1136 search results - page 183 / 228 » Finding Small Holes |
CVPR
2008
IEEE
14 years 10 months ago
2008
IEEE
The selection of weak classifiers is critical to the success of boosting techniques. Poor weak classifiers do not perform better than random guess, thus cannot help decrease the t...
CVPR
2008
IEEE
14 years 10 months ago
2008
IEEE
To learn a new visual category from few examples, prior knowledge from unlabeled data as well as previous related categories may be useful. We develop a new method for transfer le...
ECCV
2002
Springer
14 years 10 months ago
2002
Springer
Abstract. Brightness values of pixels in an image are related to image irradiance by a non-linear function, called the radiometric response function. Recovery of this function is i...
ICIP
2007
IEEE
14 years 10 months ago
2007
IEEE
The problem of tracking involves challenges like in-plane and out-of-plane rotations, scaling, variations in ambient light and occlusions. In this paper we look at the problem of ...
ICIP
2003
IEEE
14 years 10 months ago
2003
IEEE
For effective retrieval of visual information, statistical learning plays a pivotal role. Statistical learning in such a context faces at least two major mathematical challenges: ...