387 search results - page 13 / 78 » Generative versus Discriminative Methods for Object Recognit... |
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
In patch-based object recognition, there are two important issues on the codebook generation: (1) resolution: a coarse codebook lacks sufficient discriminative power, and an over-...
122
Voted
ICPR
2008
IEEE
15 years 6 months ago
2008
IEEE
This paper introduces an edge-based object recognition method that is robust with respect to clutter, occlusion and object deformations. The method combines the use of local featu...
111
Voted
ICML
2006
IEEE
16 years 1 months ago
2006
IEEE
Clustering is one of the most widely used statistical tools for data analysis. Among all existing clustering techniques, k-means is a very popular method because of its ease of pr...
102
Voted
ICCV
2009
IEEE
16 years 5 months ago
2009
IEEE
Visual categorization problems, such as object classification or action recognition,
are increasingly often approached using a detection strategy: a classifier function
is first ...
114
click to vote
ICML
2010
IEEE
15 years 1 months ago
2010
IEEE
We develop a semi-supervised learning method that constrains the posterior distribution of latent variables under a generative model to satisfy a rich set of feature expectation c...