{"id":1813,"date":"2026-03-30T00:18:13","date_gmt":"2026-03-29T16:18:13","guid":{"rendered":"https:\/\/iweb20wp-b205b.url.tku.edu.tw\/jase\/?post_type=tkuisotope&p=1813"},"modified":"2026-05-20T14:25:09","modified_gmt":"2026-05-20T06:25:09","slug":"transformer-based-multi-task-learning-for-table-tennis-motion-feature-recognition","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=transformer-based-multi-task-learning-for-table-tennis-motion-feature-recognition","title":{"rendered":"Transformer-based multi-task learning for table tennis motion feature recognition"},"content":{"rendered":"\n
\n
\n

<\/i> 2026<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 29, Issue 3<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Tianfang Ma<\/i><\/a><\/p>\n\n\n\n

Physical Education Teaching and Research Department, Harbin Finance University, Harbin 150030 China<\/p>\n<\/div>\n\n\n\n

\n

Received:\u00a0May 12, 2025
Accepted:\u00a0June 10, 2025
Publication Date:\u00a0March 30, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

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

Partial action recognition accuracy comparison<\/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:\u00a0 BibTeX <\/a>| https:\/\/doi.org\/10.6180\/jase.202603_29(3).0005<\/a>\u00a0\u00a0<\/p>\n\n\n\n

