342 search results - page 19 / 69 » Learning from Ambiguously Labeled Images |
CVPR
2007
IEEE
14 years 10 months ago
2007
IEEE
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...
ICVGIP
2004
13 years 9 months ago
2004
We propose a new unsupervised learning method to obtain a layered pictorial structure (LPS) representation of an articulated object from video sequences. It will be seen that this...
ICTAI
2008
IEEE
14 years 2 months ago
2008
IEEE
We consider a variation of the problem of combining expert opinions for the situation in which there is no ground truth to use for training. Even though we don’t have labeled da...
ICCV
2007
IEEE
14 years 10 months ago
2007
IEEE
In the task of visual object categorization, semantic context can play the very important role of reducing ambiguity in objects' visual appearance. In this work we propose to...
ICMCS
2006
IEEE
14 years 2 months ago
2006
IEEE
People identification is an essential task for video content analysis in a surveillance system. A good classifier, however, requires a large amount of training data, which may not...