SKELETON-BASED HUMAN ACTION RECOGNITION USING SPATIO-TEMPORAL LATENT FEATURES WITH A GCN MODEL

Authors

Avazjon Marakhimov, Tashkent State Technical University. Address: 2 Universitetskaya st., 100095, Tashkent, Uzbekistan. E-mail: avaz.marakhimov@yandex.ru;Follow
Kabul Khudaybergenov, Kimyo International University in Tashkent. Address: st. Shota Rustaveli, 156, 100121 Tashkent, Uzbekistan. E-mail: kabul.kudaybergenov@gmail.com, Phone: +998-91-371-51-27;Follow
Mominov Zakhriddin, Tashkent State University of Economics, Tashkent, Uzbekistan. E-mail: z.muminov@gmail.com.Follow

Abstract

Owing to its resilience to visual noise and viewpoint variations, skeleton-based analysis has become a cornerstone of human action recognition research. Despite its practical significance, existing methodologies often suffer from a reliance on single-stream skeletal representations, which fail to encompass the full complexity of action features. This study introduces Latent Features for Human Action Recognition (LFHAR), a novel architecture designed to overcome these limitations by utilizing diverse spatio-temporal latent representations for improved feature extraction. The approach applies graph-based transformations to individual skeletal frames in temporal sequences, then arranges the derived graph features into spatio-temporal matrices. Evaluation of standard datasets demonstrates the stability and invariance characteristics of the LFHAR architecture. The method produces substantial performance improvements, achieving accuracy increases of 2.7% on dataset NTU-RGB+D-60-classes and 2.1% on dataset NTU-RGB+D-120-classes, confirming its accuracy in improving human action recognition.

First Page

103

Last Page

109

References

1. Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., Liu, J. (2022). Human action recognition from various data modalities: A review. IEEE Trans. Pattern Anal. Mach. Intell.
2. Ahmad, T., Jin, L., Zhan,g X., Lai, S., Tang, G., Lin, L. (2021). Graph convolutional neural network for human action recognition: A comprehensive survey. IEEE Trans. Artif. Intell., 2 (2), 128-145.
3. Cheng, K., Zhang, Y., He, X., Chen, W., Cheng, J., Lu, H. (2020). Skeleton-based action recognition with shift graph convolutional network. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 183-192.
4. Xin, W., Liu, Y., Liu, R., Miao, Q., Shi, C., Pun, C.-M. (2023). Auto-learning-gcn: An ingenious framework for skeleton-based action recognition. Chinese Conference on Pattern Recognition and Computer Vision, Springer, 29-42.
5. Liu, R., Liu, Y., Wu, M., Xin, W., Miao, Q., Liu, X., Li, L. (2025). SG-CLR: Semantic representation-guided contrastive learning for self-supervised skeleton-based action recognition. Pattern Recognit., 162 (2025), 111377.
6. Marakhimov, A.R., Khudaybergenov, K.K. (2025). Softmax Regression with Multi-Connected Weights. Computers.
7. Aouaidjia, K., Zhang, C., Pitas, I., (2025). Spatio-temporal invariant descriptors for skeleton-based human action recognition. Inf Sci (NY), 700, 121832. doi: 10.1016/j.ins.2024.121832 (2025).
8. Tu, Z., et. al. (2022). Maxvit: multi-axis vision transformer. European Conference on Computer Vision, Springer, 459-479.
9. Wang, J. et. al. (2014). Cross-view action modeling, learning and recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2649-2656.
10. Wang, P., et. al. (2016). Action recognition based on joint trajectory maps using convolutional neural networks. Proceedings of the 24th ACM International Conference on Multimedia, 102-106.

Recommended Citation

Marakhimov, Avazjon; Khudaybergenov, Kabul; and Zakhriddin, Mominov (2025) "SKELETON-BASED HUMAN ACTION RECOGNITION USING SPATIO-TEMPORAL LATENT FEATURES WITH A GCN MODEL," Chemical Technology, Control and Management: Vol. 2025: Iss. 6, Article 11.
DOI: https://doi.org/10.59048/2181-1105.1725