Article: Latin dance action style transfer based on improved Ada IN algorithm Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.5 pp.38 - 60 Abstract: This study addresses limitations in current dance action style transfer methods, such as weak spatiotemporal coupling and poor generalisation. It proposes a novel approach using improved adaptive instance normalisation (I Ada IN) with a joint-limb-global layered normalisation structure to enhance style decoupling. The method incorporates a spatiotemporal transformer and inverse kinematics correction to improve stability and style fidelity in long sequences. Experiments show significant gains: a 43% higher style detail retention rate (0.89 vs. 0.62), a 27% improvement in structural similarity (0.94), and a 50% reduction in joint motion error (4.3 mm) over the original Ada IN. With a frame rate of 120 and processing time of 8ms per frame, the model meets real-time performance standards. This method achieves high-fidelity style transfer, accurate content preservation, and stable cross-domain generalisation through innovative hierarchical feature fusion and spatiotemporal modelling strategies, providing feasible technical support and application prospects for virtual dance teaching, intelligent choreography systems, and the digital protection of intangible cultural heritage. Inderscience Publishers - linking academia, business and industry through research

Title: Latin dance action style transfer based on improved Ada IN algorithm

Authors: Hui Lan

Addresses: Physical Education and Arts School, Chengyi College Jimei University, Xiamen, 361021, China

Abstract: This study addresses limitations in current dance action style transfer methods, such as weak spatiotemporal coupling and poor generalisation. It proposes a novel approach using improved adaptive instance normalisation (I Ada IN) with a joint-limb-global layered normalisation structure to enhance style decoupling. The method incorporates a spatiotemporal transformer and inverse kinematics correction to improve stability and style fidelity in long sequences. Experiments show significant gains: a 43% higher style detail retention rate (0.89 vs. 0.62), a 27% improvement in structural similarity (0.94), and a 50% reduction in joint motion error (4.3 mm) over the original Ada IN. With a frame rate of 120 and processing time of 8ms per frame, the model meets real-time performance standards. This method achieves high-fidelity style transfer, accurate content preservation, and stable cross-domain generalisation through innovative hierarchical feature fusion and spatiotemporal modelling strategies, providing feasible technical support and application prospects for virtual dance teaching, intelligent choreography systems, and the digital protection of intangible cultural heritage.

Keywords: dance action style transfer; improved adaptive instance normalisation; Ada IN algorithm; multi-feature fusion; feature extraction; digital art.

DOI: 10.1504/IJICT.2026.151533

International Journal of Information and Communication Technology, 2026 Vol.27 No.5, pp.38 - 60

Received: 08 Aug 2025
Accepted: 25 Nov 2025
Published online: 04 Feb 2026 *

Title: Latin dance action style transfer based on improved Ada IN algorithm

Keep up-to-date