Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P.F. and Girshick, R.B. and McAllester, D. and Ramanan, D.



Support
Academic Torrents!

Disable your
ad-blocker!

Object Detection with Discriminatively Trained Part-Based Models.pdf5.77MB
Type: Paper
Tags: Computer-Assisted;Imaging, Three-Dimensional;Pattern Recognition, Automated;Reproducibility of Results;Sensitivity and Specificity

Bibtex:
@article{5255236,
author= {Felzenszwalb, P.F. and Girshick, R.B. and McAllester, D. and Ramanan, D.},
journal= {Pattern Analysis and Machine Intelligence, IEEE Transactions on},
title= {Object Detection with Discriminatively Trained Part-Based Models},
year= {2010},
volume= {32},
number= {9},
pages= {1627-1645},
abstract= {We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL data sets. Our system relies on new methods for discriminative training with partially labeled data. We combine a margin-sensitive approach for data-mining hard negative examples with a formalism we call latent SVM. A latent SVM is a reformulation of MI--SVM in terms of latent variables. A latent SVM is semiconvex, and the training problem becomes convex once latent information is specified for the positive examples. This leads to an iterative training algorithm that alternates between fixing latent values for positive examples and optimizing the latent SVM objective function.},
keywords= {data mining;iterative methods;object detection;object recognition;support vector machines;PASCAL object detection;data mining;discriminative trained part-based models;iterative training algorithm;latent SVM objective function;margin-sensitive approach;multiscale deformable part models;object detection system;object recognition;support vector machine;Object recognition;deformable models;discriminative training;latent SVM.;pictorial structures;Algorithms;Artificial Intelligence;Discriminant Analysis;Image Enhancement;Image Interpretation, Computer-Assisted;Imaging, Three-Dimensional;Pattern Recognition, Automated;Reproducibility of Results;Sensitivity and Specificity},
doi= {10.1109/TPAMI.2009.167},
issn= {0162-8828},
month= {Sept},
terms= {}
}