Traditional linear Fukunaga-Koontz Transform (FKT) [1] is a powerful discriminative subspaces building approach. Previous work has successfully extended FKT to be able to deal wit...
This paper proposes a method for computing fast approximations to support vector decision functions in the field of object detection. In the present approach we are building on an...
We study the combined problem of approximating a surface by a quad mesh (or quad-dominant mesh) which on the one hand has planar faces, and which on the other hand is aestheticall...
Mirko Zadravec, Alexander Schiftner, Johannes Wall...
— This paper describes a sensor for autonomous surveillance capable of continuously monitoring the environment, while acquiring detailed images of specific areas. This is achiev...
Stefano Ghidoni, Alberto Pretto, Emanuele Menegatt...
Dynamic modeling of facial appearances and sight directions are demanded for HCI and multimedia applications. Traditional approaches for face tracking and eye tracking from 2D vid...