999 search results - page 3 / 200 » Efficient Learning to Label Images |
NIPS
2008
13 years 11 months ago
2008
Extensive labeled data for image annotation systems, which learn to assign class labels to image regions, is difficult to obtain. We explore a hybrid model framework for utilizing...
Publication
One of the principal bottlenecks in applying learning techniques to classification problems is the large amount of labeled training data required. Especially for images and video, ...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...
MICCAI
2005
Springer
14 years 10 months ago
2005
Springer
Abstract. In this paper, we propose a new dynamic learning framework that requires a small amount of labeled data in the beginning, then incrementally discovers informative unlabel...
AAAI
2012
12 years 5 days ago
2012
It is well known that exploiting label correlations is important for multi-label learning. Existing approaches typically exploit label correlations globally, by assuming that the ...