779 search results - page 68 / 156 » Information-theoretic Competitive Learning |
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
The compositional nature of visual objects significantly limits their representation complexity and renders learning of structured object models tractable. Adopting this modeling ...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
ICCV
2005
IEEE
14 years 11 months ago
2005
IEEE
We have developed a two-phase generative / discriminative learning procedure for the recognition of classes of objects and concepts in outdoor scenes. Our method uses both multipl...
ECCV
2006
Springer
14 years 10 months ago
2006
Springer
Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstra...
ICML
2009
IEEE
14 years 9 months ago
2009
IEEE
Semi-Supervised Support Vector Machines (S3VMs) typically directly estimate the label assignments for the unlabeled instances. This is often inefficient even with recent advances ...