518 search results - page 10 / 104 » Object correspondence as a machine learning problem |
124
click to vote
ICCV
2007
IEEE
15 years 6 months ago
2007
IEEE
This paper treats tracking as a foreground/background classification problem and proposes an online semisupervised learning framework. Initialized with a small number of labeled ...
ML
2007
ACM
14 years 11 months ago
2007
ACM
In many learning problems prior knowledge about pattern variations can be formalized and beneficially incorporated into the analysis system. The corresponding notion of invarianc...
71
Voted
ICML
2003
IEEE
16 years 16 days ago
2003
IEEE
In many real world applications, active selection of training examples can significantly reduce the number of labelled training examples to learn a classification function. Differ...
69
Voted
AAAI
1996
15 years 1 months ago
1996
As more information becomes available electronically, tools for finding information of interest to users becomes increasingly important. The goal of the research described here is...
123
click to vote
CVPR
2011
IEEE
14 years 7 months ago
2011
IEEE
Nearly every structured prediction problem in computer vision requires approximate inference due to large and complex dependencies among output labels. While graphical models prov...