344 search results - page 39 / 69 » cvpr 2009 |
104
click to vote
CVPR
2009
IEEE
16 years 5 months ago
2009
IEEE
We consider regions of images that exhibit smooth statistics, and pose the question of characterizing
the “essence” of these regions that matters for visual recognition. Ideal...
127
Voted
CVPR
2009
IEEE
16 years 5 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 ...
124
Voted
CVPR
2009
IEEE
16 years 5 months ago
2009
IEEE
Feature selection plays a fundamental role in many pattern
recognition problems. However, most efforts have been
focused on the supervised scenario, while unsupervised feature
s...
97
Voted
CVPR
2009
IEEE
16 years 5 months ago
2009
IEEE
Many problems in computer vision can be modeled using
conditional Markov random fields (CRF). Since finding
the maximum a posteriori (MAP) solution in such models
is NP-hard, mu...
CVPR
2009
IEEE
16 years 5 months ago
2009
IEEE
Multiple-instance Learning (MIL) is a new paradigm
of supervised learning that deals with the classification of
bags. Each bag is presented as a collection of instances
from whi...