A framework is proposed that answers the following question: if a moving object is observed by one camera in a pan-tilt-zoom (PTZ) camera network, what other camera(s) might be fo...
Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
Spyros Matsoukas, Antti-Veikko I. Rosti, Bing Zhan...
iary models in order to bridge the semantic gap between high-level, abstract user requirements and low-level, concrete programs and to support a stepwise refinement process. This d...
In comparison with 2D face images, 3D face models have the advantage of being illumination and pose invariant, which provides improved capability of handling changing environments ...
Yi Yao, Sreenivas R. Sukumar, Besma R. Abidi, Davi...
Automatic image annotation is a promising solution to enable semantic image retrieval via keywords. In this paper, we propose a multi-level approach to annotate the semantics of n...