6113 search results - page 139 / 1223 » Learning Features for Tracking |
141
Voted
IR
2010
15 years 1 months ago
2010
In this article we present Supervised Semantic Indexing (SSI) which defines a class of nonlinear (quadratic) models that are discriminatively trained to directly map from the word...
121
click to vote
ECCC
2006
15 years 2 months ago
2006
Detecting the relevant attributes of an unknown target concept is an important and well studied problem in algorithmic learning. Simple greedy strategies have been proposed that s...
104
Voted
ICML
2003
IEEE
16 years 3 months ago
2003
IEEE
When the training instances of the target class are heavily outnumbered by non-target training instances, SVMs can be ineffective in determining the class boundary. To remedy this...
118
Voted
ISNN
2007
Springer
15 years 8 months ago
2007
Springer
Manifold learning algorithms have been proven to be capable of discovering some nonlinear structures. However, it is hard for them to extend to test set directly. In this paper, a ...
126
Voted
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
Interest point detectors are the starting point in image analysis for depth estimation using epipolar geometry and camera ego-motion estimation. With several detectors defined in ...