37 search results - page 6 / 8 » Multiresolution Deep Belief Networks |
ICPR
2010
IEEE
13 years 11 months ago
2010
IEEE
This work introduces a new pattern recognition model for segmenting and tracking lip contours in video sequences. We formulate the problem as a general nonrigid object tracking me...
CVPR
2011
IEEE
13 years 3 months ago
2011
IEEE
The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered features, and then to...
ICML
2009
IEEE
14 years 8 months ago
2009
IEEE
The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free paramete...
JMLR
2012
11 years 10 months ago
2012
While determining model complexity is an important problem in machine learning, many feature learning algorithms rely on cross-validation to choose an optimal number of features, ...
IJCAI
2001
13 years 9 months ago
2001
Deductive, mode-estimation has become an essential component of robotic space systems, like NASA's deep space probes. Future robots will serve as components of large robotic ...