Sciweavers

725 search results - page 61 / 145
» Invariances in kernel methods: From samples to objects
Sort
View
ICCV
2009
IEEE
1419views Computer Vision» more  ICCV 2009»
15 years 2 months ago
On Feature Combination for Multiclass Object Classification
A key ingredient in the design of visual object classification systems is the identification of relevant class specific aspects while being robust to intra-class variations. Whil...
Peter Gehler, Sebastian Nowozin
CVPR
2007
IEEE
14 years 11 months ago
Optimizing Distribution-based Matching by Random Subsampling
We boost the efficiency and robustness of distributionbased matching by random subsampling which results in the minimum number of samples required to achieve a specified probabili...
Alex Po Leung, Shaogang Gong
DSSCV
2005
Springer
14 years 2 months ago
From Stochastic Completion Fields to Tensor Voting
Abstract. Several image processing algorithms imitate the lateral interaction of neurons in the visual striate cortex V1 to account for the correlations along contours and lines. H...
Markus van Almsick, Remco Duits, Erik Franken, Bar...
ICDM
2006
IEEE
119views Data Mining» more  ICDM 2006»
14 years 3 months ago
Fast On-line Kernel Learning for Trees
Kernel methods have been shown to be very effective for applications requiring the modeling of structured objects. However kernels for structures usually are too computational dem...
Fabio Aiolli, Giovanni Da San Martino, Alessandro ...
VIS
2008
IEEE
176views Visualization» more  VIS 2008»
14 years 10 months ago
Particle-based Sampling and Meshing of Surfaces in Multimaterial Volumes
Abstract-- Methods that faithfully and robustly capture the geometry of complex material interfaces in labeled volume data are important for generating realistic and accurate visua...
Miriah Meyer, Ross Whitaker, Robert M. Kirby, C...