Sciweavers

307 search results - page 16 / 62
» Discriminative Feature Co-Occurrence Selection for Object De...
Sort
View
ICCCN
2007
IEEE
13 years 6 months ago
Online Selection of Tracking Features using AdaBoost
In this paper, a novel feature selection algorithm for object tracking is proposed. This algorithm performs more robust than the previous works by taking the correlation between f...
Ying-Jia Yeh, Chiou-Ting Hsu
CVPR
2012
IEEE
11 years 9 months ago
Boosting algorithms for simultaneous feature extraction and selection
The problem of simultaneous feature extraction and selection, for classifier design, is considered. A new framework is proposed, based on boosting algorithms that can either 1) s...
Mohammad J. Saberian, Nuno Vasconcelos
ECCV
2008
Springer
14 years 8 months ago
Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images
Abstract. We address the problem of estimating human body pose from a single image with cluttered background. We train multiple local linear regressors for estimating the 3D pose f...
Ryuzo Okada, Stefano Soatto
CVPR
2004
IEEE
14 years 8 months ago
Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection
We consider the problem of detecting a large number of different object classes in cluttered scenes. Traditional approaches require applying a battery of different classifiers to ...
Antonio B. Torralba, Kevin P. Murphy, William T. F...
ICCV
1999
IEEE
13 years 11 months ago
Motion Segmentation based on Factorization Method and Discriminant Criterion
A motion segmentation algorithm based on factorization method and discriminant criterion is proposed. This method uses a feature with the most useful similarities for grouping, se...
Naoyuki Ichimura