— Estimating the pose of an imaging sensor is a central research problem. Many solutions have been proposed for the case of a rigid environment. In contrast, we tackle the case o...
In this paper, we propose an unsupervised approach to select representative face samples (models) from raw videos and build an appearance-based face recognition system. The approa...
This paper summarizes a probabilistic approach for localizing people through the signal strengths of a wireless IEEE 802.11b network. Our approach uses data labeled by ground trut...
Sebastian Thrun, Geoffrey J. Gordon, Frank Pfennin...
Multiple-instance learning (MIL) is a popular concept among the AI community to support supervised learning applications in situations where only incomplete knowledge is available....
In a typical reinforcement learning (RL) setting details of the environment are not given explicitly but have to be estimated from observations. Most RL approaches only optimize th...