Keynote Speakers PDF Print E-mail

1. Dr Andrew B. Watson
NASA Ames Research Center, USA

watsonTitle : Vision Models and Visual Quality

Abstract : One grand challenge for the engineering of multimedia quality has been to develop algorithms that can convert physical measurements – of displays, of images, of graphics, of video sequences, or of complete imaging systems – into metrics that have perceptual meaning. These metrics should enable automated detection of artifacts, quantification of system performance, and optimization of positive multimedia attributes. In the last decade, we and others have made some progress towards this goal. The progress has been achieved by joining display and image measurements to simplified models of processing in the human visual system. In this talk I will describe several of the key concepts and components of these models, and will show how the models can be applied to key problems in display design and image and video processing.  This research may also provide insights for computer graphics applications.

Biography : Andrew B. Watson did undergraduate work at Columbia University and received a PhD in Psychology from the University of Pennsylvania. He subsequently held postdoctoral positions at the University of Cambridge in England and at Stanford University in California. Since 1982 he has worked at NASA Ames Research Center in California, where he is the Senior Scientist for Vision Research, and where he works on models of vision and their application to visual technology. He is the author of over 100 papers on topics such as spatial and temporal sensitivity, motion perception, image quality, and neural models of visual coding and processing. He is the author of six patents, in areas such as image compression, video quality, and detection of artifacts in display manufacturing. In 2001, he founded the Journal of Vision (http://journalofvision.org) where he now serves as Editor-in-Chief. Dr. Watson is a Fellow of the Optical Society of America, of the Association for Research in Vision and Ophthalmology, and of the Society for Information Display. He also serves as the Vice Chair for Vision Science and Human Factors of the International Committee on Display Measurement. In 1990, he received NASA’s H. Julian Allen Award for outstanding scientific paper, and in 1993 he was appointed Ames Associate Fellow for exceptional scientific achievement. He is the 2007 recipient of the Otto Schade Award from the Society for Information Display, and the 2008 winner of the Special Recognition Award from the Association for Research in Vision and Ophthalmology. In 2011, he received the Presidential Rank Award from the President of the United States.

 

2. Prof. David Bull
VI-Lab, University of Bristol, UK

david bullTitle : Perceptual Compression for Emerging Immersive Video Formats

Abstract : User expectations continue to be a driver for increasing the flexibility, quantity and quality of audiovisual information. New formats and displays have raised expectations about how visually engaging content can be, but, when coupled with increasing dynamic range, spatial resolution and frame-rate, these require significantly increased bit-rates to deliver improvements in immersion.
This talk will explore the complex interactions between content type and video parameters including dynamic range, frame rate and spatial resolution, suggesting what impact they have on perceived quality and immersion.  A key question is: how can this impact be assessed and quantified. Furthermore, once quantified, how can these results be used to inform and optimise content delivery?
To deal with the demands of new formats, dramatic improvements in compression will be needed. While significant advances have been made through recentstandards, these are unlikely to deliver the rate-quality performance needed to retain the immersive qualities of the content. Longer term work in parametric video compression, perceptual coding and perceptual metrics is beginning to address this issue and these will be explored in the lecture.

Biography : David Bull C.Eng, FIET, FIEEE is Professor of Signal Processing at the University of Bristol UK. He leads the Visual Information Laboratory at Bristol and is Director of Bristol Vision Institute, a cross disciplinary collaboration between EEE, CS, Mathematics, biology, psychology and the arts.. His previous roles include: Lecturer at the Universityof Wales (Cardiff) and Systems Engineer for Rolls Royce. He was Head of the Electrical and Electronic Engineering Department at Bristol between 2001 and 2006.  In 2001, he co-founded ProVision Communication Technologies, Ltd., a company specialising in high quality wireless video distribution. Based on his work, ProVision was awarded the Frost and Sullivan European Innovation Award for Wireless Multimedia Streaming in 2010.
David has worked widely in the fields of 1-D and 2-D signal processing. He received an IEE Premium for his work on Scanning Confocal Near-Infrared Microscopy, and the IEE Ambrose Fleming Premium for his work on primitive operator filters. He has published numerous patents, several of which have been exploited commercially. His current activities are focused on the problems of image and video communications and analysis, particularly focusing on emerging immersive formats.He has published over 400 academic papers, various articles and two books and has also given numerous invited/keynote lectures and tutorials.

 

3. Prof. Stéphane Mallat
Ecole Polytechnique, Centre de Mathématiques Appliquées, France

stephanemallat Title : Image Classification with Deep Wavelet Invariant Networks

Abstract : Image classification requires to reduce intra-class variability and hence thus build invariant representations. Deep neural networks architectures compute hierchical invariants through cascade of convolutions and non-linearities. Wavelet filters are shown to produce stable "scattering" invariants to groups of transformations such as translation, rotation or scaling. Learning invariants over more complex groups is achieved with unsupervised classification strategies. We show applications to image classification and will discuss relations with simple and complex cell models in the visual cortex area V1, V2 and V4.

Biography : Stephane Mallat received the Ph.D. degree in electrical engineering from the University of Pennsylvania, Philadelphia, in 1988. In 1988, he joined the Computer Science Department of the Courant Institute of Mathematical Sciences where he was Associate Professor in 1994 and Professor in 1996. Since 1995, he has been a full Professor in the Applied Mathematics Department at Ecole Polytechnique, Paris. From 2001 to 2008 he was a co-founder and CEO of a start-up company.
Dr. Mallat is an IEEE and EURASIP fellow. He received the 1990 IEEE Signal Processing Society's paper award, the 1993 Alfred Sloan fellowship in Mathematics, the 1997 Outstanding Achievement Award from the SPIE Optical Engineering Society, the 1997 Blaise Pascal Prize in applied mathematics from the French Academy of Sciences, the 2004 European IST Grand prize, the 2004 INIST-CNRS prize for most cited French researcher in engineering and computer science, and the 2007 EADS prize of the French Academy of Sciences. His research interests include signal processing, learning and harmonic analysis.

 

EUVIP Videos

You must have the Adobe Flash Player installed to view this player.

Sponsors

Relative Organizations

Sorbonne Paris Cite
University Paris 13
L2TI
Institut Mines Telecom
University Paris 7
Telecom Paristech
Plaine Commune