145 search results - page 5 / 29 » Selective Sampling Based on the Variation in Label Assignmen... |
WWW
2009
ACM
14 years 2 months ago
2009
ACM
We propose a novel cost-efficient approach to threshold selection for binary web-page classification problems with imbalanced class distributions. In many binary-classification ta...
PAMI
2006
13 years 7 months ago
2006
Multiple-instance problems arise from the situations where training class labels are attached to sets of samples (named bags), instead of individual samples within each bag (called...
MM
2009
ACM
14 years 2 months ago
2009
ACM
In this work, we investigate how to automatically reassign the manually annotated labels at the image-level to those contextually derived semantic regions. First, we propose a bi-...
FCSC
2007
13 years 7 months ago
2007
1 The techniques for image analysis and classi cation generally consider the image sample labels xed and without uncertainties. The rank regression problem is studied in this pape...
ISDA
2009
IEEE
14 years 2 months ago
2009
IEEE
— In this contribution a feature selection method in semi-supervised problems is proposed. This method selects variables using a feature clustering strategy, using a combination ...