Located Hidden Random Fields: Learning Discriminative Parts for Object Detection

  • Ashish Kapoor
  • John Winn
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3953)


This paper introduces the Located Hidden Random Field (LHRF), a conditional model for simultaneous part-based detection and segmentation of objects of a given class. Given a training set of images with segmentation masks for the object of interest, the LHRF automatically learns a set of parts that are both discriminative in terms of appearance and informative about the location of the object. By introducing the global position of the object as a latent variable, the LHRF models the long-range spatial configuration of these parts, as well as their local interactions. Experiments on benchmark datasets show that the use of discriminative parts leads to state-of-the-art detection and segmentation performance, with the additional benefit of obtaining a labeling of the object’s component parts.


Object Detection Object Class Conditional Random Field Discriminative Model Segmentation Accuracy 
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.


  1. 1.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: International Conference on Machine Learning (2001)Google Scholar
  2. 2.
    Crandall, D., Felzenszwalb, P., Huttenlocher, D.: Spatial priors for part-based recognition using statistical models. In: CVPR (2005)Google Scholar
  3. 3.
    Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: European Conference on Computer Vision (2002)Google Scholar
  4. 4.
    Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: Workshop on Statistical Learning in Computer Vision (2004)Google Scholar
  5. 5.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Computer Vision and Pattern Recognition (2003)Google Scholar
  6. 6.
    Fergus, R., Perona, P., Zisserman, A.: A sparse object category model for efficient learning and exhaustive recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego (2005)Google Scholar
  7. 7.
    Winn, J., Jojic, N.: LOCUS: Learning Object Classes with Unsupervised Segmentation. In: International Conference on Computer Vision (2005)Google Scholar
  8. 8.
    Borenstein, E., Sharon, E., Ullman, S.: Combining top-down and bottom-up segmentation. In: Proceedings IEEE workshop on Perceptual Organization in Computer Vision, CVPR 2004 (2004)Google Scholar
  9. 9.
    Shotton, J., Blake, A., Cipolla, R.: Contour-based learning for object detection. In: International Conference on Computer Vision (2005)Google Scholar
  10. 10.
    Kumar, S., Hebert, M.: Discriminative random fields: A discriminative framework for contextual interaction in classification. In: ICCV (2003)Google Scholar
  11. 11.
    Quattoni, A., Collins, M., Darrell, T.: Conditional random fields for object recognition. In: Neural Information Processing Systems (2004)Google Scholar
  12. 12.
    Kumar, M.P., Torr, P.H.S., Zisserman, A.: OBJ CUT. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego (2005)Google Scholar
  13. 13.
    Szummer, M.: Learning diagram parts with hidden random fields. In: International Conference on Document Analysis and Recognition (2005)Google Scholar
  14. 14.
    Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. In: Workshop on Artificial Intelligence and Statistics (2005)Google Scholar
  15. 15.
    Felzenszwalb, P., Huttenlocher, D.: Efficient belief propagation for early vision. In: Computer Vision and Pattern Recognition (2004)Google Scholar
  16. 16.
    Lowe, D.: Object recognition from local scale-invariant features. In: InternationalConference on Computer Vision (1999)Google Scholar
  17. 17.
    Garg, A., Agarwal, S., Huang., T.S.: Fusion of global and local information for object detection. In: International Conference on Pattern Recognition (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ashish Kapoor
    • 1
  • John Winn
    • 2
  1. 1.MIT Media LaboratoryCambridgeUSA
  2. 2.Microsoft ResearchCambridgeUK

Personalised recommendations