Multi-view Regularized Extreme Learning Machine for Human Action Recognition

  • Alexandros Iosifidis
  • Anastasios Tefas
  • Ioannis Pitas
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8445)

Abstract

In this paper, we propose an extension of the ELM algorithm that is able to exploit multiple action representations. This is achieved by incorporating proper regularization terms in the ELM optimization problem. In order to determine both optimized network weights and action representation combination weights, we propose an iterative optimization process. The proposed algorithm has been evaluated by using the state-of-the-art action video representation on three publicly available action recognition databases, where its performance has been compared with that of two commonly used video representation combination approaches, i.e., the vector concatenation before learning and the combination of classification outcomes based on learning on each view independently.

Keywords

Extreme Learning Machine Multi-view Learning Single-hidden Layer Feedforward networks Human Action Recognition 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Turaga, P., Chellappa, R., Subrahmanian, V., Udrea, O.: Machine recognition of human activities: A survey. IEEE Transactions on Circuits and Systems for Video Technology 18(11), 1473–1488 (2008)CrossRefGoogle Scholar
  2. 2.
    Ji, X., Liu, H.: Advances in View-Invariant Human Motion Analysis: Review. IEEE Transactions on Systems, Man and Cybernetics Part–C 40(1), 13–24 (2010)Google Scholar
  3. 3.
    Wang, H., Klaser, A., Schmid, C., Liu, C.L.: Dense Trajectories and Motion Boundary Descriptors for Action Recognition. International Journal of Computer Vision 103(60), 1–20 (2013)CrossRefMATHMathSciNetGoogle Scholar
  4. 4.
    Kittler, J., Hatef, M., Duin, R., Matas, J.: On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(3), 226–239 (1998)CrossRefGoogle Scholar
  5. 5.
    Iosifidis, A., Tefas, A., Pitas, I.: View-invariant action recognition based on Artificial Neural Networks. IEEE Transactions on Neural Networks and Learning Systems 23(3), 412–424 (2012)CrossRefGoogle Scholar
  6. 6.
    Huang, G., Zhu, Q., Siew, C.: Extreme Learning Machine: A new learning scheme for feedfowrard neural networks. In: IEEE International Joint Conference on Neural Networks (2004)Google Scholar
  7. 7.
    Bartlett, P.L.: The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network. IEEE Transactions on Information Theory 44(2), 525–536 (1998)CrossRefMATHMathSciNetGoogle Scholar
  8. 8.
    Minhas, R., Baradarani, A., Seifzadeh, S., Wu, Q.J.: Human action recognition using Extreme Learning Machine based on visual vocabularies. Neurocomputing 73(10), 1906–1917 (2010)CrossRefGoogle Scholar
  9. 9.
    Iosifidis, A., Tefas, A., Pitas, I.: Multi-view Human Action Recognition under Occlusion based on Fuzzy Distances and Neural Networks. In: European Signal Processing Conference (2012)Google Scholar
  10. 10.
    Iosifidis, A., Tefas, A., Pitas, I.: Minimum Class Variance Extreme Learning Machine for Human Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology 23(11), 1968–1979 (2013)CrossRefGoogle Scholar
  11. 11.
    Iosifidis, A., Tefas, A., Pitas, I.: Dynamic action recognition based on Dynemes and Extreme Learning Machine. Pattern Recognition Letters 34, 1890–1898 (2013)CrossRefGoogle Scholar
  12. 12.
    Huang, G., Zhou, H., Ding, Z., Zhang, R.: Extreme Learning Machine for Regression and Multiclass Classification. IEEE Transactions on Systems, Man and Cybernetics Part–B 42(2), 513–529 (2012)CrossRefGoogle Scholar
  13. 13.
    Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
  14. 14.
    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)CrossRefGoogle Scholar
  15. 15.
    Hadfield, S., Bowden, R.: Hollywood 3D: Recognizing Actions in 3D Natural Scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (2013)Google Scholar
  16. 16.
    Lanckriet, G.R.G., Cristianini, N., Ghaoui, L.E., Bartlett, P., Jordan, M.I.: Learning the kernel matrix with semidefinite programming. Journal of Machine Learning Research 5, 27–72 (2013)Google Scholar
  17. 17.
    Bach, F.R., Lanckriet, G.R.G., Jordan, M.I.: Multiple kernel learning, conic duality, and the SMO algorithm. In: International Conference on Machine Learning (2004)Google Scholar
  18. 18.
    Damoulas, T., Girolami, M.A.: Combining feature spaces for classification. Pattern Recognition 42(11), 2671–2683 (2009)CrossRefMATHGoogle Scholar
  19. 19.
    Gonen, M., Alpaydin, E.: Multiple Kernel Learning Algorithms. Journal of Machine Learning Research 12, 2211–2268 (2011)MathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Alexandros Iosifidis
    • 1
  • Anastasios Tefas
    • 1
  • Ioannis Pitas
    • 1
  1. 1.Department of InformaticsAristotle University of ThessalonikiThessalonikiGreece

Personalised recommendations