Skip to main content
SpringerLink
Log in

Hidden Two-Stream Convolutional Networks for Action Recognition

  • Conference paper
  • First Online:
Book cover Computer Vision – ACCV 2018 (ACCV 2018)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 11363))

Included in the following conference series:

Abstract

Analyzing videos of human actions involves understanding the temporal relationships among video frames. State-of-the-art action recognition approaches rely on traditional optical flow estimation methods to pre-compute motion information for CNNs. Such a two-stage approach is computationally expensive, storage demanding, and not end-to-end trainable. In this paper, we present a novel CNN architecture that implicitly captures motion information between adjacent frames. We name our approach hidden two-stream CNNs because it only takes raw video frames as input and directly predicts action classes without explicitly computing optical flow. Our end-to-end approach is 10x faster than its two-stage baseline. Experimental results on four challenging action recognition datasets: UCF101, HMDB51, THUMOS14 and ActivityNet v1.2 show that our approach significantly outperforms the previous best real-time approaches.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    Detailed comparisons can be found in the supplementary material.

  2. 2.

    In general, the requirement for real-time processing is 25 fps. We also compare to other non real-time approaches in the supplementary materials.

References

  1. Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

    Google Scholar 

  2. Diba, A., Pazandeh, A.M., Van Gool, L.: Efficient two-stream motion and appearance 3D CNNs for video classification. In: European Conference on Computer Vision (ECCV) Workshops (2016)

    Google Scholar 

  3. Fernando, B., Gavves, E., Oramas, J.M., Ghodrati, A., Tuytelaars, T.: Modeling video evolution for action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)

    Google Scholar 

  4. Fischer, P., et al.: FlowNet: learning optical flow with convolutional networks. In: International Conference on Computer Vision (ICCV) (2015)

    Google Scholar 

  5. Gorban, A., et al.: THUMOS challenge: action recognition with a large number of classes (2015). http://www.thumos.info/

  6. Gu, B., Xin, M., Huo, Z., Huang, H.: Asynchronous doubly stochastic sparse kernel learning. In: Association for the Advancement of Artificial Intelligence (AAAI) (2018)

    Google Scholar 

  7. Heilbron, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: ActivityNet: a large-scale video benchmark for human activity understanding. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)

    Google Scholar 

  8. Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

    Google Scholar 

  9. Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer network. In: Neural Information Processing Systems (NIPS) (2015)

    Google Scholar 

  10. Kantorov, V., Laptev, I.: Efficient feature extraction, encoding and classification for action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)

    Google Scholar 

  11. Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)

    Google Scholar 

  12. Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: International Conference on Computer Vision (ICCV) (2011)

    Google Scholar 

  13. Lan, Z., Zhu, Y., Hauptmann, A.G., Newsam, S.: Deep local video feature for action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

    Google Scholar 

  14. Miao, X., Zhen, X., Liu, X., Deng, C., Athitsos, V., Huang, H.: Direct shape regression networks for end-to-end face alignment. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  15. Ng, J.Y.H., Choi, J., Neumann, J., Davis, L.S.: ActionFlowNet: learning motion representation for action recognition. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2018)

    Google Scholar 

  16. Ng, J.Y.H., Hausknecht, M., Vijay., S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)

    Google Scholar 

  17. Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: International Conference on Computer Vision (ICCV) (2017)

    Google Scholar 

  18. Sedaghat, N.: Next-flow: hybrid multi-tasking with next-frame prediction to boost optical-flow estimation in the wild. arXiv:1612.03777 (2016)

  19. Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Neural Information Processing Systems (NIPS) (2014)

    Google Scholar 

  20. Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human action classes from videos in the wild. In: CRCV-TR-12-01 (2012)

    Google Scholar 

  21. Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: International Conference on Computer Vision (ICCV) (2015)

    Google Scholar 

  22. Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  23. Wang, H., Schmid, C.: Action recognition with improved trajectories. In: International Conference on Computer Vision (ICCV) (2013)

    Google Scholar 

  24. Wang, L., Xiong, Y., Wang, Z., Qiao, Y.: Towards good practices for very deep two-stream ConvNets. arXiv:1507.02159 (2015)

  25. 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

    Chapter  Google Scholar 

  26. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004)

    Article  Google Scholar 

  27. Wu, C.Y., Zaheer, M., Hu, H., Manmatha, R., Smola, A.J., Krähenbühl, P.: Compressed video action recognition. arXiv:1712.00636 (2017)

  28. Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding. arXiv:1712.04851 (2017)

  29. Xue, J., Zhang, H., Dana, K.: Deep texture manifold for ground terrain recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  30. Xue, T., Chen, B., Wu, J., Wei, D., Freeman, W.T.: Video enhancement with task-oriented flow. arXiv:1711.09078 (2017)

  31. Yu, J.J., Harley, A.W., Derpanis, K.G.: Back to basics: unsupervised learning of optical flow via brightness constancy and motion smoothness. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 3–10. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49409-8_1

    Chapter  Google Scholar 

  32. Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74936-3_22

    Chapter  Google Scholar 

  33. Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with enhanced motion vector CNNs. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)

    Google Scholar 

  34. Zhu, Y., Long, Y., Guan, Y., Newsam, S., Shao, L.: Towards universal representation for unseen action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  35. Zhu, Y., Newsam, S.: DenseNet for dense flow. In: IEEE International Conference on Image Processing (ICIP) (2017)

    Google Scholar 

  36. Zhu, Y., Newsam, S.: Learning optical flow via dilated networks and occlusion reasoning. In: IEEE International Conference on Image Processing (ICIP) (2018)

    Google Scholar 

Download references

Acknowledgement

We gratefully acknowledge the support of NVIDIA Corporation through the donation of the Titan Xp GPUs used in this work.

Author information

Authors and Affiliations

  1. University of California at Merced, Merced, CA, 95343, USA

    Yi Zhu & Shawn Newsam

  2. Carnegie Mellon University, Pittsburgh, PA, 15213, USA

    Zhenzhong Lan & Alexander Hauptmann

Authors
  1. Yi Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhenzhong Lan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shawn Newsam
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Alexander Hauptmann
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yi Zhu .

Editor information

Editors and Affiliations

  1. IIIT Hyderabad, Hyderabad, India

    C. V. Jawahar

  2. ANU, Canberra, ACT, Australia

    Hongdong Li

  3. Simon Fraser University, Burnaby, BC, Canada

    Greg Mori

  4. ETH Zurich, Zurich, Zürich, Switzerland

    Konrad Schindler

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1040 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhu, Y., Lan, Z., Newsam, S., Hauptmann, A. (2019). Hidden Two-Stream Convolutional Networks for Action Recognition. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11363. Springer, Cham. https://doi.org/10.1007/978-3-030-20893-6_23

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-20893-6_23

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-20892-9

  • Online ISBN: 978-3-030-20893-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation