We propose a novel algorithm for segmenting multiple motions of different types from point correspondences in multiple affine or perspective views. Since point trajectories associ...
Existing content-based publish/subscribe systems are designed assuming that all matching publications are equally relevant to a subscription. As we cannot know in advance the dist...
Kresimir Pripuzic, Ivana Podnar Zarko, Karl Aberer
We study an extension of the "standard" learning models to settings where observing the value of an attribute has an associated cost (which might be different for differ...
Abstract— This paper considers two issues arising in an integrated IEEE 802.16e/802.11 network: 1) finding a possible network, which mobile station (MSTA) can switch to, and 2) ...
We consider the problem of recognizing 3-D objects from 2-D images using geometric models and assuming different viewing angles and positions. Our goal is to recognize and localize...