The objective of this work is automatic detection and identification of individuals in unconstrained consumer video, given a minimal number of labelled faces as training data. Whi...
Foreground detection is at the core of many video processing tasks. In this paper, we propose a novel video foreground detection method that exploits the statistics of 3D space-tim...
In this paper we propose a new approach to web visualisation with VRML based on a function-based shape modelling, which unifies different types of mathematical functions in order ...
Human motion can be understood on many levels. The most basic level is the notion that humans are collections of things that have predictable visual appearance. Next is the notion...
Christopher Richard Wren, Brian P. Clarkson, Alex ...
We present a new shape-from-distortion framework for recovering specular (reflective/refractive) surfaces. While most existing approaches rely on accurate correspondences between 2...