10054 search results - page 503 / 2011 » On the Complexity of Function Learning |
180
click to vote
CVPR
2008
IEEE
16 years 8 months ago
2008
IEEE
We present a random field based model for stereo vision with explicit occlusion labeling in a probabilistic framework. The model employs non-parametric cost functions that can be ...
165
Voted
CVPR
2008
IEEE
16 years 8 months ago
2008
IEEE
We pose the recognition problem as data association. In this setting, a novel object is explained solely in terms of a small set of exemplar objects to which it is visually simila...
177
Voted
PKDD
2009
Springer
16 years 1 months ago
2009
Springer
A serious drawback of kernel methods, and Support Vector Machines (SVM) in particular, is the difficulty in choosing a suitable kernel function for a given dataset. One of the appr...
188
click to vote
CVPR
2008
IEEE
16 years 1 months ago
2008
IEEE
While low-dimensional image representations have been very popular in computer vision, they suffer from two limitations: (i) they require collecting a large and varied training se...
193
Voted
IDA
2005
Springer
16 years 7 days ago
2005
Springer
We consider the problem of learning a ranking function, that is a mapping from instances to rankings over a finite number of labels. Our learning method, referred to as ranking by...