Sciweavers

132 search results - page 1 / 27
» Tunable Kernels for Tracking
Sort
View
CVPR
2006
IEEE
14 years 7 months ago
Tunable Kernels for Tracking
We present a tunable representation for tracking that simultaneously encodes appearance and geometry in a manner that enables the use of mean-shift iterations for tracking. The cl...
Vasu Parameswaran, Visvanathan Ramesh, Imad Zoghla...
TSMC
2010
12 years 11 months ago
Probability Density Estimation With Tunable Kernels Using Orthogonal Forward Regression
A generalized or tunable-kernel model is proposed for probability density function estimation based on an orthogonal forward regression procedure. Each stage of the density estimat...
Sheng Chen, Xia Hong, Chris J. Harris
CVPR
2006
IEEE
14 years 7 months ago
Efficient Optimal Kernel Placement for Reliable Visual Tracking
This paper describes a novel approach to optimal kernel placement in kernel-based tracking. If kernels are placed at arbitrary places, kernel-based methods are likely to be trappe...
Zhimin Fan, Ming Yang, Ying Wu, Gang Hua, Ting Yu
MVA
2011
326views Computer Vision» more  MVA 2011»
13 years 16 hour ago
Kernel-based object tracking using asymmetric kernels with adaptive scale and orientation selection
Abstract Kernel-based object tracking refers to computing the translation of an isotropic object kernel from one video frame to the next. The kernel is commonly chosen as a primiti...
Alper Yilmaz
NIPS
1998
13 years 6 months ago
Dynamically Adapting Kernels in Support Vector Machines
The kernel-parameter is one of the few tunable parameters in Support Vector machines, controlling the complexity of the resulting hypothesis. Its choice amounts to model selection...
Nello Cristianini, Colin Campbell, John Shawe-Tayl...