— Tendon driven mechanisms have been considered in robotic design for several decades. They provide lightweight end effectors with high dynamics. Using remote actuators it is pos...
Most coreference resolution models determine if two mentions are coreferent using a single function over a set of constraints or features. This approach can lead to incorrect deci...
Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstra...
This work provides a framework for learning sequential attention in real-world visual object recognition, using an architecture of three processing stages. The first stage rejects...
In this work we focus on the problem of frequent itemset mining on large, out-of-core data sets. After presenting a characterization of existing out-of-core frequent itemset minin...