Hierarchical part-based visual object categorization

@article{Bouchard2005HierarchicalPV,
  title={Hierarchical part-based visual object categorization},
  author={Guillaume Bouchard and Bill Triggs},
  journal={2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)},
  year={2005},
  volume={1},
  pages={710-715 vol. 1}
}
We propose a generative model that codes the geometry and appearance of generic visual object categories as a loose hierarchy of parts, with probabilistic spatial relations linking parts to subparts, soft assignment of subparts to parts, and scale invariant keypoint based local features at the lowest level of the hierarchy. The method is designed to efficiently handle categories containing hundreds of redundant local features, such as those returned by current key-point detectors. This… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 126 CITATIONS, ESTIMATED 23% COVERAGE

Visual object class recognition using local descriptions

VIEW 8 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

3D compositional hierarchies for object categorization

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Object Detection in Real Images

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Geometric primitive feature extraction - concepts, algorithms, and applications

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Probabilistic Framework for 3D Visual Object Representation

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2009
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Hierarchical Model of Shape and Appearance for Human Action Classification

  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
VIEW 1 EXCERPT
CITES METHODS
HIGHLY INFLUENCED

Binary Co-occurrences of Weak Descriptors

VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Hierarchical Object Recognition System Based on Multi-scale Principal Curvature Regions

  • 18th International Conference on Pattern Recognition (ICPR'06)
  • 2006
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Sparse Flexible Models of Local Features

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Constellation Models for Recognition of Generic Objects

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2005
2017

CITATION STATISTICS

  • 10 Highly Influenced Citations

  • Averaged 1 Citations per year over the last 3 years

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…