Skip to main content
SpringerLink
Log in
Book cover

International Conference on Intelligent Science and Big Data Engineering

IScIDE 2015: Intelligence Science and Big Data Engineering. Image and Video Data Engineering pp 145–153Cite as

Assigning PLS Based Descriptors by SVM in Action Recognition

  • Conference paper
  • First Online:

  • 2401 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 9242))

Abstract

In this paper, we propose assigning PLS based descriptors by SVM to obtain the representations of human action videos. First, in addition to the spatially gradient orientation, we add spatio-temporal gradient statistic to generate the extended Histogram of Oriented Gradient (HOG). Second, different from requently-used cuboid descriptors in which Principal Component Analysis (PCA) is applied for dimension reduction, the proposed features utilize the Partial Least Squares (PLS) method for better performance. Then, we apply a multi-class SVM for assignment instead of assigning descriptors to the nearest (Euclidean distance) visual word in traditional Bag of Visual Words (BOVW) framework. Finally, the K-nearest neighbor algorithm is used to classify the histogram of visual words. The experimental results on the facial expression dataset and KTH human activity dataset validate the effectiveness of our proposed method.

This is a preview of subscription content, 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

Learn about institutional subscriptions

References

  1. Laptev, I.: On space-time interest points. Int. J. Comput. Vis. 64(2), 107–123 (2005)

    Article  MathSciNet  Google Scholar 

  2. Wang, H., Yuan, C., Luo, G., Weiming, H., Sun, C.: Action recognition using linear dynamic systems. Pattern Recogn. 46(6), 1710–1718 (2013)

    Article  Google Scholar 

  3. Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976–990 (2010)

    Article  Google Scholar 

  4. Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos “in the wild”. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1996–2003 (2009)

    Google Scholar 

  5. Sadanand, S., Corso, J.J.: Action bank: a high-level representation of activity in video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1234–1241 (2012)

    Google Scholar 

  6. Tamrakar, A., Ali, S., Yu, Q., Liu, J., Javed, O., Divakaran, A., Cheng, H., Sawhney, H.: Evaluation of low-level features and their combinations for complex event detection in open source videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3681–3688 (2012)

    Google Scholar 

  7. Klaser, A., Marszalek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients. In: Proceedings of the British Machine Vision Conference, pp. 995–1004 (2008)

    Google Scholar 

  8. Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)

    Google Scholar 

  9. Wang, H., Ulla, M.M., Klaser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: Proceedings of the British Machine Vision Conference 124(11), pp. 1–124 (2009)

    Google Scholar 

  10. Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: Proceedings of the International Conference on Pattern Recognition, pp. 32–36 (2004)

    Google Scholar 

  11. Wang, H., Yuan, C., Weiming, H., Sun, C.: Supervised class-specific dictionary learning for sparse modeling in action recognition. Pattern Recog. 45(11), 3902–3911 (2012)

    Article  Google Scholar 

  12. Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatiotemporal features. In: IEEE International Workshop on Visual Surveillance and Performance valuation of Tracking and Surveillance, pp. 65–72 (2005)

    Google Scholar 

  13. Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2169–2178 (2006)

    Google Scholar 

  14. Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 794–1801 (2009)

    Google Scholar 

  15. Schwartz, W.R., Davis, L.S.: Learning discriminative appearance-based models using partial least squares. In: 2009 XXII Brazilian Symposium on Computer Graphics and Image Processing, pp. 322–329 (2009)

    Google Scholar 

  16. Schwartz, W.R., Kembhavi, A., Harwood, D., Davis, L.S.: Human detection using partial least squares analysis. In: IEEE 12th International Conference on Computer vision, pp. 24–31 (2009)

    Google Scholar 

  17. Hu, Y.-G., Ren, C.-X., Yao, Y.-F., Li, W.-Y., Feng-Wang, : Face recognition using nonlinear partial least squares in reproducing kernel hilbert space. In: Liu, C.-L., Zhang, C., Wang, L. (eds.) CCPR 2012. CCIS, vol. 321, pp. 316–323. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  18. Everts, I., van Gemert, J.C., Gevers, T.: Evaluation of color STIPs for human action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2850–2857 (2013)

    Google Scholar 

  19. Crammer, K., Singer, Y.: On the algorithmic implementation of multi-class SVMs. J. Mach. Learn. Res. 2(2), 265–292 (2001)

    MATH  Google Scholar 

  20. Bregonzio, M., Gong, S., Xiang, T.: Recognising action as clouds of space-time interest points. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1948–1955 (2009)

    Google Scholar 

  21. Niebles, J.C., Chen, C.-W., Fei-Fei, L.: Modeling temporal structure of decomposable motion segments for activity classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 392–405. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  22. Li, B., Ayazoglu, M., Mao, T., Camps, O., Sznaier, M.: Activity recognition using dynamic subspace angles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3193–3200 (2011)

    Google Scholar 

Download references

Acknowledgments

The work was supported in part by National Natural Science Foundation of China under Grant No. 61305058, No. 61375001, Natural Science Foundation of Jiangsu Province of China under Grant No. BK20130471 and No. BK20140638, China Postdoctoral Science Foundation under grant No.2013M540404, Jiangsu Planned Projects for Postdoctoral Research Funds under grant No.1401037B, open fund of Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education under Grant No.MCCSE2013B01, the Open Project Program of Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University (No. CDLS-2014-04), and A Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD), and the Fundamental Research Funds for the Central Universities.

Author information

Authors and Affiliations

  1. School of Automation, Southeast University, Nanjing, 210096, China

    Jiayu Sheng, Biyun Sheng, Wankou Yang & Changyin Sun

  2. Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, 210096, China

    Jiayu Sheng, Biyun Sheng, Wankou Yang & Changyin Sun

  3. Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, 210096, China

    Wankou Yang

Authors
  1. Jiayu Sheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Biyun Sheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wankou Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Changyin Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Biyun Sheng .

Editor information

Editors and Affiliations

  1. Zhejiang University, Hangzhou, China

    Xiaofei He

  2. Xidian University, Xi'an, China

    Xinbo Gao

  3. Northwestern Polytechnical University, Shaanxi, China

    Yanning Zhang

  4. Nanjing University, Nanjing, China

    Zhi-Hua Zhou

  5. Chinese Academy of Sciences, Beijing, China

    Zhi-Yong Liu

  6. Suzhou University of Science and Technology, Suzhou, China

    Baochuan Fu

  7. Suzhou University of Science and Technology, Jiangsu, China

    Fuyuan Hu

  8. Suzhou University of Science and Technology, Jiangsu, China

    Zhancheng Zhang

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Sheng, J., Sheng, B., Yang, W., Sun, C. (2015). Assigning PLS Based Descriptors by SVM in Action Recognition. In: He, X., et al. Intelligence Science and Big Data Engineering. Image and Video Data Engineering. IScIDE 2015. Lecture Notes in Computer Science(), vol 9242. Springer, Cham. https://doi.org/10.1007/978-3-319-23989-7_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-23989-7_16

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-23987-3

  • Online ISBN: 978-3-319-23989-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation