As a major branch of video understanding, human action recognition has become a popular research topic in the field of computer vision and has a wide range of applications in many areas. To address the problems of high parameter consumption and weak spatiotemporal modeling capabilities in existing action recognition methods, this study proposes a lightweight dual-branch convolutional network called SlowFast-Light Net. Inspired and influenced by the renowned two-branch SlowFast network proposed by the expert Kaiming He, this study adopts a lightweight two-branch network design, which is an improvement based on the SlowFast network. The network significantly reduces parameter consumption by introducing a lightweight feature extraction network and accelerating the model convergence speed. This study conducts experimental verification on the UCF101 and HMDB51 datasets, achieving an action recognition accuracy of 93.80% and 80.00%, respectively, on the two test sets. The experimental results showed that the model proposed in this study achieved a recognition accuracy comparable to that of the original model with a considerably lower number of parameters.

1. [1] S. Hoshino and K. Niimura, “Robot vision system for human detection and action recognition,” J. Adv. Comput. Intell. Intell. Inform., Vol.24, No.3, pp. 346-356, 2020. https://doi.org/10.20965/jaciii.2020.p0346
2. [2] C. Feichtenhofer, H. Fan, J. Malik, and K. He, “SlowFast networks for video recognition,” 2019 IEEE/CVF Int. Conf. on Computer Vision, pp. 6201-6210, 2019. https://doi.org/10.1109/ICCV.2019.00630
3. [3] X. Zhang, X. Zhou, M. Lin, and J. Sun, “ShuffleNet: An extremely efficient convolutional neural network for mobile devices,” 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 6848-6856, 2018. https://doi.org/10.1109/CVPR.2018.00716
4. [4] A. G. Howard et al., “MobileNets: Efficient convolutional neural networks for mobile vision applications,” arXiv:1704.04861, 2017. https://doi.org/10.48550/arXiv.1704.04861
5. [5] M. Tan and Q. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” Proc. of the 36th Int. Conf. on Machine Learning, pp. 6105-6114, 2019.
6. [6] K. Simonyan and A. Zisserman, “Two-stream convolutional networks for action recognition in videos,” Proc. of the 28th Int. Conf. on Neural Information Processing Systems, Vol.1, pp. 568-576, 2014.
7. [7] C. Feichtenhofer, A. Pinz, and A. Zisserman, “Convolutional two-stream network fusion for video action recognition,” 2016 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1933-1941, 2016. https://doi.org/10.1109/CVPR.2016.213
8. [8] D. Tran, L. Bourdev, R. Fergus, L. Torresani, and M. Paluri, “Learning spatiotemporal features with 3D convolutional networks,” 2015 IEEE Int. Conf. on Computer Vision, pp. 4489-4497, 2015. https://doi.org/10.1109/ICCV.2015.510
9. [9] Z. Qiu, T. Yao, and T. Mei, “Learning spatio-temporal representation with pseudo-3D residual networks,” 2017 IEEE Int. Conf. on Computer Vision, pp. 5534-5542, 2017. https://doi.org/10.1109/ICCV.2017.590
10. [10] J. Carreira and A. Zisserman, “Quo vadis, action recognition? A new model and the Kinetics dataset,” 2017 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 4724-4733, 2017. https://doi.org/10.1109/CVPR.2017.502
11. [11] F. N. Iandola et al., “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size,” arXiv:1602.07360, 2016. https://doi.org/10.48550/arXiv.1602.07360
12. [12] N. Ma, X. Zhang, H.-T. Zheng, and J. Sun, “ShuffleNet V2: Practical guidelines for efficient CNN architecture design,” Proc. of the 15th European Conf. on Computer Vision, Part 14, pp. 122-138, 2018. https://doi.org/10.1007/978-3-030-01264-9_8
13. [13] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 4510-4520, 2018. https://doi.org/10.1109/CVPR.2018.00474
14. [14] P. Wang, L. Li, F. Pan, and L. Wang, “Lightweight bilateral network for real-time semantic segmentation,” J. Adv. Comput. Intell. Intell. Inform., Vol.27, No.4, pp. 673-682, 2023. https://doi.org/10.20965/jaciii.2023.p0673
15. [15] Z. Du, Y. Jin, H. Ma, and P. Liu, “A lightweight and accurate method for detecting traffic flow in real time,” J. Adv. Comput. Intell. Intell. Inform., Vol.27, No.6, pp. 1086-1095, 2023. https://doi.org/10.20965/jaciii.2023.p1086
16. [16] Y. Li et al., “TEA: Temporal excitation and aggregation for action recognition,” 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 906-915, 2020. https://doi.org/10.1109/CVPR42600.2020.00099
17. [17] C. Gu et al., “AVA: A video dataset of spatio-temporally localized atomic visual actions,” 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 6047-6056, 2018. https://doi.org/10.1109/CVPR.2018.00633
18. [18] K. Soomro, A. R. Zamir, and M. Shah, “UCF101: A dataset of 101 human actions classes from videos in the wild,” arXiv:1212.0402, 2012. https://doi.org/10.48550/arXiv.1212.0402
19. [19] S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” Proc. of the 32nd Int. Conf. on Machine Learning, pp. 448-456, 2015.
20. [20] G. Bertasius, H. Wang, and L. Torresani, “Is space-time attention all you need for video understanding?,” arXiv:2102.05095, 2021. https://doi.org/10.48550/arXiv.2102.05095
21. [21] D. Chen et al., “LS-VIT: Vision Transformer for action recognition based on long and short-term temporal difference,” Frontiers in Neurorobotics, Vol.18, Article No.1457843, 2024. https://doi.org/10.3389/fnbot.2024.1457843
22. [22] O. Köpüklü, N. Kose, A. Gunduz, and G. Rigoll, “Resource efficient 3D convolutional neural networks,” 2019 IEEE/CVF Int. Conf. on Computer Vision Workshop, pp. 1910-1919, 2019. https://doi.org/10.1109/ICCVW.2019.00240
23. [23] D. Wei et al., “Efficient dual attention SlowFast networks for video action recognition,” Computer Vision and Image Understanding, Vol.222, Article No.103484, 2022. https://doi.org/10.1016/j.cviu.2022.103484