667 search results - page 62 / 134 » Learning to Model Sequences Generated by Switching Distribut... |
166
click to vote
CVPR
2007
IEEE
16 years 5 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...
126
Voted
ICIP
2006
IEEE
16 years 5 months ago
2006
IEEE
We develop a Bayesian model of digitized archival films and use this for denoising, or more specifically de-graining, individual frames. In contrast to previous approaches our mod...
156
Voted
PAMI
2002
15 years 3 months ago
2002
The product of experts learning procedure [1] can discover a set of stochastic binary features that constitute a nonlinear generative model of handwritten images of digits. The qua...
133
click to vote
ICDAR
2009
IEEE
15 years 10 months ago
2009
IEEE
This paper proposes a recognition based approach to handwritten numeral string segmentation. We consider two classes: numeral strings segmented correctly or not. The feature vecto...
132
Voted
CVPR
2007
IEEE
16 years 5 months ago
2007
IEEE
We introduce an exemplar model that can learn and generate a region of interest around class instances in a training set, given only a set of images containing the visual class. T...