2884 search results - page 176 / 577 » Evaluating learning algorithms and classifiers |
153
click to vote
ICIP
2007
IEEE
16 years 6 months ago
2007
IEEE
Abstract - The proposed algorithm in this work provides superresolution for color images by using a learning based technique that utilizes both generative and discriminant approach...
152
click to vote
NIPS
2008
15 years 5 months ago
2008
Policy gradient (PG) reinforcement learning algorithms have strong (local) convergence guarantees, but their learning performance is typically limited by a large variance in the e...
157
click to vote
ENC
2004
IEEE
15 years 8 months ago
2004
IEEE
A method to induce bayesian networks from data to overcome some limitations of other learning algorithms is proposed. One of the main features of this method is a metric to evalua...
122
click to vote
ICCV
2009
IEEE
16 years 9 months ago
2009
IEEE
Our objective is to obtain a state-of-the art object category
detector by employing a state-of-the-art image classifier
to search for the object in all possible image subwindows....
158
click to vote
CVPR
2009
IEEE
16 years 11 months ago
2009
IEEE
Edge-based color constancy makes use of image derivatives
to estimate the illuminant. However, different edge
types exist in real-world images such as shadow, geometry,
material...