Combining Deep Learning and Preference Learning for Object Tracking

  • Shuchao Pang
  • Juan José del Coz
  • Zhezhou YuEmail author
  • Oscar Luaces
  • Jorge Díez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9949)


Object tracking is nowadays a hot topic in computer vision. Generally speaking, its aim is to find a target object in every frame of a video sequence. In order to build a tracking system, this paper proposes to combine two different learning frameworks: deep learning and preference learning. On the one hand, deep learning is used to automatically extract latent features for describing the multi-dimensional raw images. Previous research has shown that deep learning has been successfully applied in different computer vision applications. On the other hand, object tracking can be seen as a ranking problem, in the sense that the regions of an image can be ranked according to their level of overlapping with the target object. Preference learning is used to build the ranking function. The experimental results of our method, called \( DPL^{2} \)(Deep & Preference Learning), are competitive with respect to the state-of-the-art algorithms.


Deep learning Preference learning Object tracking 



This work was funded by Ministerio de Economía y Competitividad de España (grant TIN2015-65069-C2-2-R), Specialized Research Fund for the Doctoral Program of Higher Education of China (grant 20120061110045) and the Project of Science and Technology Development Plan of Jilin Province, China (grant 20150204007GX). The paper was written while Shuchao Pang was visiting the University of Oviedo at Gijón.


  1. 1.
    Bahamonde, A., Bayón, G.F., Díez, J., Quevedo, J.R., Luaces, O., del Coz, J.J., Alonso, J., Goyache, F.: Feature subset selection for learning preferences: a case study. In: ACM ICML (2004)Google Scholar
  2. 2.
    Bai, Y., Tang, M.: Robust tracking via weakly supervised ranking svm. In: IEEE CCVPR (2012)Google Scholar
  3. 3.
    Dai, P., Liu, K., Xie, Y., Li, C.: Online co-training ranking svm for visual tracking. In: IEEE ICASSP (2014)Google Scholar
  4. 4.
    Demšar, J.: Statistical comparisons of classifiers over multiple data sets. JMLR 7, 1–30 (2006)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Jepson, A.D., Fleet, D.J., El-Maraghi, T.F.: Robust online appearance models for visual tracking. IEEE PAMI 25(10), 1296–1311 (2003)CrossRefGoogle Scholar
  6. 6.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  7. 7.
    Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)zbMATHGoogle Scholar
  8. 8.
    Wang, N., Yeung, D.Y.: Learning a deep compact image representation for visual tracking. In: NIPS (2013)Google Scholar
  9. 9.
    Wu, Y., Lim, J., Yang, M.: Object tracking benchmark. IEEE PAMI 37(9), 1834–1848 (2015)CrossRefGoogle Scholar
  10. 10.
    Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. (CSUR) 38(4), 13 (2006)CrossRefGoogle Scholar
  11. 11.
    Zhao, L., Hu, Q., Zhou, Y.: Heterogeneous features integration via semi-supervised multi-modal deep networks. In: Arik, S., Huang, T., Lai, W.K., Liu, Q. (eds.) ICONIP 2015. LNCS, vol. 9492, pp. 11–19. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-26561-2_2 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Shuchao Pang
    • 1
    • 2
  • Juan José del Coz
    • 2
  • Zhezhou Yu
    • 1
    Email author
  • Oscar Luaces
    • 2
  • Jorge Díez
    • 2
  1. 1.College of Computer Science and TechnologyJilin UniversityChangchunChina
  2. 2.Artificial Intelligence CenterUniversity of OviedoGijónSpain

Personalised recommendations