In this paper we propose to use lexical semantic networks to extend the state-of-the-art object recognition techniques. We use the semantics of image labels to integrate prior kno...
In this paper we present a method for reasoning about privacy using the concepts of exchangeability and deFinetti's theorem. We illustrate the usefulness of this technique by...
Abstract. We present the first (to our knowledge) approximation algorithm for tensor clustering—a powerful generalization to basic 1D clustering. Tensors are increasingly common...
Most of vision-based algorithms for motion and localization estimation requires matching some interest points in a pair of images. After building feature correspondence, it is pos...
—People within and outside the information visualization community are motivated to create new tools to address their own unique problems of understanding data. However, the tec...