712 search results - page 18 / 143 » Pruning Training Sets for Learning of Object Categories |
ECCV
2008
Springer
14 years 11 months ago
2008
Springer
Abstract. Building visual recognition models that adapt across different domains is a challenging task for computer vision. While feature-learning machines in the form of hierarchi...
ICCV
2007
IEEE
14 years 11 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...
GECCO
2008
Springer
13 years 10 months ago
2008
Springer
Selective sampling is a form of active learning which can reduce the cost of training by only drawing informative data points into the training set. This selected training set is ...
KDD
2005
ACM
14 years 2 months ago
2005
ACM
This paper describes a successful but challenging application of data mining in the railway industry. The objective is to optimize maintenance and operation of trains through prog...
GECCO
2009
Springer
14 years 1 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...