This paper describes a novel view-based learning algorithm for 3D object recognition from 2D images using a network of linear units. The SNoW learning architecture is a sparse netw...
Real-time estimation of a camera’s pose relative to an object is still an open problem. The difficulty stems from the need for fast and robust detection of known objects in the s...
A system to retrieve images using a description of the image intensity surface is presented. Gaussian derivative lters at several scales are applied to the image and low order 2D ...
This paper presents a novel representation for human actions which encodes the variations in the shape and motion of the performing actor. When an actor performs an action, at eac...
: Modeling of families of geometric objects is a major topic in modern geometric and solid modeling. Object families are central to many important solid modeling applications, incl...