Sciweavers

725 search results - page 23 / 145
» Invariances in kernel methods: From samples to objects
Sort
View
NIPS
2008
13 years 9 months ago
An Extended Level Method for Efficient Multiple Kernel Learning
We consider the problem of multiple kernel learning (MKL), which can be formulated as a convex-concave problem. In the past, two efficient methods, i.e., Semi-Infinite Linear Prog...
Zenglin Xu, Rong Jin, Irwin King, Michael R. Lyu
CVPR
2000
IEEE
14 years 9 months ago
In Search of Illumination Invariants
We consider the problem of determining functions of an image of an object that are insensitive to illumination changes. We rst show that for an object with Lambertian r e e ctanc ...
Hansen F. Chen, Peter N. Belhumeur, David W. Jacob...
ICIP
2008
IEEE
14 years 9 months ago
Using local regression kernels for statistical object detection
We present a novel approach to the problem of detection of visual similarity between a template image, and patches in a given image. The method is based on the computation of a lo...
Hae Jong Seo, Peyman Milanfar
CVPR
2011
IEEE
12 years 11 months ago
Using Specular Highlights as Pose Invariant Features for 2D-3D Pose Estimation
We address the problem of 2D-3D pose estimation in difficult viewing conditions, such as low illumination, cluttered background, and large highlights and shadows that appear on t...
Aaron Netz, Margarita Osadchy
SIGGRAPH
2010
ACM
14 years 5 days ago
Multi-class blue noise sampling
Sampling is a core process for a variety of graphics applications. Among existing sampling methods, blue noise sampling remains popular thanks to its spatial uniformity and absenc...
Li-Yi Wei