Sciweavers

780 search results - page 19 / 156
» Learning Mid-Level Features For Recognition
Sort
View
BMVC
2010
13 years 5 months ago
Large-scale Dictionary Learning For Local Coordinate Coding
Local coordinate coding has recently been introduced to learning visual feature dictionary and achieved top level performance for object recognition. However, the computational co...
Bo Xie, Mingli Song, Dacheng Tao
CVPR
2009
IEEE
1390views Computer Vision» more  CVPR 2009»
15 years 2 months ago
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
In this paper we present a method for learning classspecific features for recognition. Recently a greedy layerwise procedure was proposed to initialize weights of deep belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
CVPR
2009
IEEE
15 years 2 months ago
Learning Invariant Features Through Topographic Filter Maps
Several recently-proposed architectures for highperformance object recognition are composed of two main stages: a feature extraction stage that extracts locallyinvariant feature...
Koray Kavukcuoglu, Marc'Aurelio Ranzato, Rob Fergu...
TSMC
2011
292views more  TSMC 2011»
13 years 2 months ago
Circular Blurred Shape Model for Multiclass Symbol Recognition
—In this paper, we propose a circular blurred shape model descriptor to deal with the problem of symbol detection and classification as a particular case of object recognition. ...
Sergio Escalera, Alicia Fornés, Oriol Pujol...
ICML
2000
IEEE
13 years 12 months ago
Mutual Information in Learning Feature Transformations
We present feature transformations useful for exploratory data analysis or for pattern recognition. Transformations are learned from example data sets by maximizing the mutual inf...
Kari Torkkola, William M. Campbell