Most approaches to classifying media content assume a fixed, closed vocabulary of labels. In contrast, we advocate machine learning approaches which take advantage of the millions...
We present HOMER, an observational-equivalence model checker for the 3rd-order fragment of Idealized Algol (IA) augmented with iteration. It works by first translating terms of the...
Abstract. Mobile intention recognition is the problem of inferring an agent's intentions from the spatio-temporal behavior she shows. We present a framework for mobile intenti...
—Although IP Multicast is an effective network primitive for best-effort, large-scale, multi-point communication, many multicast applications such as shared whiteboards, multi-pl...
Abstract—We propose a fully automatic and computationally efficient framework for analysis and summarization of soccer videos using cinematic and object-based features. The propo...