Abstract
Action recognition is a crucial task in computer vision and video analysis. The Two-stream network and 3D ConvNets are representative works. Although both of them have achieved outstanding performance, the optical flow and 3D convolution require huge computational effort, without taking into account the need for real-time applications. Current work extracts motion vectors and residuals directly from the compressed video to replace optical flow. However, due to the noisy and inaccurate representation of the motion, the accuracy of the model is significantly decreased when using motion vectors as input. Besides the current works focus only on improving accuracy or reducing computational cost, without exploring the tradeoff strategy between them. In this paper, we propose a light and efficient multi-stream framework, including a motion temporal fusion module (MTFM) and a double compressed knowledge distillation module (DCKD). MTFM improves the network’s ability to extract complete motion information and compensates to some extent for the problem of inaccurate description of motion information by motion vectors in compressed video. DCKD allows the student network to gain more knowledge from teacher with less parameters and input frames. Experimental results on the two public benchmarks(UCF-101 and HMDB-51) outperform the state of the art on the compressed domain.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, vol. 27 (2014)
Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933–1941 (2016)
Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20–36. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_2
Zhu, Y., Lan, Z., Newsam, S., Hauptmann, A.: Hidden two-stream convolutional networks for action recognition. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 363–378. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20893-6_23
Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: Actionvlad: learning spatio-temporal aggregation for action classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 971–980 (2017)
Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489–4497 (2015)
Diba, A., et al.: Temporal 3d convnets: new architecture and transfer learning for video classification. arXiv preprint arXiv:1711.08200 (2017)
Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3d residual networks. In: proceedings of the IEEE International Conference on Computer Vision, pp. 5533–5541 (2017)
Kantorov, V., Laptev, I.: Efficient feature extraction, encoding and classification for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2593–2600 (2014)
Töreyin, B.U., Cetin, A.E., Aksay, A., Akhan, M.B.: Moving object detection in wavelet compressed video. Sig. Process. Image Commun. 20(3), 255–264 (2005)
Yeo, B.L., Liu, B.: Rapid scene analysis on compressed video. IEEE Trans. Circuits Syst. Video Tech. 5(6), 533–544 (1995)
Wu, C.Y., Zaheer, M., Hu, H., Manmatha, R., Smola, A.J., Krähenbühl, P.: Compressed video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6026–6035 (2018)
Shou, Z., et al.: Dmc-net: generating discriminative motion cues for fast compressed video action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1268–1277 (2019)
Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with enhanced motion vector CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2718–2726 (2016)
Wu, M.C., Chiu, C.T.: Multi-teacher knowledge distillation for compressed video action recognition based on deep learning. J. Syst. Archit. 103, 101695 (2020)
Lin, J., Gan, C., Han, S.: Tsm: temporal shift module for efficient video understanding. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7083–7093 (2019)
Zhao, B., Cui, Q., Song, R., Qiu, Y., Liang, J.: Decoupled knowledge distillation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11953–11962 (2022)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Soomro, K., Zamir, A.R., Shah, M.: A dataset of 101 human action classes from videos in the wild. Center for Res. Comput. Vis. 2(11) (2012)
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision, pp. 2556–2563. IEEE (2011)
Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299–6308 (2017)
Yang, K., et al.: IF-TTN: Information fused temporal transformation network for video action recognition. arXiv Computer Vision and Pattern Recognition (2019)
Huo, Y., Xu, X., Lu, Y., Niu, Y., Lu, Z., Wen, J.R.: Mobile video action recognition. arXiv preprint arXiv:1908.10155 (2019)
Battash, B., Barad, H., Tang, H., Bleiweiss, A.: Mimic the raw domain: accelerating action recognition in the compressed domain. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 684–685 (2020)
Chen, J., Ho, C.M.: Mm-vit: multi-modal video transformer for compressed video action recognition. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1910–1921 (2022)
Yang, X., Yang, C.: Imrnet: an iterative motion compensation and residual reconstruction network for video compressed sensing. In: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2350–2354. IEEE (2021)
Li, B., Kong, L., Zhang, D., Bao, X., Huang, D., Wang, Y.: Towards practical compressed video action recognition: a temporal enhanced multi-stream network. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 3744–3750. IEEE (2021)
Acknowledgment
This work was supported by the Inner Mongolia Natural Science Foundation of China under Grant No. 2021MS06016.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Guo, J., Zhang, J., Zhang, X., Ma, M. (2023). LAE-Net: Light and Efficient Network for Compressed Video Action Recognition. In: Dang-Nguyen, DT., et al. MultiMedia Modeling. MMM 2023. Lecture Notes in Computer Science, vol 13834. Springer, Cham. https://doi.org/10.1007/978-3-031-27818-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-27818-1_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27817-4
Online ISBN: 978-3-031-27818-1
eBook Packages: Computer ScienceComputer Science (R0)