Advertisement

Action Recognition Using Visual Attention with Reinforcement Learning

  • Hongyang Li
  • Jun Chen
  • Ruimin Hu
  • Mei Yu
  • Huafeng Chen
  • Zengmin Xu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11296)

Abstract

Human action recognition in videos is a challenging and significant task with a broad range of applications. The advantage of the visual attention mechanism is that it can effectively reduce noise interference by focusing on the relevant parts of the image and ignoring the irrelevant part. We propose a deep visual attention model with reinforcement learning for this task. We use Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) units as a learning agent. The agent interact with video and decides both where to look next frame and where to locate the most relevant region of the selected video frame. REINFORCE method is used to learn the agent’s decision policy and back-propagation method is used to train the action classifier. The experimental results demonstrate that this glimpse window can focus on important clues. Our model achieves significant performance improvement on the action recognition datasets: UCF101 and HMDB51.

Keywords

Human action recognition Reinforcement learning Visual attention 

Notes

Acknowledgement

The research was supported by the National Nature Science Foundation of China (61671336, U1611461, U1736206), Technology Research Program of Ministry of Public Security (2016JSYJA12), Hubei Province Technological Innovation Major Project (2016AAA015, 2017AAA123), Hubei Provincial Education Department Project (16Q070), Nature Science Foundation of Jiangsu Province (BK20160386).

References

  1. 1.
    Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: ICLR (2015)Google Scholar
  2. 2.
    Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)Google Scholar
  3. 3.
    Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)Google Scholar
  4. 4.
    Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal residual networks for video action recognition. In: NIPS (2016)Google Scholar
  5. 5.
    Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR (2016)Google Scholar
  6. 6.
    Girdhar, R., Ramanan, D.: Attentional pooling for action recognition. In: NIPS (2017)Google Scholar
  7. 7.
    Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: ActionVLAD: learning spatio-temporal aggregation for action classification. In: CVPR (2017)Google Scholar
  8. 8.
    Ji, Y., Yang, Y., Xu, X., Shen, H.T.: One-shot learning based pattern transition map for action early recognition. Signal Process. 143, 364–370 (2018)CrossRefGoogle Scholar
  9. 9.
    Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)Google Scholar
  10. 10.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
  11. 11.
    Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: ICCV (2011)Google Scholar
  12. 12.
    Li, Z., Gavrilyuk, K., Gavves, E., Jain, M., Snoek, C.G.: VideoLSTM convolves, attends and flows for action recognition. Comput. Vis. Image Underst. 166, 41–50 (2018)CrossRefGoogle Scholar
  13. 13.
    Long, X., Gan, C., de Melo, G., Wu, J., Liu, X., Wen, S.: Attention clusters: purely attention based local feature integration for video classification. In: CVPR (2018)Google Scholar
  14. 14.
    Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: NIPS (2014)Google Scholar
  15. 15.
    Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: CVPR (2015)Google Scholar
  16. 16.
    Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. In: ICLR (2016)Google Scholar
  17. 17.
    Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)Google Scholar
  18. 18.
    Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)
  19. 19.
    Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: ICML (2015)Google Scholar
  20. 20.
    Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)Google Scholar
  21. 21.
    Wang, K., Wang, X., Lin, L., Wang, M., Zuo, W.: 3D human activity recognition with reconfigurable convolutional neural networks (2014)Google Scholar
  22. 22.
    Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep convolutional descriptors. In: CVPR (2015)Google Scholar
  23. 23.
    Wang, L., Li, W., Li, W., Van Gool, L.: Appearance-and-relation networks for video classification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  24. 24.
    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_2CrossRefGoogle Scholar
  25. 25.
    Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)Google Scholar
  26. 26.
    Xu, Z., Hu, R., Chen, J., Chen, H., Li, H.: Global contrast based salient region boundary sampling for action recognition. In: Tian, Q., Sebe, N., Qi, G.-J., Huet, B., Hong, R., Liu, X. (eds.) MMM 2016. LNCS, vol. 9516, pp. 187–198. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-27671-7_16CrossRefGoogle Scholar
  27. 27.
    Yeung, S., Russakovsky, O., Mori, G., Fei-Fei, L.: End-to-end learning of action detection from frame glimpses in videos. In: CVPR (2016)Google Scholar
  28. 28.
    Zhang, M., Yang, Y., Ji, Y., Xie, N., Shen, F.: Recurrent attention network using spatial-temporal relations for action recognition. Signal Process. 145, 137–145 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Hongyang Li
    • 1
    • 3
  • Jun Chen
    • 1
    • 2
  • Ruimin Hu
    • 1
    • 2
  • Mei Yu
    • 3
  • Huafeng Chen
    • 4
  • Zengmin Xu
    • 1
  1. 1.National Engineering Research Center for Multimedia Software, School of Computer ScienceWuhan UniversityWuhanChina
  2. 2.Hubei Key Laboratory of Multimedia and Network Communication EngineeringWuhan UniversityWuhanChina
  3. 3.College of Computer and Information TechnologyChina Three Gorges UniversityYichangChina
  4. 4.Jingchu University of TechnologyJingmenChina

Personalised recommendations