780 search results - page 79 / 156 » Learning Mid-Level Features For Recognition |
CORR
2008
Springer
13 years 9 months ago
2008
Springer
We investigate a biologically motivated approach to fast visual classification, directly inspired by the recent work [13]. Specifically, trading-off biological accuracy for comput...
AAAI
2008
13 years 11 months ago
2008
An important feature of many problem domains in machine learning is their geometry. For example, adjacency relationships, symmetries, and Cartesian coordinates are essential to an...
CVPR
2005
IEEE
14 years 2 months ago
2005
IEEE
Here we explore a discriminative learning method on underlying generative models for the purpose of discriminating between object categories. Visual recognition algorithms learn m...
ICML
2008
IEEE
14 years 9 months ago
2008
IEEE
In real-world machine learning problems, it is very common that part of the input feature vector is incomplete: either not available, missing, or corrupted. In this paper, we pres...
IJCAI
2007
13 years 10 months ago
2007
A key challenge in applying kernel-based methods for discriminative learning is to identify a suitable kernel given a problem domain. Many methods instead transform the input data...