In this paper, we present a method to speed up video encoding of GPU rendered scenes. Modern video codecs, like H.264/AVC, are based on motion compensation and support partitionin...
In this paper, we present an approach for video surveillance involving (a) moving object detection, (b) tracking and (c) normal/abnormal event recognition. The detection step uses...
This paper presents a fast disparity analysis approach based on a hybrid block- and pixel-recursive matching scheme. The key idea is to choose efficiently a small number of candid...
Peter Kauff, Nicole Brandenburg, Michael Karl, Oli...
This paper presents a multi-view articulated human motion tracking framework using particle filter with manifold learning through Gaussian process latent variable model. The dime...
We consider the problem of learning with instances defined over a space of sets of vectors. We derive a new positive definite kernel f(A B) defined over pairs of matrices A B base...