We present methods for training high quality object detectors
very quickly. The core contribution is a pair of fast
training algorithms for piece-wise linear classifiers, which
...
In this poster, we present how our previously published method of computing continuous 2D scatterplots can be performed with hardware acceleration on a GPU. By doing this, we expl...
This paper presents a novel method to approximate shiftvariant Gaussian filtering of an image using a set of shiftinvariant Gaussian filters. This approximation affords filtering ...
We present a new statistical shape-from-shading framework for images of unknown illumination. The object (e.g., face) to be reconstructed is described by a parametric model. To de...
3D visualization and segmentation of organs in abdominal volume images are important in medical image processing for applications such as diagnosis, treatment and surgical plannin...