Human behavior recognition is one of the most important and challenging objectives performed by intelligent vision systems. Several issues must be faced in this domain ranging fro...
Motivated by the problem of customer wallet estimation, we propose a new setting for multi-view regression, where we learn a completely unobserved target (in our case, customer wa...
In this paper, we present a novel approach, named RS2D, to risk driven semantic service query routing in unstructured, so called pure P2P networks. Following the RS2D protocol, ea...
Adaptive Hypermedia Systems adjust the content to best suit users' personal characteristics, but rarely consider delivery performance. Performance issues are even more signifi...
Lejla Rovcanin, Cristina Hava Muntean, Gabriel-Mir...
In this paper, we present a connectionist approach for detecting and precisely localizing semi-frontal human faces in complex images, making no assumption about the content or the...