This talk addresses the problem of appearance matching across disjoint camera views. Significant appearance
changes, caused by variations in view angle, illumination and object pose, make the problem challenging. We
propose to formulate the appearance matching problem as the task of learning a model that selects the most
descriptive features for a specific class of objects. Learning is performed in a covariance metric space using an
entropy‐driven criterion. Our main idea is that different regions of the object appearance ought to be
matched using different strategies to obtain a distinctive representation. The proposed technique has been
successfully applied to the person re‐identification problem, in which a human appearance has to be matched
across non‐overlapping cameras. We demonstrate that our approach improves state of the art performance in
the context of pedestrian recognition.
Dr. Slawomir Bak is a computer vision scientist at the STARS team at INRIA Sophia Antipolis. He obtained his Bachelor's Degree in 2007 at Poznan University of Technology, Faculty of Computing Science. In 2007 he was a member of the Automated Scheduling Optimisation and Planning (ASAP)research group at University of Nottingham. He obtained his Master degree in 2008 at Poznan University of Technology in GRID computing. Since 2008, he has conducted research in computer vision as a joint research scientist between INRIA and PSNC. In 2012 he obtained his PhD at University of Nice under the supervision of Francois Bremond and Jan Weglarz. The thesis was reviewed by Cordelia Schmid,Mubarak Shah and Frederic Jurie.
