Sciweavers

107 search results - page 21 / 22
» Robust feature extraction via information theoretic learning
Sort
View
DIS
2007
Springer
15 years 3 months ago
A Hilbert Space Embedding for Distributions
We describe a technique for comparing distributions without the need for density estimation as an intermediate step. Our approach relies on mapping the distributions into a reprodu...
Alexander J. Smola, Arthur Gretton, Le Song, Bernh...
135
Voted
IJCV
2006
299views more  IJCV 2006»
14 years 9 months ago
Graph Cuts and Efficient N-D Image Segmentation
Combinatorial graph cut algorithms have been successfully applied to a wide range of problems in vision and graphics. This paper focusses on possibly the simplest application of gr...
Yuri Boykov, Gareth Funka-Lea
AAAI
2008
14 years 12 months ago
Unstructured Audio Classification for Environment Recognition
My thesis aims to contribute towards building autonomous agents that are able to understand their surrounding environment through the use of both audio and visual information. To ...
Selina Chu
ICCV
1999
IEEE
15 years 11 months ago
Fluid Motion Recovery by Coupling Dense and Parametric Vector Fields
In this paper we address the problem of estimating and analyzing the motion in image sequences that involve fluid phenomena. In this context standard motion estimation techniques ...
Étienne Mémin, Patrick Pérez
ICIP
2009
IEEE
14 years 7 months ago
Selecting representative and distinctive descriptors for efficient landmark recognition
To have a robust and informative image content representation for image categorization, we often need to extract as many as possible visual features at various locations, scales a...
Sheng Gao, Joo-Hwee Lim