Sciweavers

342 search results - page 64 / 69
» Learning from Ambiguously Labeled Images
Sort
View
CVPR
2007
IEEE
14 years 10 months ago
Joint Optimization of Cascaded Classifiers for Computer Aided Detection
The existing methods for offline training of cascade classifiers take a greedy search to optimize individual classifiers in the cascade, leading inefficient overall performance. W...
Murat Dundar, Jinbo Bi
PAKDD
2005
ACM
128views Data Mining» more  PAKDD 2005»
14 years 1 months ago
A Framework for Incorporating Class Priors into Discriminative Classification
Abstract. Discriminative and generative methods provide two distinct approaches to machine learning classification. One advantage of generative approaches is that they naturally mo...
Rong Jin, Yi Liu
ICIP
2003
IEEE
14 years 10 months ago
Feature selection for unsupervised discovery of statistical temporal structures in video
We present algorithms for automatic feature selection for unsupervised structure discovery from video sequences. Feature selection in this scenario is hard because of the absence ...
Lexing Xie, Shih-Fu Chang, Ajay Divakaran, Huifang...
IJCV
2008
151views more  IJCV 2008»
13 years 8 months ago
Describing Visual Scenes Using Transformed Objects and Parts
We develop hierarchical, probabilistic models for objects, the parts composing them, and the visual scenes surrounding them. Our approach couples topic models originally developed...
Erik B. Sudderth, Antonio Torralba, William T. Fre...
ICCV
2003
IEEE
14 years 10 months ago
Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification
In this work we present Discriminative Random Fields (DRFs), a discriminative framework for the classification of image regions by incorporating neighborhood interactions in the l...
Sanjiv Kumar, Martial Hebert