In this paper, we show that in a multi-camera context, we can effectively handle occlusions in real-time at each frame independently, even when the only available data comes from ...
An anytime algorithm is capable of returning a response to the given task at essentially any time; typically the quality of the response improves as the time increases. Here, we c...
Abstract— In this paper, we focus on 2 : 1 spatial resolution downscaling transcoding from MPEG-2 to WMV. We propose two architectures (for sequences with or without B-frames res...
Online communities are extremely popular; yet most of them still rely primarily on text for knowledge creation and communication. This paper describes a graphical webpoll prototyp...
Abstract— This paper introduces a novel approach to representing and learning tool affordances by a robot. The tool representation described here uses a behavior-based approach t...