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

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

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.<\/p>\n\n\n\n

Keywords: multi-task table tennis motion; feature recognition; Transformer; multi-task learning; support vector machine<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
    \n
  1. [1] S. Edriss, C. Romagnoli, L. Caprioli, A. Zanela, E. Panichi, F. Campoli, E. Padua, G. Annino, and V. Bonaiuto, (2024) \u201cThe role of emergent technologies in the dynamic and kinematic assessment of human movement in sport and clinical applications\u201d Applied Sciences 14(3): 1012. DOI: 10.3390\/app14031012.<\/li>\n
  2. [2] R. Leib, I. S. Howard, M. Millard, and D. W. Franklin, (2024) \u201cBehavioral motor performance\u201d Comprehensive Physiology 14(1): 5179\u20135224. DOI: 10.1002\/j.2040-4603.2024.tb00286.x.<\/li>\n
  3. [3] A. Jisi, S. Yin, et al., (2021) \u201cA new feature fusion network for student behavior recognition in education\u201d Journal of Applied Science and Engineering 24(2): 133\u2013140. DOI: 10.6180\/jase.202104_24(2).0002.<\/li>\n
  4. [4] J. Luo, W. Wang, and H. Qi, (2014) \u201cSpatio-temporal feature extraction and representation for RGB-D human action recognition\u201d Pattern Recognition Letters 50: 139\u2013148. DOI: 10.1016\/j.patrec.2014.03.024.<\/li>\n
  5. [5] M. Lovanshi and V. Tiwari, (2024) \u201cHuman skeleton pose and spatio-temporal feature-based activity recognition using ST-GCN\u201d Multimedia Tools and Applications 83(5): 12705\u201312730. DOI: 10.1007\/s11042-023-16001-9.<\/li>\n
  6. [6] Z. Wang, H. Lu, J. Jin, and K. Hu, (2022) \u201cHuman action recognition based on improved two-stream convolution network\u201d Applied Sciences 12(12): 5784. DOI: 10.3390\/app12125784.<\/li>\n
  7. [7] M. Xiao, (2024) \u201cThe best angle correction of basketball shooting based on the fusion of time series features and dual CNN\u201d Egyptian Informatics Journal 28: 100579. DOI: 10.1016\/j.eij.2024.100579.<\/li>\n
  8. [8] A.-A. Liu, N. Xu, W.-Z. Nie, Y.-T. Su, and Y.-D. Zhang, (2018) \u201cMulti-domain and multi-task learning for human action recognition\u201d IEEE Transactions on Image Processing 28(2): 853\u2013867. DOI: 10.1109\/TIP.2018.2872879.<\/li>\n
  9. [9] A. Laghari, H. He, A. Khan, R. Laghari, S. Yin, and J. Wang, (2022) \u201cCrowdsourcing platform for QoE evaluation for cloud multimedia services\u201d Computer Science and Information Systems 19(3): 1305. DOI: 10.2298\/csis220322038l.<\/li>\n
  10. [10] E. Aksan, M. Kaufmann, P. Cao, and O. Hilliges. \u201cA spatio-temporal transformer for 3d human motion prediction\u201d. In: 2021 International Conference on 3D Vision (3DV). IEEE. 2021, 565\u2013574. DOI: 10.1109 \/ 3DV53792.2021.00066.<\/li>\n
  11. [11] K. Ding, A. J. Liang, B. Perozzi, T. Chen, R. Wang, L. Hong, E. H. Chi, H. Liu, and D. Z. Cheng. \u201cHyperFormer: Learning expressive sparse feature representations via hypergraph transformer\u201d. In: Proceedings of the 46th international ACM SIGIR conference on research and development in information retrieval. 2023, 2062\u20132066. DOI: 10.1145\/3539618.3591999.<\/li>\n
  12. [12] Y. Pang, Q. Ke, H. Rahmani, J. Bailey, and J. Liu. \u201cIgformer: Interaction graph transformer for skeleton-based human interaction recognition\u201d. In: European Conference on Computer Vision. Springer. 2022, 605\u2013622. DOI: 10.1007\/978-3-031-19806-9_35.<\/li>\n
  13. [13] S. Madden, M. J. Franklin, J. M. Hellerstein, and W. Hong, (2002) \u201cTAG: A tiny aggregation service for ad-hoc sensor networks\u201d ACM SIGOPS Operating Systems Review 36(SI): 131\u2013146. DOI: 10.1145\/844128.844142.<\/li>\n
  14. [14] H. Rao, S. Wang, X. Hu, M. Tan, Y. Guo, J. Cheng, X. Liu, and B. Hu, (2021) \u201cA self-supervised gait encoding approach with locality-awareness for 3D skeleton based person re-identification\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence 44(10): 6649\u20136666. DOI: 10.1109\/TPAMI.2021.3092833.<\/li>\n
  15. [15] J. Jiang, J. Chen, and Y. Guo. \u201cA dual-masked autoencoder for robust motion capture with spatial-temporal skeletal token completion\u201d. In: Proceedings of the 30th ACM International Conference on Multimedia. 2022, 5123\u20135131. DOI: 10.1145\/3503161.3547796.<\/li>\n
  16. [16] H.-g. Chi, M. H. Ha, S. Chi, S. W. Lee, Q. Huang, and K. Ramani. \u201cInfoGcn: Representation learning for human skeleton-based action recognition\u201d. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2022, 20186\u201320196. DOI: 10.1109\/CVPR52688.2022.01955.<\/li>\n
  17. [17] S. Guan, H. Lu, L. Zhu, and G. Fang, (2022) \u201cAFE-CNN: 3D skeleton-based action recognition with action feature enhancement\u201d Neurocomputing 514: 256\u2013267. DOI: 10.1016\/j.neucom.2022.10.016.<\/li>\n
  18. [18] J. Liu, A. Shahroudy, M. Perez, G. Wang, L.-Y. Duan, and A. C. Kot, (2019) \u201cNtu rgb+ d 120: A large-scale benchmark for 3d human activity understanding\u201d IEEE transactions on pattern analysis and machine intelligence 42(10): 2684\u20132701. DOI: 10.1109\/TPAMI.2019.2916873.<\/li>\n
  19. [19] X. Li, X. Zhang, L. Zhang, X. Chen, and P. Zhou, (2023) \u201cA transformer-based multi-task learning framework for myoelectric pattern recognition supporting muscle force estimation\u201d IEEE Transactions on Neural Systems and Rehabilitation Engineering 31: 3255\u20133264. DOI: 10.1109\/TNSRE.2023.3298797.<\/li>\n
  20. [20] W. Xin, R. Liu, Y. Liu, Y. Chen, W. Yu, and Q. Miao, (2023) \u201cTransformer for skeleton-based action recognition: A review of recent advances\u201d Neurocomputing 537: 164\u2013186. DOI: 10.1016\/j.neucom.2023.03.001.<\/li>\n
  21. [21] C. Shi and S. Liu, (2024) \u201cHuman action recognition with transformer based on convolutional features\u201d Intelligent Decision Technologies 18(2): 881\u2013896. DOI: 10.3233\/IDT-240159.<\/li>\n
  22. [22] Y. Xing, Z. Hu, X. Mo, P. Hang, S. Li, Y. Liu, Y. Zhao, and C. Lv, (2024) \u201cDriver steering behaviour modelling based on neuromuscular dynamics and multi-task time-series transformer\u201d Automotive Innovation 7(1): 45\u201358. DOI: 10.1007\/s42154-023-00272-x.<\/li>\n
  23. [23] C. Fan, S. Lin, B. Cheng, D. Xu, K. Wang, Y. Peng, and S. Kwong, (2024) \u201cEEG-TransMTL: A transformer-based multi-task learning network for thermal comfort evaluation of railway passenger from EEG\u201d Information Sciences 657: 119908. DOI: 10.1016\/j.ins.2023.119908.<\/li>\n
  24. [24] W. Li, N. Zhou, and X. Qu. \u201cEnhancing eye-tracking performance through multi-task learning transformer\u201d. In: International Conference on Human-Computer Interaction. Springer. 2024, 31\u201346. DOI: 10.1007\/978-3-031-61572-6_3.<\/li>\n<\/ol>\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":[12,15,6,118],"tags":[172],"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:\u00a0 BibTeX | https:\/\/doi.org\/10.6180\/jase.202603_29(3).0005\u00a0\u00a0 Download PDF In the process of multi-task sports motion behavior feature recognition, it…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/1813"}],"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=1813"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1813"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1813"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}