342 search results - page 23 / 69 » Learning from Ambiguously Labeled Images |
CVPR
2010
IEEE
14 years 4 months ago
2010
IEEE
Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been u...
ICIP
2005
IEEE
14 years 10 months ago
2005
IEEE
In this article, we propose a special type of decision tree, called a decision cascade, for binarizing document images. Such images are produced by cameras, resulting in varying de...
FIMH
2009
Springer
13 years 6 months ago
2009
Springer
Cardiac magnetic resonance (MR) imaging has advanced to become a powerful diagnostic tool in clinical practice. Automatic detection of anatomic landmarks from MR images is importan...
NIPS
1997
13 years 9 months ago
1997
Multiple-instance learning is a variation on supervised learning, where the task is to learn a concept given positive and negative bags of instances. Each bag may contain many ins...
PAMI
2012
11 years 11 months ago
2012
—Web-scale image search engines (e.g. Google Image Search, Bing Image Search) mostly rely on surrounding text features. It is difficult for them to interpret users’ search int...