Skip to main content
Book cover

European Conference on Computer Vision

ECCV 2012: Computer Vision – ECCV 2012 pp 640–653Cite as

Auto-Grouped Sparse Representation for Visual Analysis

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNIP,volume 7572)

Abstract

In this work, we investigate how to automatically uncover the underlying group structure of a feature vector such that each group characterizes certain object-specific patterns, e.g., visual pattern or motion trajectories from one object. By mining the group structure, we can effectively alleviate the mutual inference of multiple objects and improve the performance in various visual analysis tasks. To this end, we propose a novel auto-grouped sparse representation (ASR) method. ASR groups semantically correlated feature elements together through optimally fusing their multiple sparse representations. Due to the intractability of primal objective function, we also propose well-behaved convex relaxation and smooth approximation to guarantee obtaining a global optimal solution effectively. Finally, we apply ASR in two important visual analysis tasks: multi-label image classification and motion segmentation. Comprehensive experimental evaluations show that ASR is able to achieve superior performance compared with the state-of-the-arts on these two tasks.

Download conference paper PDF

References

  1. Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: CVPR (2005)

    Google Scholar 

  2. Perronnin, F., Sánchez, J., Mensink, T.: Improving the Fisher Kernel for Large-Scale Image Classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143–156. Springer, Heidelberg (2010)

    CrossRef  Google Scholar 

  3. Yang, J., Yu, K., Huang, T.: Efficient Highly Over-Complete Sparse Coding Using a Mixture Model. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 113–126. Springer, Heidelberg (2010)

    CrossRef  Google Scholar 

  4. Li, F., Carreira, J., Sminchisescu, C.: Object recognition as ranking holistic figure-ground hypotheses. In: CVPR (2010)

    Google Scholar 

  5. Song, Z., Chen, Q., Huang, Z., Hua, Y., Yan, S.: Contextualizing object detection and classification. In: CVPR (2011)

    Google Scholar 

  6. Wright, J., Yang, A., Ganesh, A., Sastry, S., Ma, Y.: Robust face recognition via sparse representation. TPAMI (2008)

    Google Scholar 

  7. Yuan, X., Yan, S.: Visual classification with multi-task joint sparse representation. In: CVPR (2010)

    Google Scholar 

  8. Wright, J., Ma, Y., Mairal, J., Sapiro, G., Huang, T., Yan, S.: Sparse representation for computer vision and pattern recognition. IEEE (2010)

    Google Scholar 

  9. Elhamifar, E., Vidal, R.: Sparse subspace clustering. In: CVPR (2009)

    Google Scholar 

  10. Liu, D., Yan, S., Rui, Y., Zhang, H.: Unified tag analysis with multi-edge graph. In: MM (2010)

    Google Scholar 

  11. Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the em algorithm. J Roy. Stat. Soc. B Met. (1977)

    Google Scholar 

  12. Vidal, R., Ma, Y., Sastry, S.: Generalized principal component analysis (gpca). TPAMI (2005)

    Google Scholar 

  13. Gaffney, S., Smyth, P.: Trajectory clustering with mixtures of regression models. In: KDD (1999)

    Google Scholar 

  14. Quadrianto, N., Caetano, T., Lim, J., Schuurmans, D.: Convex relaxation of mixture regression with efficient algorithms. In: NIPS (2009)

    Google Scholar 

  15. Hocking, T., Vert, J., Bach, F., Joulin, A.: Clusterpath: an algorithm for clustering using convex fusion penalties. In: ICML (2011)

    Google Scholar 

  16. Shen, X., Huang, H.: Grouping pursuit through a regularization solution surface. J Am. Stat. Assoc. (2010)

    Google Scholar 

  17. Vert, J., Bleakley, K.: Fast detection of multiple change-points shared by many signals using group lars. In: NIPS (2010)

    Google Scholar 

  18. Nesterov, Y.: Smooth minimization of non-smooth functions. Math. Program. (2005)

    Google Scholar 

  19. Ng, A., Jordan, M., Weiss, Y.: On spectral clustering: Analysis and an algorithm. In: NIPS (2001)

    Google Scholar 

  20. Boyd, S., Vandenberghe, L.: Convex optimization. Cambridge Univ. Pr. (2004)

    Google Scholar 

  21. Duchi, J., Shalev-Shwartz, S., Singer, Y., Chandra, T.: Efficient projections onto the ℓ1-ball for learning in high dimensions. In: ICML (2008)

    Google Scholar 

  22. Tseng, P.: On accelerated proximal gradient methods for convex-concave optimization. Submitted to SIAM J. Optimiz. (2008)

    Google Scholar 

  23. Subramanya, A., Bilmes, J.: Entropic graph regularization in non-parametric semi-supervised classification. In: NIPS (2009)

    Google Scholar 

  24. Zhu, X., Ghahramani, Z.: Learning from labeled and unlabeled data with label propagation. Tech. Rep. (2002)

    Google Scholar 

  25. Yan, S., Wang, H.: Semi-supervised learning by sparse representation. In: SDM (2009)

    Google Scholar 

  26. Yan, S., Xu, D., Zhang, B., Zhang, H., Yang, Q., Lin, S.: Graph embedding and extensions: A general framework for dimensionality reduction. TPAMI (2007)

    Google Scholar 

  27. Chua, T., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: Nus-wide: a real-world web image database from national university of singapore. In: CIVR (2009)

    Google Scholar 

  28. Chen, X., Yuan, X., Chen, Q., Yan, S., Chua, T.: Multi-label visual classification with label exclusive context. In: ICCV (2011)

    Google Scholar 

  29. Hartley, R., Zisserman, A.: Multiple view geometry in computer vision. Cambridge Univ. Press (2000)

    Google Scholar 

  30. Tron, R., Vidal, R.: A benchmark for the comparison of 3-d motion segmentation algorithms. In: CVPR (2007)

    Google Scholar 

  31. Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM (1981)

    Google Scholar 

  32. Elhamifar, E., Vidal, R.: Sparse subspace clustering. In: CVPR (2009)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of ECE, National University of Singapore, Singapore

    Jiashi Feng & Shuicheng Yan

  2. Department of Statistics, Rutgers University, USA

    Xiaotong Yuan

  3. Department of Automation, University of Science and Technology of China, China

    Zilei Wang

  4. Department of ME, National University of Singapore, Singapore

    Huan Xu

Authors
  1. Jiashi Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaotong Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zilei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Huan Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shuicheng Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Microsoft Research Ltd., CB3 0FB, Cambridge, UK

    Andrew Fitzgibbon

  2. Dept. of Computer Science, University of North Carolina, 27599, Chapel Hill, NC, USA

    Svetlana Lazebnik

  3. California Institute of Technology, 91125, Pasadena, CA, USA

    Pietro Perona

  4. Institute of Industrial Science, The University of Tokyo, 153-8505, Tokyo, Japan

    Yoichi Sato

  5. INRIA, 38330, Montbonnot, France

    Cordelia Schmid

Rights and permissions

Reprints and Permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Feng, J., Yuan, X., Wang, Z., Xu, H., Yan, S. (2012). Auto-Grouped Sparse Representation for Visual Analysis. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7572. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33718-5_46

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-33718-5_46

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-33717-8

  • Online ISBN: 978-3-642-33718-5

  • eBook Packages: Computer ScienceComputer Science (R0)