Many successful models for predicting attention in a scene involve three main steps: convolution with a set of filters, a center-surround mechanism and spatial pooling to constru...
Naila Murray, Maria Vanrell, Xavier Otazu, C. Alej...
Despite the prominence of multi-touch technologies, there has been little work investigating its integration into the desktop environment. Bringing multi-touch into desktop comput...
Xiaojun Bi, Tovi Grossman, Justin Matejka, George ...
Imagine that you have been entrusted with private data, such as corporate product information, sensitive government information, or symptom and treatment information about hospita...
Nicolas Anciaux, Mehdi Benzine, Luc Bouganim, Phil...
Collaborative annotation tools are in widespread use. The metadata from these systems can be mined to induce semantic relationships among Web objects (sites, pages, tags, concepts...
Contextual information is vital for the robust extraction of semantic information in automated surveillance systems. We have developed a scene independent framework for the detect...