CVPR
2007
IEEE
13 years 11 months ago
2007
IEEE
Within the field of pattern classification, the Fisher kernel is a powerful framework which combines the strengths of generative and discriminative approaches. The idea is to ch...
CVPR
2007
IEEE
13 years 11 months ago
2007
IEEE
Generative model learning is one of the key problems in machine learning and computer vision. Currently the use of generative models is limited due to the difficulty in effective...
ICDAR
2009
IEEE
13 years 11 months ago
2009
IEEE
The Fisher kernel is a generic framework which combines the benefits of generative and discriminative approaches to pattern classification. In this contribution, we propose to a...
CVPR
2010
IEEE
14 years 18 days ago
2010
IEEE
Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformation field that warps a disto...
ICPR
2004
IEEE
14 years 5 months ago
2004
IEEE
For the tasks of classification, two types of patterns can generate problems: ambiguous patterns and outliers. Furthermore, it is possible to separate classification algorithms in...
ICPR
2006
IEEE
14 years 5 months ago
2006
IEEE
It is possible to broadly characterize two approaches to probabilistic modeling in terms of generative and discriminative methods. Provided with sufficient training data the discr...
ICPR
2008
IEEE
14 years 5 months ago
2008
IEEE
We present a new technique that employs support vector machines and Gaussian mixture densities to create a generative/discriminative joint classifier. In the past, several approac...
ICCV
2005
IEEE
14 years 6 months ago
2005
IEEE
Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and classification have, in...
ICCV
2005
IEEE
14 years 6 months ago
2005
IEEE
We present an efficient method for learning part-based object class models from unsegmented images represented as sets of salient features. A model includes parts' appearance...
CVPR
2008
IEEE
14 years 6 months ago
2008
IEEE
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...