2014 search results - page 322 / 403 » A P2P Approach for Global Computing |
202
click to vote
CVPR
2012
IEEE
13 years 8 months ago
2012
IEEE
We present a novel technique for figure-ground segmentation, where the goal is to separate all foreground objects in a test image from the background. We decompose the test image...
209
click to vote
CVPR
2009
IEEE
17 years 1 months ago
2009
IEEE
Non-linear dimensionality reductionmethods are powerful techniques to deal with
high-dimensional datasets. However, they often are susceptible to local minima
and perform poorly ...
149
click to vote
ICCV
2009
IEEE
16 years 11 months ago
2009
IEEE
Supervised learning of a parts-based model can be for-
mulated as an optimization problem with a large (exponen-
tial in the number of parts) set of constraints. We show how
thi...
156
click to vote
CVPR
2003
IEEE
16 years 8 months ago
2003
IEEE
In this paper, we develop a general classification framework called Kullback-Leibler Boosting, or KLBoosting. KLBoosting has following properties. First, classification is based o...
171
click to vote
CVPR
2004
IEEE
16 years 8 months ago
2004
IEEE
In this paper, we introduce a novel discriminative feature space which is efficient not only for face detection but also for recognition. The face representation is based on local...