Article: Enhancement of accuracy and analytical efficiency of gymnastics video using convolutional neural network and semantic analysis approach Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.30 pp.24 - 42 Abstract: Gymnastics competition's conventional video analysis approach mostly depends on shallow image processing technology, which is challenging to sufficiently capture the subtleties of participants' motions and semantic information in the competition. This work suggests a semantic analysis approach of gymnastics competition film based on domain knowledge and depth features to compensate this deficit. First, one builds a knowledge base based on action classification in addition to the domain knowledge of gymnastics competition. Second, the temporal and spatial traits of video and the dynamic performance of athletes are extracted using convolutional neural network (CNN) in combination with long-term and short-term memory network (LSTM). In the analysis of gymnastics competition video, the experimental findings reveal that this approach produces better recognition accuracy and analytical efficiency than the conventional one. Inderscience Publishers - linking academia, business and industry through research

Title: Enhancement of accuracy and analytical efficiency of gymnastics video using convolutional neural network and semantic analysis approach

Authors: Xiangyang Cai; Lijing Xu; Shijun Wang

Addresses: Hebi Institute of Engineering and Technology, Henan Polytechnic University, Hebi 458030, China ' College of Art and Design, Zhengzhou University of Industrial Technology, Xinzheng 451100, China ' School of Physical Education, Zhengzhou Technical College, Zhengzhou 450000, China

Abstract: Gymnastics competition's conventional video analysis approach mostly depends on shallow image processing technology, which is challenging to sufficiently capture the subtleties of participants' motions and semantic information in the competition. This work suggests a semantic analysis approach of gymnastics competition film based on domain knowledge and depth features to compensate this deficit. First, one builds a knowledge base based on action classification in addition to the domain knowledge of gymnastics competition. Second, the temporal and spatial traits of video and the dynamic performance of athletes are extracted using convolutional neural network (CNN) in combination with long-term and short-term memory network (LSTM). In the analysis of gymnastics competition video, the experimental findings reveal that this approach produces better recognition accuracy and analytical efficiency than the conventional one.

Keywords: physical gymnastics competition; video analysis; deep learning; CNN; LSTM.

DOI: 10.1504/IJICT.2025.147761

International Journal of Information and Communication Technology, 2025 Vol.26 No.30, pp.24 - 42

Received: 24 May 2025
Accepted: 17 Jun 2025
Published online: 30 Jul 2025 *

Title: Enhancement of accuracy and analytical efficiency of gymnastics video using convolutional neural network and semantic analysis approach

Keep up-to-date