Abstract. Selective attention shift can help neural networks learn invariance. We describe a method that can produce a network with invariance to changes in visual input caused by ...
In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlatio...
In this paper, we describe methods to localize a mobile robot in an indoor environment from visual information. An appearance-based approach is adopted in which the environment is ...
In this paper we present the World-Wide Web Wrapper Factory (W4F), a Java toolkit to generate wrappers for Web data sources. Some key features of W4F are an expressive language to...
We present a new downsampling method for structured volume grids, which preserves much more of the topology of a scalar field than existing downsampling methods by preferably selec...