We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and po...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
A common way to model multiclass classification problems is by means of Error-Correcting Output Codes (ECOCs). Given a multiclass problem, the ECOC technique designs a code word fo...
Sergio Escalera, David M. J. Tax, Oriol Pujol, Pet...
This paper presents a family of techniques that we call congealing for modeling image classes from data. The idea is to start with a set of images and make them appear as similar a...
This paper presents a method for fully automatic and robust estimation of two-view geometry, autocalibration, and 3D metric reconstruction from point correspondences in images take...
In this paper, we propose two novel methods for face recognition under arbitrary unknown lighting by using spherical harmonics illumination representation, which require only one t...