Current uses of tagged images typically exploit only the most explicit information: the link between the nouns named and the objects present somewhere in the image. We propose to ...
Sung Ju Hwang, University of Texas, Kristen Grauma...
Typical Human Robot Interaction (HRI) assumes that the user explicitly interacts with robots. However, explicit control with robots can be unnecessary or even undesirable in certa...
The availability of map interfaces and location-aware devices makes a growing amount of unstructured, geo-referenced information available on the Web. In particular, over twelve m...
An important feature of future context-aware and adaptive networks would be the ability to provide QoS to user flows. Our approach enables end-hosts and other devices to expose an...
Roel Ocampo, Alex Galis, Hermann de Meer, Chris To...