:\/\/doi.org\/10.3390\/app112311568.<\/li>\n
  8. [8] T. Mallick, P. P. Das, and A. K. Majumdar, (2022) “Posture and Sequence Recognition for Bharatanatyam Dance Performances Using Machine Learning Approaches” Journal of Visual Communication and Image Representation 87: 103548. DOI: https:\/\/doi.org\/10.1016\/j.jvcir.2022.103548.<\/li>\n
  9. [9] Z. Miao, W. Wang, J. Xie, L. Ma, and N. Hu, (2025) “Research on Original Environment Folk Dance Movement Evaluation Based on Spatio-Temporal Graph Convolutional Networks” Signal, Image and Video Processing 19(3): 266. DOI: https:\/\/doi.org\/10.1007\/s11760-025-03844-y.<\/li>\n
  10. [10] S. Wang and S. Tong, (2022) “Analysis of High-Level Dance Movements Under Deep Learning and Internet of Things” The Journal of Supercomputing 78(12): 14294-14316. DOI: https:\/\/doi.org\/10.1007\/s11227-022-04454-y.<\/li>\n
  11. [11] K. Kritsis, A. Gkiokas, A. Pikrakis, and V. Katsouros, (2022) “DanceConv: Dance Motion Generation With Convolutional Networks” IEEE Access 10: 44982-45000. DOI: https:\/\/doi.org\/10.1109\/ACCESS.2022.3169782.<\/li>\n
  12. [12] R. Zhang, (2022) “Analyzing Body Changes of High-Level Dance Movements Through Biological Image Visualization Technology by Convolutional Neural Network” The Journal of Supercomputing 78(8): 10521-10541. DOI: https:\/\/doi.org\/10.1007\/s11227-021-04298-y.<\/li>\n
  13. [13] C. J. Rani and N. Devarakonda, (2022) “An Effectual Classical Dance Pose Estimation and Classification System Employing Convolution Neural Network-Long Short-Term Memory (CNN-LSTM) Network for Video Sequences” Microprocessors and Microsystems 95: 104651. DOI: https:\/\/doi.org\/10.1016\/j.micpro.2022.104651.<\/li>\n
  14. [14] J. P. Ferreira et al., (2021) “Learning to Dance: A Graph Convolutional Adversarial Network to Generate Realistic Dance Motions from Audio” Computers & Graphics 94: 11-21. DOI: https:\/\/doi.org\/10.1016\/j.cag.2020.09.009.<\/li>\n
  15. [15] R. Li, S. Yang, D. A. Ross, and A. Kanazawa. “AI Choreographer: Music Conditioned 3D Dance Generation with AIST++”. In: 2021, 13381-13392. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.01315.<\/li>\n<\/ol>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[2188,6,2189],"tags":[2301],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. Download Citation: BibTeX | http:\/\/dx.doi.org\/10.6180\/jase.202701_36.021 Download PDF Human motion understanding has become an important research area for choreography…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/12961"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=12961"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=12961"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=12961"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}