We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
Recent work in Ontology learning and Text mining has mainly focused on engineering methods to solve practical problem. In this thesis, we investigate methods that can substantially...
Object-based segmentation is a challenging topic. Most of the previous algorithms focused on segmenting a single or a small set of objects. In this paper, the multiple class objec...
We present a variational approach to jointly estimate a displacement map and a superresolution texture for a 3D model from multiple calibrated views. The superresolution image form...
In conventional security systems, protected resources such as documents, hardware devices and software applications follow an On/Off access policy. On, allows to grant access and ...