Comparison and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to human behavior understanding

Comparison and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to human behavior understanding

Place: Large Lecture Room

Abstract: Developing intelligent systems dedicated to human behavior understanding has been a very hot research topic in the few recent decades. In this talk, we consider a novel space-time representation of human landmark sequences. We propose a representation based on the trajectories of Gram matrices of human landmarks. Gram matrices are positive semi-definite matrices of fixed rank and lie on a nonlinear manifold. We evaluate the proposed approach in several applications involving 2D and 3D landmarks of human faces and bodies such us emotion recognition from facial expression and body movements and also action recognition from skeletons. We will also show how these ideas can be extended to face images.

Short Bio: Mohamed Daoudi is a Full Professor of Computer Science at IMT Lille Douai and the Head of Image group at CRIStAL Laboratory (UMR CNRS 9189). He received his Ph.D. degree in Computer Engineering from the University of Lille (France) in 1993 and Habilitation A Diriger des Recherches from the University of Littoral (France) in 2000. His research interests include pattern recognition, shape analysis and computer vision. He has published over 150 papers in some of the most distinguished scientific journals and international conferences. He is Associate Editor of Image and Vision Computing Journal.