80 search results - page 3 / 16 » Learning the Kernel Combination for Object Categorization |
MCS
2010
Springer
14 years 18 days ago
2010
Springer
Abstract. In this paper we present a novel approach to combining multiple kernels where the kernels are computed from different information channels. In contrast to traditional me...
ICCV
2007
IEEE
14 years 7 months ago
2007
IEEE
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
ICCV
2005
IEEE
14 years 7 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...
ECCV
2006
Springer
14 years 7 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...
CVPR
2010
IEEE
13 years 3 months ago
2010
IEEE
We address the problem of computing joint sparse representation of visual signal across multiple kernel-based representations. Such a problem arises naturally in supervised visual...