Robust methods for spatial and temporal alignment

Lecturer: 
Dr. Stefanos Zafeiriou
Lecturer's institute: 
Imperial College London, UK
Date: 
3.6.2014 13:15
Place: 
TS128

 

Infotech Oulu Lecture Series

Robust methods for spatial and temporal alignment

 

Lecturer: Dr. Stefanos Zafeiriou, Imperial College London, UK

Date: Tuesday, June 3, 2014
Time: 13-16
Room: TS128

 

Abstract

The past decade computer vision (CV), the area of computer science that specialises in automatic analysis and understanding of visual data, has witnessed tremendous developments due to the abundance of visual data, the development of powerful features (such as SIFT, HoGs, LBPs etc.) and the prevalence of Statistical Machine Learning (SML) , which promised and delivered many powerful learning methodologies. But what is then the difference between modern computer vision and statistical machine learning? The difference is alignment. In particular, in computer vision before defining SML algorithms, or even applying a simple (dis)-similarity between spatial or temporal data, we first need to remove any spatial or temporal discrepancies. In this tutorial, I will motivate and describe recent methodologies of my group regarding spatial alignment of facial images, as well as, temporal alignment of facial behaviour.

CV

Dr. Stefanos Zafeiriou, since 2012, is a Lecturer (equivalent to Assistant Professor) in Computer Vision and Pattern Recognition in the  Department of Computing, Imperial College London. He has been awarded  one of the prestigious Junior Research Fellowships (JRF) from Imperial  College London in 2011. He received the B.Sc, degree in Informatics with  highest honors and the Ph.D degree in Informatics in 2003 and 2007,  respectively, from the Aristotle University of Thessaloniki, Greece. He  has been conducting research in automatic facial analysis for more than  9 years participating in more than 10 EU and British research projects. From 2003 to 2007 he was a research and teaching assistant in the  Department of Informatics at Aristotle University of Thessaloniki,  Greece. During 2007-2008 he was a Research Associate in the same  Department. During 2008-2011 he was a Research Associate/Research Fellow  in the Departments of Electrical and Electronic Engineering and  Computing, Imperial College London, UK. In 2009 he was a Visiting  Researcher at the University of Houston, Texas, USA. He has received  various scholarships and awards during his undergraduate, Ph.D. and  postdoctoral studies. Dr. Zafeiriou is an associate editor of Image and  Vision Computing Journal and of IEEE Transactions on Cybernetics  (previously IEEE Transactions on Systems, Man, and Cybernetics Part B).  He has co-authored more than 100 technical papers including more than 30 journal papers in face recognition, face tracking/alignment, modelling  of facial motion and deformation and novel machine learning approaches  to modelling facial behaviour, as well as more than 20 papers in top  vision and learning conferences such as CVPR, ICCV, ECCV, ICML, ECML etc.

 

More information: Guoying Zhao

Attachments: 

Last updated: 19.5.2014