Transformer-based multi-task learning for table tennis motion feature recognition
In the process of multi-task sports motion behavior feature recognition, it is prone to be affected by few-shot samples, resulting in catastrophic forgetting phenomena, which leads to poor processing ability of variability. In order to solve the above-mentioned problems, this paper proposes a novel...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tamkang University Press
2025-06-01
|
| Series: | Journal of Applied Science and Engineering |
| Subjects: | |
| Online Access: | http://jase.tku.edu.tw/articles/jase-202603-29-03-0005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849420150379380736 |
|---|---|
| author | Tianfang Ma |
| author_facet | Tianfang Ma |
| author_sort | Tianfang Ma |
| collection | DOAJ |
| description | In the process of multi-task sports motion behavior feature recognition, it is prone to be affected by few-shot samples, resulting in catastrophic forgetting phenomena, which leads to poor processing ability of variability. In order to solve the above-mentioned problems, this paper proposes a novel table tennis motion feature recognition method based on Transformer-based multi-task learning. This model adopts a grouped attention structure to enhance the extraction ability of local features, and adds the spatial information embedding and temporal information embedding modules to enhance the extraction of spatial and temporal features by the original Transformer model. The extracted chaotic invariant features are classified and recognized through the multi-task learning method by support vector machine to achieve the accurate recognition of multi-task table tennis motion features. The experiment results show that this new method can efficiently identify the motions of table tennis movement, accurately capture the subtle changes of joints, and perform excellently in both single/complex multi-tasks and cross-individual scenarios. |
| format | Article |
| id | doaj-art-626ea0e2cf784ae4b03c5be58b9fa791 |
| institution | Kabale University |
| issn | 2708-9967 2708-9975 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Tamkang University Press |
| record_format | Article |
| series | Journal of Applied Science and Engineering |
| spelling | doaj-art-626ea0e2cf784ae4b03c5be58b9fa7912025-08-20T03:31:49ZengTamkang University PressJournal of Applied Science and Engineering2708-99672708-99752025-06-0129354555210.6180/jase.202603_29(3).0005Transformer-based multi-task learning for table tennis motion feature recognitionTianfang Ma0Physical Education Teaching and Research Department, Harbin Finance University, Harbin 150030 ChinaIn the process of multi-task sports motion behavior feature recognition, it is prone to be affected by few-shot samples, resulting in catastrophic forgetting phenomena, which leads to poor processing ability of variability. In order to solve the above-mentioned problems, this paper proposes a novel table tennis motion feature recognition method based on Transformer-based multi-task learning. This model adopts a grouped attention structure to enhance the extraction ability of local features, and adds the spatial information embedding and temporal information embedding modules to enhance the extraction of spatial and temporal features by the original Transformer model. The extracted chaotic invariant features are classified and recognized through the multi-task learning method by support vector machine to achieve the accurate recognition of multi-task table tennis motion features. The experiment results show that this new method can efficiently identify the motions of table tennis movement, accurately capture the subtle changes of joints, and perform excellently in both single/complex multi-tasks and cross-individual scenarios.http://jase.tku.edu.tw/articles/jase-202603-29-03-0005multi-task table tennis motionfeature recognitiontransformermulti-task learningsupport vector machine |
| spellingShingle | Tianfang Ma Transformer-based multi-task learning for table tennis motion feature recognition Journal of Applied Science and Engineering multi-task table tennis motion feature recognition transformer multi-task learning support vector machine |
| title | Transformer-based multi-task learning for table tennis motion feature recognition |
| title_full | Transformer-based multi-task learning for table tennis motion feature recognition |
| title_fullStr | Transformer-based multi-task learning for table tennis motion feature recognition |
| title_full_unstemmed | Transformer-based multi-task learning for table tennis motion feature recognition |
| title_short | Transformer-based multi-task learning for table tennis motion feature recognition |
| title_sort | transformer based multi task learning for table tennis motion feature recognition |
| topic | multi-task table tennis motion feature recognition transformer multi-task learning support vector machine |
| url | http://jase.tku.edu.tw/articles/jase-202603-29-03-0005 |
| work_keys_str_mv | AT tianfangma transformerbasedmultitasklearningfortabletennismotionfeaturerecognition |