Max-margin additive classifiers for detection

  title={Max-margin additive classifiers for detection},
  author={Subhransu Maji and Alexander C. Berg},
  journal={2009 IEEE 12th International Conference on Computer Vision},
We present methods for training high quality object detectors very quickly. The core contribution is a pair of fast training algorithms for piece-wise linear classifiers, which can approximate arbitrary additive models. The classifiers are trained in a max-margin framework and significantly outperform linear classifiers on a variety of vision datasets. We report experimental results quantifying training time and accuracy on image classification tasks and pedestrian detection, including… CONTINUE READING
Highly Influential
This paper has highly influenced 27 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 207 citations. REVIEW CITATIONS
121 Citations
39 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 121 extracted citations

208 Citations

Citations per Year
Semantic Scholar estimates that this publication has 208 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 39 references

An experimental study on pedestrian classification

  • A. Berg S. Maji, J. Malik
  • PAMI, 28(11):1863–1868,
  • 2008

Similar Papers

Loading similar papers…