Beyond sliding windows: Object localization by efficient subwindow search

@article{Lampert2008BeyondSW,
  title={Beyond sliding windows: Object localization by efficient subwindow search},
  author={Christoph H. Lampert and Matthew B. Blaschko and Thomas Hofmann},
  journal={2008 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2008},
  pages={1-8}
}
Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To perform localization, one can take a sliding window approach, but this strongly increases the computational cost, because the classifier function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branch-and-bound scheme that allows efficient maximization… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 583 CITATIONS

Fall 1-4-2013 Object Detection and Recognition in Natural Settings

VIEW 12 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Addressing Ambiguity In Object Instance Detection

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Human Action Localization And Recognition In Unconstrained Videos

VIEW 22 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Image classification using latent spatial pyramid matching

VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Towards Optimal Naive Bayes Nearest Neighbor

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

What is an object?

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 14 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Fast concurrent object localization and recognition

  • 2009 IEEE Conference on Computer Vision and Pattern Recognition
  • 2009
VIEW 15 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2008
2019

CITATION STATISTICS

  • 95 Highly Influenced Citations

  • Averaged 21 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

Learning with kernels

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Groups of Adjacent Contour Segments for Object Detection

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2008
VIEW 2 EXCERPTS

An Exemplar Model for Learning Object Classes

  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
VIEW 3 EXCERPTS

Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006

Multiclass Object Recognition with Sparse, Localized Features

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006