Skip to main content
SpringerLink
Log in

Research on Temporal Structure for Action Recognition

  • Conference paper
  • First Online:
Biometric Recognition (CCBR 2017)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 10568))

Included in the following conference series:

Abstract

Cameras may be employed to facilitate data collection, to serve as a data source for controlling actuators, or to monitor the status of a process which includes tracking. We proposed an algorithm to explore the temporal relations between trajectory groups in videos, and applied it to action recognition and intelligent human-machine interaction systems. The trajectory components are application-independent features, and function well as mid-level descriptors of actions in videos. The experiments demonstrated performance improvements compared with a pure bag-of-features method. The success of this semantics-free recognition method provides the potential to define high-level actions using low-level components and temporal the relationships between them. This is similar to the way humans perceive and recognize actions.

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

References

  1. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection, In: IEEE Conference on Computer Vision Pattern Recognition (CVPR), pp. 886–893 (2005)

    Google Scholar 

  2. Laptev, I., Caputo, B., Schuldt, C., Lindeberg, T.: Local velocity-adapted motion events for spatio-temporal recognition. Comput. Vis. Image Underst. (CVIU) 108(3), 207–229 (2007)

    Article  Google Scholar 

  3. Yu, E., Aggarwal, J.K.: Human action recognition with extremities as semantic posture representation, In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2009)

    Google Scholar 

  4. Lin, Z., Jiang, Z., Davis, L.: Recognizing actions by shape-motion prototype trees. In: IEEE International Conference on Computer Vision (ICCV), pp. 444–451 (2009)

    Google Scholar 

  5. Wang, H., Kläser, A., Schmid, C., Liu, C.-L.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vis. (IJCV) 103(1), 60–79 (2013)

    Article  MathSciNet  Google Scholar 

  6. Wang, H., Kläser, A., Schmid, C., Liu, C.: Action recognition by dense trajectories, In: IEEE Conference Computer Vision on Pattern Recognition (CVPR), pp. 3169–3176 (2011)

    Google Scholar 

  7. Petridis, S., Paliouras, G., Perantonis, S.J.: Allen’s hourglass: probabilistic treatment of interval relations, In: International Symposium Temporal Representation and Reasoning, pp. 87–94 (2010)

    Google Scholar 

Download references

Acknowledgement

This paper is supported by the National Natural Science Foundation of China (Grant Nos. 61501467, 61502506, and 61402484).

Author information

Authors and Affiliations

  1. People’s Public Security University of China, Beijing, 100038, China

    Wengang Feng, Huawei Tian & Yanhui Xiao

Authors
  1. Wengang Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Huawei Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yanhui Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wengang Feng .

Editor information

Editors and Affiliations

  1. Tsinghua University, Beijing, China

    Jie Zhou

  2. Beihang University, Beijing, China

    Yunhong Wang

  3. Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Zhenan Sun

  4. Computing and Technology, Chinese Academy of Sciences, Beijing, China

    Yong Xu

  5. Shenzhen University, Shenzhen, China

    Linlin Shen

  6. Tsinghua University, Beijing, China

    Jianjiang Feng

  7. Chinese Academy of Sciences, Beijing, China

    Shiguang Shan

  8. Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

    Yu Qiao

  9. Graduate School at Shenzhen, Tsinghua University, Shenzhen, China

    Zhenhua Guo

  10. Shenzhen University, Shenzhen, China

    Shiqi Yu

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Feng, W., Tian, H., Xiao, Y. (2017). Research on Temporal Structure for Action Recognition. In: Zhou, J., et al. Biometric Recognition. CCBR 2017. Lecture Notes in Computer Science(), vol 10568. Springer, Cham. https://doi.org/10.1007/978-3-319-69923-3_67

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-69923-3_67

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-69922-6

  • Online ISBN: 978-3-319-69923-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation