A common way to represent a time series is to divide it into shortduration blocks, each of which is then represented by a set of basis functions. A limitation of this approach, ho...
We study the compression problem of visual scenes acquired with a camera for transmission or storage. Our proposed model is general and includes two well-known cases: that of vide...
Although semi-supervised learning has been an active area of research, its use in deployed applications is still relatively rare because the methods are often difficult to impleme...
In this paper we describe a technique to infer the topology and connectivity information of a network of cameras based on observed motion in the environment. While the technique c...
Abstract. In this contribution we present a silhouette based human motion estimation system. The system components contain silhouette extraction based on level sets, a corresponden...
Bodo Rosenhahn, Uwe G. Kersting, Andrew W. Smith, ...