This paper tackles the problem of surveillance video content modelling. Given a set of surveillance videos, the aims of our work are twofold: firstly a continuous video is segment...
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...
This paper presents the modules that comprise a knowledge-based sign synthesis architecture for Greek sign language (GSL). Such systems combine natural language (NL) knowledge, mac...
Stavroula-Evita Fotinea, Eleni Efthimiou, George C...
Boundary integral methods to simulate interfacial flows are very sensitive to numerical instabilities. In addition, surface tension introduces nonlinear terms with high order spat...
—We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object’s appearance due to changing camera pose and li...