We present an approach for object recognition that combines detection and segmentation within a efficient hypothesize/test framework. Scanning-window template classifiers are the ...
This paper presents a new approach for multi-view object class detection. Appearance and geometry are treated as separate learning tasks with different training data. Our approach...
Our goal is to provide tools to support working meetings on an electronic whiteboard, called Tivoli. This paper describes how we have integrated structured domain objects, which r...
We seek to support the development of open, distributed applications from patible software abstractions. In order to rigorously specify these abstractions, we are elaborating a for...
Markus Lumpe, Jean-Guy Schneider, Oscar Nierstrasz
: In this paper we describe a method for tracking walking humans in the visual field. Active contour models are used to track moving objects in a sequence of images. The resulting ...