Sciweavers

148 search results - page 14 / 30
» Scientific visualization - some novel approaches to learning
Sort
View
CVPR
2012
IEEE
13 years 1 months ago
Meta-class features for large-scale object categorization on a budget
In this paper we introduce a novel image descriptor enabling accurate object categorization even with linear models. Akin to the popular attribute descriptors, our feature vector ...
Alessandro Bergamo, Lorenzo Torresani
ICCV
2003
IEEE
16 years 14 days ago
Weighted and Robust Incremental Method for Subspace Learning
Visual learning is expected to be a continuous and robust process, which treats input images and pixels selectively. In this paper we present a method for subspace learning, which...
Danijel Skocaj, Ales Leonardis
NIPS
2001
14 years 12 months ago
Categorization by Learning and Combining Object Parts
We describe an algorithm for automatically learning discriminative components of objects with SVM classifiers. It is based on growing image parts by minimizing theoretical bounds ...
Bernd Heisele, Thomas Serre, Massimiliano Pontil, ...
GBRPR
2007
Springer
15 years 2 months ago
Constellations and the Unsupervised Learning of Graphs
Abstract. In this paper, we propose a novel method for the unsupervised clustering of graphs in the context of the constellation approach to object recognition. Such method is an E...
Boyan Bonev, Francisco Escolano, Miguel Angel Loza...
ICML
2009
IEEE
15 years 11 months ago
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks. Scaling such models to full-sized, high-dimensional images re...
Honglak Lee, Roger Grosse, Rajesh Ranganath, Andre...