In this paper we describe Maestro, a dataflow computation framework for Ibis, our Java-based grid middleware. The novelty of Maestro is that it is a self-organizing peer-to-peer s...
Abstract Weproposeacomputationalmodelofcontourintegration for visual saliency. The model uses biologically plausible devices to simulate how the representations of elements aligned...
In this paper we explore object recognition in clutter. We test our object recognition techniques on Gimpy and EZGimpy, examples of visual CAPTCHAs. A CAPTCHA ("Completely Au...
In this paper, we present a methodology to estimate a detailed state of a video scene involving multiple humans and vehicles. In order to annotate and retrieve videos containing a...
Mobile devices are increasingly powerful in media storage and rendering. The prevalent request of decent video browsing on mobile devices is demanding. However, one limitation com...