Boosting is a popular way to derive powerful learners from simpler hypothesis classes. Following previous work (Mason et al., 1999; Friedman, 2000) on general boosting frameworks,...
We pose robust matching with parametric and non-parametric constraints as the problem of finding a stable independent set (SIS) in an oriented graph whose vertices are all possible...
Linear perspective projection has served as the dominant imaging model in computer vision. Recent developments in image sensing make the perspective model highly restrictive. This...
Motion stereo is to extract the 3-0 information of an object from images of a moving camera, using geometric relationships between corresponding points. This paper presents an acc...
A generalized image model (GIM) is presented. Images are represented as sets of four-dimensional (4D) sites combining position and intensity information, as well as their associat...