Abstract
In the field of video-based action recognition, a majority of advanced approaches train a two-stream architecture in which an appearance stream for images and a motion stream for optical flow frames. Due to the considerable computation cost of optical flow and high inference latency of the two-stream method, knowledge distillation is introduced to efficiently capture two-stream representation while only inputting RGB images. Following this technique, this paper proposes a novel distillation learning strategy to sufficiently learn and mimic the representation of the motion stream. Besides, we propose a lightweight attention-based fusion module to uniformly exploit both appearance and motion information. Experiments illustrate that the proposed distillation strategy and fusion module achieve better performance over the baseline technique, and our proposal outperforms the known state-of-art approaches in terms of single-stream and traditional two-stream methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
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)
Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: MARS: motion-augmented RGB stream for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7882–7891 (2019)
Diba, A., Sharma, V., Van Gool, L.: Deep temporal linear encoding networks. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 2329–2338 (2017)
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)
Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576 (2015)
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)
Goyal, R., et al.: The “something something” video database for learning and evaluating visual common sense. In: ICCV, vol. 1, p. 3 (2017)
Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6546–6555 (2018)
Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_43
Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)
Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
Liu, H., Tu, J., Liu, M.: Two-stream 3D convolutional neural network for skeleton-based action recognition. arXiv preprint arXiv:1705.08106 (2017)
Pérez, J.S., Meinhardt-Llopis, E., Facciolo, G.: Tv-l1 optical flow estimation. Image Process. Line 2013, 137–150 (2013)
Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976–990 (2010)
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568–576 (2014)
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)
Tran, D., Ray, J., Shou, Z., Chang, S.F., Paluri, M.: Convnet architecture search for spatiotemporal feature learning. arXiv preprint arXiv:1708.05038 (2017)
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450–6459 (2018)
Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Van Gool, L.: Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41, 2740–2755 (2018)
Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)
Xu, H., Das, A., Saenko, K.: R-C3D: region convolutional 3d network for temporal activity detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5783–5792 (2017)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Zhang, J., Shen, F., Xu, X., Shen, H.T.: Cooperative cross-stream network for discriminative action representation. arXiv preprint arXiv:1908.10136 (2019)
Zhu, J., Zhu, Z., Zou, W.: End-to-end video-level representation learning for action recognition. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 645–650. IEEE (2018)
Acknowledgment
This research is supported by The Foundation of Sichuan Provincial Education Department (NO. 18ZA0501).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, L. et al. (2020). Learning and Distillating the Internal Relationship of Motion Features in Action Recognition. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Communications in Computer and Information Science, vol 1332. Springer, Cham. https://doi.org/10.1007/978-3-030-63820-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-63820-7_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63819-1
Online ISBN: 978-3-030-63820-7
eBook Packages: Computer ScienceComputer Science (R0)