Transformer-based multi-task learning for table tennis motion feature recognition

Tianfang  Ma

doi:10.6180/jase.202603_29(3).0005

Transformer-based multi-task learning for table tennis motion feature recognition

Physics

Tianfang MaThis email address is being protected from spambots. You need JavaScript enabled to view it.

Physical Education Teaching and Research Department, Harbin Finance University, Harbin 150030 China

Received: May 12, 2025
Accepted: June 10, 2025
Publication Date: June 26, 2025

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: ||https://doi.org/10.6180/jase.202603_29(3).0005

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.

Keywords: multi-task table tennis motion; feature recognition; Transformer; multi-task learning; support vector machine

[1] S. Edriss, C. Romagnoli, L. Caprioli, A. Zanela, E. Panichi, F. Campoli, E. Padua, G. Annino, and V. Bonaiuto, (2024) “The role of emergent technologies in the dynamic and kinematic assessment of human movement in sport and clinical applications" Applied Sciences 14(3): 1012. DOI: 10.3390/app14031012.
[2] R. Leib, I. S. Howard, M. Millard, and D. W. Franklin, (2024) “Behavioral motor performance" Comprehensive Physiology 14(1): 5179–5224. DOI: 10.1002/j.2040-4603.2024.tb00286.x.
[3] A. Jisi, S. Yin, et al., (2021) “A new feature fusion network for student behavior recognition in education" Jour nal of Applied Science and Engineering 24(2): 133 140. DOI: 10.6180/jase.202104_24(2).0002.
[4] J. Luo, W. Wang, and H. Qi, (2014) “Spatio-temporal feature extraction and representation for RGB-D human action recognition" Pattern Recognition Letters 50: 139–148. DOI: 10.1016/j.patrec.2014.03.024.
[5] M. Lovanshi and V. Tiwari, (2024) “Human skeleton pose and spatio-temporal feature-based activity recognition using ST-GCN" Multimedia Tools and Applications 83(5): 12705–12730. DOI: 10.1007/s11042-023-16001-9.
[6] Z. Wang, H. Lu, J. Jin, and K. Hu, (2022) “Human action recognition based on improved two-stream convolution network" Applied Sciences 12(12): 5784. DOI: 10.3390/app12125784.
[7] M. Xiao, (2024) “The best angle correction of basketball shooting based on the fusion of time series features and dual CNN" Egyptian Informatics Journal 28: 100579. DOI: 10.1016/j.eij.2024.100579.
[8] A. -A. Liu, N. Xu, W. -Z. Nie, Y. -T. Su, and Y. -D. Zhang, (2018) “Multi-domain and multi-task learning for hu man action recognition" IEEE Transactions on Image Processing 28(2): 853–867. DOI: 10.1109/TIP.2018.2872879.
[9] A. Laghari, H. He, A. Khan, R. Laghari, S. Yin, and J. Wang, (2022) “Crowdsourcing platform for QoE evaluation for cloud multimedia services" Computer Science and Information Systems 19(3): 1305. DOI: 10.2298/csis220322038l.
[10] E. Aksan, M. Kaufmann, P. Cao, and O. Hilliges. “A spatio-temporal transformer for 3d human motion prediction”. In: 2021 International Conference on 3D Vision (3DV). IEEE. 2021, 565–574. DOI: 10.1109/3DV53792.2021.00066.
[11] K. Ding, A. J. Liang, B. Perozzi, T. Chen, R. Wang, L. Hong, E. H. Chi, H. Liu, and D. Z. Cheng. “Hyper Former: Learning expressive sparse feature representations via hypergraph transformer”. In: Proceedings of the 46th international ACM SIGIR conference on research and development in information retrieval. 2023, 2062–2066. DOI: 10.1145/3539618.3591999.
[12] Y. Pang, Q. Ke, H. Rahmani, J. Bailey, and J. Liu. “Igformer: Interaction graph transformer for skeleton based human interaction recognition”. In: European Conference on Computer Vision. Springer. 2022, 605 622. DOI: 10.1007/978-3-031-19806-9_35.
[13] S. Madden, M. J. Franklin, J. M. Hellerstein, and W. Hong, (2002) “TAG: A tiny aggregation service for ad hoc sensor networks" ACM SIGOPS Operating Systems Review 36(SI): 131–146. DOI: 10.1145/844128.844142.
[14] H. Rao, S. Wang, X. Hu, M. Tan, Y. Guo, J. Cheng, X. Liu, and B. Hu, (2021) “A self-supervised gaiten coding approach with locality-awareness for 3D skeleton based person re-identification" IEEE Transactions on Pattern Analysis and Machine Intelligence 44(10): 6649–6666. DOI: 10.1109/TPAMI.2021.3092833.
[15] J. Jiang, J. Chen, and Y. Guo. “A dual-masked auto encoder for robust motion capture with spatial temporal skeletal token completion”. In: Proceedings of the 30th ACM International Conference on Multimedia. 2022, 5123–5131. DOI: 10.1145/3503161.3547796.
[16] H.-g. Chi, M. H. Ha, S. Chi, S. W. Lee, Q. Huang, and K. Ramani. “Infogcn: Representation learning for human skeleton-based action recognition”. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022, 20186–20196. DOI: 10.1109/CVPR52688.2022.01955.
[17] S. Guan, H. Lu, L. Zhu, and G. Fang, (2022) “AFE CNN: 3D skeleton-based action recognition with action feature enhancement" Neurocomputing 514: 256–267. DOI: 10.1016/j.neucom.2022.10.016.
[18] J. Liu, A. Shahroudy, M. Perez, G. Wang, L.-Y. Duan, and A. C. Kot, (2019) “Ntu rgb+ d 120: A large-scale benchmark for 3d human activity understanding" IEEE transactions on pattern analysis and machine intel ligence 42(10): 2684–2701. DOI: 10.1109/TPAMI.2019.2916873.
[19] X. Li, X. Zhang, L. Zhang, X. Chen, and P. Zhou, (2023) “A transformer-based multi-task learning frame work for myoelectric pattern recognition supporting muscle force estimation" IEEE Transactions on Neural Sys tems and Rehabilitation Engineering 31: 3255–3264. DOI: 10.1109/TNSRE.2023.3298797.
[20] W. Xin, R. Liu, Y. Liu, Y. Chen, W. Yu, and Q. Miao, (2023) “Transformer for skeleton-based action recognition: A review of recent advances" Neurocomputing 537: 164–186. DOI: 10.1016/j.neucom.2023.03.001.
[21] C. Shi and S. Liu, (2024) “Human action recognition with transformer based on convolutional features" Intelligent Decision Technologies 18(2): 881–896. DOI: 10.3233/IDT-240159.
[22] Y. Xing, Z. Hu, X. Mo, P. Hang, S. Li, Y. Liu, Y. Zhao, and C. Lv, (2024) “Driver steering behaviour modelling based on neuromuscular dynamics and multi-task time series transformer" Automotive Innovation 7(1): 45 58. DOI: 10.1007/s42154-023-00272-x.
[23] C. Fan, S. Lin, B. Cheng, D. Xu, K. Wang, Y. Peng, and S. Kwong, (2024) “EEG-TransMTL: A transformer based multi-task learning network for thermal comfort evaluation of railway passenger from EEG" Information Sciences 657: 119908. DOI: 10.1016/j.ins.2023.119908.
[24] W. Li, N. Zhou, and X. Qu. “Enhancing eye tracking performance through multi-task learning transformer”. In: International Conference on Human Computer Interaction. Springer. 2024, 31–46. DOI: 10. 1007/978-3-031-61572-6_3.