Precise Recognition and Feature Depth Analysis of Tennis Training Actions Based on Multimodal Data Integration and Key Action Classification
To address the issues of accuracy and generalization in action recognition within complex tennis training scenarios, this study proposes an Adaptive Semantic-Enhanced Convolutional Neural Network (ASE-CNN) model. The model optimizes multimodal data integration and complex action classification perfo...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10870269/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823857129699672064 |
|---|---|
| author | Weichao Yang |
| author_facet | Weichao Yang |
| author_sort | Weichao Yang |
| collection | DOAJ |
| description | To address the issues of accuracy and generalization in action recognition within complex tennis training scenarios, this study proposes an Adaptive Semantic-Enhanced Convolutional Neural Network (ASE-CNN) model. The model optimizes multimodal data integration and complex action classification performance, enabling precise analysis of key action features in tennis training. Experimental results demonstrate that ASE-CNN excels in multimodal feature extraction, achieving a Receiver Operating Characteristic-Area Under Curve (ROC-AUC) value of 0.85–0.95 and a Feature Distribution Uniformity of 0.75–0.85, validating its accuracy and stability in feature classification. The fused weighted Precision-Recall Area Under Curve (PR-AUC) value ranges from 0.80 to 0.92, highlighting its capability for synergistic optimization of multimodal data. For key action recognition, the classification accuracy reaches up to 0.98, with Euclidean distances between key actions and ideal action templates as low as 0.05–0.15, demonstrating exceptional fine-detail discrimination. Compared to state-of-the-art models, ASE-CNN exhibits significant advantages in per-frame processing time and resource utilization efficiency, offering potential for efficient real-time feedback in resource-constrained environments. This study provides scientific evidence and technical support for optimizing actions and improving strategies in professional training. |
| format | Article |
| id | doaj-art-5898aef096c54827b8c79499cf417a98 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-5898aef096c54827b8c79499cf417a982025-02-12T00:02:38ZengIEEEIEEE Access2169-35362025-01-0113254092541810.1109/ACCESS.2025.353878010870269Precise Recognition and Feature Depth Analysis of Tennis Training Actions Based on Multimodal Data Integration and Key Action ClassificationWeichao Yang0https://orcid.org/0000-0003-3107-4398Department of Physical Education, Luoyang Institute of Science and Technology, Luoyang, ChinaTo address the issues of accuracy and generalization in action recognition within complex tennis training scenarios, this study proposes an Adaptive Semantic-Enhanced Convolutional Neural Network (ASE-CNN) model. The model optimizes multimodal data integration and complex action classification performance, enabling precise analysis of key action features in tennis training. Experimental results demonstrate that ASE-CNN excels in multimodal feature extraction, achieving a Receiver Operating Characteristic-Area Under Curve (ROC-AUC) value of 0.85–0.95 and a Feature Distribution Uniformity of 0.75–0.85, validating its accuracy and stability in feature classification. The fused weighted Precision-Recall Area Under Curve (PR-AUC) value ranges from 0.80 to 0.92, highlighting its capability for synergistic optimization of multimodal data. For key action recognition, the classification accuracy reaches up to 0.98, with Euclidean distances between key actions and ideal action templates as low as 0.05–0.15, demonstrating exceptional fine-detail discrimination. Compared to state-of-the-art models, ASE-CNN exhibits significant advantages in per-frame processing time and resource utilization efficiency, offering potential for efficient real-time feedback in resource-constrained environments. This study provides scientific evidence and technical support for optimizing actions and improving strategies in professional training.https://ieeexplore.ieee.org/document/10870269/Tennis action recognitionconvolutional neural network architecturemultimodal datafeature extractionASE-CNN |
| spellingShingle | Weichao Yang Precise Recognition and Feature Depth Analysis of Tennis Training Actions Based on Multimodal Data Integration and Key Action Classification IEEE Access Tennis action recognition convolutional neural network architecture multimodal data feature extraction ASE-CNN |
| title | Precise Recognition and Feature Depth Analysis of Tennis Training Actions Based on Multimodal Data Integration and Key Action Classification |
| title_full | Precise Recognition and Feature Depth Analysis of Tennis Training Actions Based on Multimodal Data Integration and Key Action Classification |
| title_fullStr | Precise Recognition and Feature Depth Analysis of Tennis Training Actions Based on Multimodal Data Integration and Key Action Classification |
| title_full_unstemmed | Precise Recognition and Feature Depth Analysis of Tennis Training Actions Based on Multimodal Data Integration and Key Action Classification |
| title_short | Precise Recognition and Feature Depth Analysis of Tennis Training Actions Based on Multimodal Data Integration and Key Action Classification |
| title_sort | precise recognition and feature depth analysis of tennis training actions based on multimodal data integration and key action classification |
| topic | Tennis action recognition convolutional neural network architecture multimodal data feature extraction ASE-CNN |
| url | https://ieeexplore.ieee.org/document/10870269/ |
| work_keys_str_mv | AT weichaoyang preciserecognitionandfeaturedepthanalysisoftennistrainingactionsbasedonmultimodaldataintegrationandkeyactionclassification |