Constructing Visual Models with a Latent Space Approach

  • Florent Monay
  • Pedro Quelhas
  • Daniel Gatica-Perez
  • Jean-Marc Odobez
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3940)


We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns of visual co-occurrence and if the learned visual models improve performance when less labeled data are available. We present and discuss results that support these hypotheses. Probabilistic Latent Semantic Analysis (PLSA) automatically identifies aspects from the data with semantic meaning, producing unsupervised soft clustering. The resulting compact representation retains sufficient discriminative information for accurate object classification, and improves the classification accuracy through the use of unlabeled data when less labeled training data are available. We perform experiments on a 7-class object database containing 1776 images.


Support Vector Machine Local Descriptor Visual Model Probabilistic Latent Semantic Analysis Feature Extraction Process 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Baeza-Yates, R., Ribeiro-Neto, B.: Modern Information Retrieval. ACM Press, New York (1999)Google Scholar
  2. 2.
    Blei, D., Andrew, Y., Jordan, M.: Latent dirichlet allocation. Journal of Machine Learning Research 3, 993–1020 (2003)MATHGoogle Scholar
  3. 3.
    Buntine, W.: Variational extensions to em and multinomial pca. In: Proc. of Europ. Conf. on Machine Learning, Helsinki (August 2002)Google Scholar
  4. 4.
    Duygulu, P., Barnard, K., Freitas, N., Forsyth, D.: Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 97–112. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  5. 5.
    Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Machine Learning 42, 177–196 (2001)CrossRefMATHGoogle Scholar
  6. 6.
    Keller, M., Bengio, S.: Theme topic mixture model: A graphical model for document representation. IDIAP Research Report, IDIAP-RR-04-05 (January 2004)Google Scholar
  7. 7.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2003)CrossRefGoogle Scholar
  8. 8.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, Madison (June 2003)Google Scholar
  9. 9.
    Monay, F., Gatica-Perez, D.: On image auto-annotation with latent space models. In: Proc. of ACM Int. Conf. on Multimedia, Berkeley (November 2003)Google Scholar
  10. 10.
    Monay, F., Gatica-Perez, D.: PLSA-based image auto-annotation: Constraining the latent space. In: Proc. ACM Int. Conf. on Multimedia, New York (October 2004)Google Scholar
  11. 11.
    Opelt, A., Fussenegger, M., Pinz, A., Auer, P.: Weak hypotheses and boosting for generic object detection and recognition. In: Proc. of IEEE Europ. Conf. on Computer Vision, Prague (May 2004)Google Scholar
  12. 12.
    Quelhas, P., Monay, F., Odobez, J.-M., Gatica-Perez, D., Tuytelaars, T., Gool, L.V.: Modeling scenes with local descriptors and latent aspects. In: Proc. of IEEE Int. Conf. on Computer Vision, Beijing (October 2005)Google Scholar
  13. 13.
    Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering object categories in image collections. Technical report, Dept. of Engineering Science, University of Oxford (2005)Google Scholar
  14. 14.
    Sivic, J., Zisserman, A.: Video google: A text retrieval approach to object matching in videos. In: Proc. of IEEE Int. Conf. on Computer Vision, Nice (October 2003)Google Scholar
  15. 15.
    Tuytelaars, T., Van Gool, L.: Content-based image retrieval based on local affinely invariant regions. In: Proc. of Visual 1999, Amsterdam (June 1999)Google Scholar
  16. 16.
    Vailaya, A., Figueiredo, M., Jain, A., Zhang, H.J.: Image classification for content-based indexing. IEEE Trans. on Image Processing 10, 117–130 (2001)CrossRefMATHGoogle Scholar
  17. 17.
    Willamowski, J., Arregui, D., Csurka, G., Dance, C.R., Fan, L.: Categorizing nine visual classes using local appearance descriptors. In: Proc. of ICPR Workshop on Learning for Adaptable Visal Systems, Cambridge (August 2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Florent Monay
    • 1
  • Pedro Quelhas
    • 1
  • Daniel Gatica-Perez
    • 1
  • Jean-Marc Odobez
    • 1
  1. 1.IDIAP Research InstituteMartignySwitzerland

Personalised recommendations