Sciweavers

2903 search results - page 412 / 581
» The Dark Side of Object Learning: Learning Objects
Sort
View
JMLR
2010
169views more  JMLR 2010»
13 years 5 months ago
Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images
Deep belief nets have been successful in modeling handwritten characters, but it has proved more difficult to apply them to real images. The problem lies in the restricted Boltzma...
Marc'Aurelio Ranzato, Alex Krizhevsky, Geoffrey E....
TSP
2010
13 years 4 months ago
Gaussian multiresolution models: exploiting sparse Markov and covariance structure
We consider the problem of learning Gaussian multiresolution (MR) models in which data are only available at the finest scale and the coarser, hidden variables serve both to captu...
Myung Jin Choi, Venkat Chandrasekaran, Alan S. Wil...
FGR
2011
IEEE
271views Biometrics» more  FGR 2011»
13 years 1 months ago
Active conditional models
— Matching images with large geometric and iconic changes (e.g. faces under different poses and facial expressions) is an open research problem in computer vision. There are two ...
Ying Chen, Fernando De la Torre
CVPR
2012
IEEE
12 years 19 days ago
Robust visual tracking using autoregressive hidden Markov Model
Recent studies on visual tracking have shown significant improvement in accuracy by handling the appearance variations of the target object. Whereas most studies present schemes ...
Dong Woo Park, Junseok Kwon, Kyoung Mu Lee
ICSE
1999
IEEE-ACM
14 years 2 months ago
Exploiting Smalltalk Modules in a Customizable Programming Environment
This paper describes how we have extended a module structure of the Smalltalk LearningWorks to provide a programming environment deigned for very large scale technology transfer. ...
Mark Woodman, Robert Griffiths, Malcolm Macgregor,...