Current two-dimensional image based face recognition systems encounter difficulties with large facial appearance variations due to the pose, illumination and expression changes. ...
We describe techniques for exploring 3D scenes by combining non-linear projections with the interactive data mining of camera navigations from previous explorations. Our approach ...
This paper presents the Visual Touchpad, a low-cost vision-based input device that allows for fluid two-handed interactions with desktop PCs, laptops, public kiosks, or large wall...
Hough transform based object detectors learn a mapping from the image domain to a Hough voting space. Within this space, object hypotheses are formed by local maxima. The votes con...
The Informedia Digital Video Library user interface summarizes query results with a collage of representative keyframes. We present a user study in which keyframe occlusion caused...
Mark Derthick, Michael G. Christel, Alexander G. H...