61 search results - page 8 / 13 » Subset Selection for Active Object Recognition |
102
click to vote
Publication
One of the principal bottlenecks in applying learning techniques to classification problems is the large amount of labeled training data required. Especially for images and video, ...
CLOR
2006
15 years 1 months ago
2006
We present a component-based system for object detection and identification. From a set of training images of a given object we extract a large number of components which are clust...
GECCO
2009
Springer
15 years 2 months ago
2009
Springer
We present a novel stereo vision modeling framework that generates approximate, yet physically-plausible representations of objects rather than creating accurate models that are c...
110
click to vote
TIP
2010
14 years 8 months ago
2010
—In increasingly many cases of interest in computer vision and pattern recognition, one is often confronted with the situation where data size is very large. Usually, the labels ...
IBPRIA
2005
Springer
15 years 3 months ago
2005
Springer
A natural way to deal with training samples in imbalanced class problems is to prune them removing redundant patterns, easy to classify and probably over represented, and label noi...