Sciweavers

180 search results - page 13 / 36
» Optical Flow Estimation Using Learned Sparse Model
Sort
View
CVPR
2004
IEEE
16 years 1 months ago
Motion-Based Background Subtraction Using Adaptive Kernel Density Estimation
Background modeling is an important component of many vision systems. Existing work in the area has mostly addressed scenes that consist of static or quasi-static structures. When...
Anurag Mittal, Nikos Paragios
92
Voted
CVIU
2007
121views more  CVIU 2007»
14 years 11 months ago
Background estimation under rapid gain change in thermal imagery
We consider detection of moving ground vehicles in airborne sequences recorded by a thermal sensor with automatic gain control, using an approach that integrates dense optic flow...
Hulya Yalcin, Robert T. Collins, Martial Hebert
ICASSP
2011
IEEE
14 years 3 months ago
Denoising of image patches via sparse representations with learned statistical dependencies
We address the problem of denoising for image patches. The approach taken is based on Bayesian modeling of sparse representations, which takes into account dependencies between th...
Tomer Faktor, Yonina C. Eldar, Michael Elad
108
Voted
DAGM
2008
Springer
15 years 1 months ago
An Unbiased Second-Order Prior for High-Accuracy Motion Estimation
Abstract. Virtually all variational methods for motion estimation regularize the gradient of the flow field, which introduces a bias towards piecewise constant motions in weakly te...
Werner Trobin, Thomas Pock, Daniel Cremers, Horst ...
KDD
2008
ACM
259views Data Mining» more  KDD 2008»
16 years 1 days ago
Using ghost edges for classification in sparsely labeled networks
We address the problem of classification in partially labeled networks (a.k.a. within-network classification) where observed class labels are sparse. Techniques for statistical re...
Brian Gallagher, Hanghang Tong, Tina Eliassi-Rad, ...