We describe a tracker that can track moving people in long sequences without manual initialization. Moving people are modeled with the assumption that, while configuration can var...
Among the various types of semantic concepts modeled, events pose the greatest challenge in terms of computational power needed to represent the event and accuracy that can be ach...
A key problem in video content analysis using dynamic graphical models is to learn a suitable model structure given some observed visual data. We propose a Completed Likelihood AI...
Copyright 2001 IEEE. Published in the 2001 International Conference on Image Processing (ICIP-2001), October 7-10, 2001, Thessaloniki, Greece. Personal use of this material is per...
Goal-oriented methodologies have demonstrated some adequacy for modelling composite systems, from high level desired properties to operational requirements on responsible agents. T...
Christophe Ponsard, Nadiya Balych, Philippe Masson...