In the last decade, graph-cut optimization has been popular for a variety of pixel labeling problems. Typically graph-cut methods are used to incorporate a smoothness prior on a l...
We present a new method for the detection and estimation of multiple illuminants, using one image of any object with known geometry and Lambertian reflectance. Our method obviates ...
Even after more than two decades of input devices development, many people still find the interaction with computers an uncomfortable experience. Efforts should be made to adapt c...
This work describes a novel methodology for automatic contour extraction from 2D images of 3D neurons (e.g. camera lucida images and other types of 2D microscopy). Most contour-ba...
Jorge J. G. Leandro, Roberto M. Cesar, Luciano da ...
Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...