Learning hierarchical models of scenes, objects, and parts

@article{Sudderth2005LearningHM,
  title={Learning hierarchical models of scenes, objects, and parts},
  author={Erik B. Sudderth and Antonio Torralba and William T. Freeman and Alan S. Willsky},
  journal={Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1},
  year={2005},
  volume={2},
  pages={1331-1338 Vol. 2}
}
We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the expected appearance and position, in an object centered coordinate frame, of features detected by a low-level interest operator. Each object category then has its own distribution over these parts, which are shared between objects. We learn the parameters of this model via a Gibbs sampler which uses the graphical model… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 278 CITATIONS, ESTIMATED 27% COVERAGE

Transfer Learning Decision Forests for Gesture Recognition

VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Animals on the Web

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Street Scenes: towards scene understanding in still images

VIEW 5 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

3D compositional hierarchies for object categorization

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Identifying multiple objects from their appearance in inaccurate detections

  • Computer Vision and Image Understanding
  • 2015
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

NEIL: Extracting Visual Knowledge from Web Data

  • 2013 IEEE International Conference on Computer Vision
  • 2013
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2005
2019

CITATION STATISTICS

  • 25 Highly Influenced Citations

  • Averaged 8 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 22 REFERENCES

A Bayesian hierarchical model for learning natural scene categories

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 2 EXCERPTS

A view of the EM algorithm that justifies incremental , sparse , and other variants

G. E. Hinton.
  • IJCV
  • 2004

Finding scientific topics.

  • Proceedings of the National Academy of Sciences of the United States of America
  • 2004
VIEW 3 EXCERPTS

Graphical models

M. I. Jordan
  • Stat. Sci. , 19(1):140–155
  • 2004
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…