This paper describes a discriminatively trained, multi-scale, deformable part model for object detection. Our sys- tem achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge. It also outperforms the best results in the 2007 challenge in ten out of twenty categories. The system relies heavily on deformable parts. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL challenge. Our system also relies heavily on new methods for discriminative training. We combine a margin-sensitive approach for data mining hard negative examples with a formalism we call latent SVM. A latent SVM, like a hidden CRF, leads to a non-convex training problem. However, a latent SVM is semi-convex and the training problem becomes convex once latent information is specified for the positive examples. We believe that our training methods will eventually make possible the effective use of more latent information such as hierarchical (grammar) models and models involving latent three dimensional pose.
Описание
This paper is a model based approach in which the Dalal-Triggs HOG detector is used as the feature base. They have a whole and part representation. The classification is done using latent svm. Currently one of the best methods for object detection.
%0 Journal Article
%1 citeulike:2873027
%A Felzenszwalb, P.
%A Mcallester, D.
%A Ramanan, D.
%D 2008
%J Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on
%K object detection
%T A Discriminatively Trained, Multiscale, Deformable Part Model
%U http://www.ics.uci.edu/~dramanan/papers/latent.pdf
%X This paper describes a discriminatively trained, multi-scale, deformable part model for object detection. Our sys- tem achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge. It also outperforms the best results in the 2007 challenge in ten out of twenty categories. The system relies heavily on deformable parts. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL challenge. Our system also relies heavily on new methods for discriminative training. We combine a margin-sensitive approach for data mining hard negative examples with a formalism we call latent SVM. A latent SVM, like a hidden CRF, leads to a non-convex training problem. However, a latent SVM is semi-convex and the training problem becomes convex once latent information is specified for the positive examples. We believe that our training methods will eventually make possible the effective use of more latent information such as hierarchical (grammar) models and models involving latent three dimensional pose.
@article{citeulike:2873027,
abstract = {This paper describes a discriminatively trained, multi-scale, deformable part model for object detection. Our sys- tem achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge. It also outperforms the best results in the 2007 challenge in ten out of twenty categories. The system relies heavily on deformable parts. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL challenge. Our system also relies heavily on new methods for discriminative training. We combine a margin-sensitive approach for data mining hard negative examples with a formalism we call latent SVM. A latent SVM, like a hidden CRF, leads to a non-convex training problem. However, a latent SVM is semi-convex and the training problem becomes convex once latent information is specified for the positive examples. We believe that our training methods will eventually make possible the effective use of more latent information such as hierarchical (grammar) models and models involving latent three dimensional pose.},
added-at = {2009-08-24T22:45:15.000+0200},
author = {Felzenszwalb, P. and Mcallester, D. and Ramanan, D.},
biburl = {https://www.bibsonomy.org/bibtex/2a919734416302fcdb4a5280307793c1b/sitrke},
citeulike-article-id = {2873027},
citeulike-linkout-0 = {http://www.ics.uci.edu/~dramanan/papers/latent.pdf},
description = {This paper is a model based approach in which the Dalal-Triggs HOG detector is used as the feature base. They have a whole and part representation. The classification is done using latent svm. Currently one of the best methods for object detection.},
file = {:paperpool\\deformpart.pdf:PDF},
interhash = {291352229372eb2a43c7f43ef2034619},
intrahash = {a919734416302fcdb4a5280307793c1b},
journal = {Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on},
keywords = {object detection},
month = {June},
posted-at = {2008-06-08 00:42:17},
priority = {0},
timestamp = {2009-08-24T22:45:16.000+0200},
title = {A Discriminatively Trained, Multiscale, Deformable Part Model},
url = {http://www.ics.uci.edu/~dramanan/papers/latent.pdf},
year = 2008
}