Sciweavers

1765 search results - page 7 / 353
» Combinations of Weak Classifiers
Sort
View
ESWA
2008
102views more  ESWA 2008»
13 years 8 months ago
Hierarchical classifier with overlapping class groups
In this paper a novel complex classifier architecture is proposed. The architecture has a hierarchical tree-like structure with simple artificial neural networks (ANNs) at each no...
Igor T. Podolak
PAMI
2008
208views more  PAMI 2008»
13 years 8 months ago
BoostMap: An Embedding Method for Efficient Nearest Neighbor Retrieval
This paper describes BoostMap, a method for efficient nearest neighbor retrieval under computationally expensive distance measures. Database and query objects are embedded into a v...
Vassilis Athitsos, Jonathan Alon, Stan Sclaroff, G...
ICASSP
2011
IEEE
13 years 9 days ago
Combining generic and class-specific codebooks for object categorization and detection
Combining advantages of shape and appearance features, we propose a novel model that integrates these two complementary features into a common framework for object categorization ...
Hong Pan, Yaping Zhu, Liang-Zheng Xia, Truong Q. N...
CVPR
2008
IEEE
14 years 10 months ago
Boosting adaptive linear weak classifiers for online learning and tracking
Online boosting methods have recently been used successfully for tracking, background subtraction etc. Conventional online boosting algorithms emphasize on interchanging new weak ...
Toufiq Parag, Fatih Porikli, Ahmed M. Elgammal
DAGM
2008
Springer
13 years 10 months ago
Efficient Tracking as Linear Program on Weak Binary Classifiers
This paper demonstrates how a simple, yet effective, set of features enables to integrate ensemble classifiers in optical flow based tracking. In particular, gray value differences...
Michael Grabner, Christopher Zach, Horst Bischof