This workshop focuses on problems and approaches in computer vision that involve Riemannian geometric computing. Recent interest in this area has resulted in Riemannian geometric principles being applied in problems such as face recognition, activity recognition, object detection, biomedical image analysis, and structure-from-motion to name a few. Besides being mathematically appealing, Riemannian computations based on the geometry of underlying manifolds are often faster and more stable than their classical counterparts. Over the past few years, the popularity of Riemannian algorithms has increased several-fold due to their successful application in many hard computer vision problems (noted above). Some of the mathematical entities that necessitate a geometric analysis include rotation matrices (e.g. in modeling camera motion), stick figures (e.g. for activity recognition), subspace comparisons (e.g. in face recognition), symmetric positive-definite matrices (e.g. in diffusion tensor imaging), and function-spaces (e.g. in studying shapes of closed contours).
Hassen Drira, Sebastian Kurtek, Pavan Turaga,
Organisers
Dena Asta, Carnegie Mellon University
Boulbaba Ben Amor, CRIStAL Laboratory, France
Lo-Bin Chang, Johns Hopkins University
Rama Chellappa, University of Maryland
Gary Christensen, University of Iowa
Leif Ellingson, Texas Tech University
David Jacobs, University of Maryland
Hamid Krim, NC State University
Hamid Laga, University of South Australia
Ruonan Li, Harvard University
Fatih Porikli, Australian National University
Chafik Samir, University of Clermont-Ferrand
Jingyong Su, Texas Tech University
Oncel Tuzel, Mitsubishi Electric Research Labs
Nuno Vasconcelos, University of California – San Diego
Rene Vidal, Johns Hopkins University
Hazem Wannous, CRIStAL Laboratory, France
Qian Xie, Florida State University
Zhengwu Zhang, Florida State University