Abstract. Foreground and background segmentation is a typical problem in computer vision and medical imaging. In this paper, we propose a new learning based approach for 3D segment...
The building identification (BID) problem is based on a process that uses publicly available information to automatically assign addresses to buildings in satellite imagery. In pr...
Martin Michalowski, Craig A. Knoblock, Kenneth M. ...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
In this position paper we propose an evaluation framework for networked mobile gaming, consisting of user, group, communication, and environment models. Each of these components a...
Collision detection is required by most virtual reality (VR) applications, and in recent years, collision detection algorithms utilizing graphics hardware capabilities have been a...