A Bayesian hierarchical model for learning natural scene categories

@article{FeiFei2005ABH,
  title={A Bayesian hierarchical model for learning natural scene categories},
  author={Li Fei-Fei and Pietro Perona},
  journal={2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)},
  year={2005},
  volume={2},
  pages={524-531 vol. 2}
}
We propose a novel approach to learn and recognize natural scene categories. Unlike previous work, it does not require experts to annotate the training set. We represent the image of a scene by a collection of local regions, denoted as codewords obtained by unsupervised learning. Each region is represented as part of a "theme". In previous work, such themes were learnt from hand-annotations of experts, while our method learns the theme distributions as well as the codewords distribution over… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 2,645 CITATIONS

Automatic volume classification in intravascular optical coherence tomography images

  • 2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP)
  • 2017
VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Indoor localization via multi-view images and videos

  • Computer Vision and Image Understanding
  • 2017
VIEW 22 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

B-HMAX: A fast binary biologically inspired model for object recognition

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Scene classification based on single-layer SAE and SVM

  • Expert Syst. Appl.
  • 2015
VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Scene classification using class-supervised local-space-constraint latent Dirichlet allocation

  • Multimedia Tools and Applications
  • 2015
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A FWCL-based method for visual vocabulary formation

  • Multimedia Tools and Applications
  • 2014
VIEW 14 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2004
2019

CITATION STATISTICS

  • 313 Highly Influenced Citations

  • Averaged 123 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 18 REFERENCES

Latent Dirichlet Allocation

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

  • International Journal of Computer Vision
  • 2001
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Object recognition from local scale-invariant features

  • Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Texture classification: are filter banks necessary?

  • 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Sharing features: efficient boosting procedures for multiclass object detection

  • Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
  • 2004
VIEW 2 EXCERPTS

Rapid natural scene categorization in the near absence of attention.

  • Proceedings of the National Academy of Sciences of the United States of America
  • 2002
VIEW 1 EXCERPT