PRIMORIS      Contacts      FAQs      INSTICC Portal
 

Keynote Lectures

Social Cameras
Andrea Cavallaro, Queen Mary University of London, United Kingdom

Gesture Interaction with Virtual Humans and Social Robots
Daniel Thalmann, Nanyang Technological University, Singapore

Topological and Feature-based Visualization
Gerik Scheuermann, Universtät Leipzig, Germany

From Single Object to Contextual Authentication - A New Challenge in Multimedia Forensics and Beyond
Mauro Barni, Universita` di Siena, Italy

 

Social Cameras

Andrea Cavallaro
Queen Mary University of London
United Kingdom
 

Brief Bio
Andrea Cavallaro is Professor of Multimedia Signal Processing and Director of the Centre for Intelligent Sensing at Queen Mary University of London, UK. He received his Ph.D. in Electrical Engineering from the Swiss Federal Institute of Technology (EPFL), Lausanne, in 2002. He was a Research Fellow with British Telecommunications (BT) in 2004/2005 and was awarded the Royal Academy of Engineering teaching Prize in 2007; three student paper awards on target tracking and perceptually sensitive coding at IEEE ICASSP in 2005, 2007 and 2009; and the best paper award at IEEE AVSS 2009. Prof. Cavallaro is Area Editor for the IEEE Signal Processing Magazine and Associate Editor for the IEEE Transactions on Image Processing. He is an elected member of the IEEE Signal Processing Society, Image, Video, and Multidimensional Signal Processing Technical Committee, and chair of its Awards committee. He served as an elected member of the IEEE Signal Processing Society, Multimedia Signal Processing Technical Committee, as Associate Editor for the IEEE Transactions on Multimedia and the IEEE Transactions on Signal Processing, and as Guest Editor for seven international journals. He was General Chair for IEEE/ACM ICDSC 2009, BMVC 2009, M2SFA2 2008, SSPE 2007, and IEEE AVSS 2007. Prof. Cavallaro was Technical Program chair of IEEE AVSS 2011, the European Signal Processing Conference (EUSIPCO 2008) and of WIAMIS 2010. He has published more than 130 journal and conference papers, one monograph on Video tracking (2011,Wiley) and three edited books: Multi-camera networks (2009, Elsevier); Analysis, retrieval and delivery of multimedia content (2012, Springer); and Intelligent multimedia surveillance (2013, Springer).


Abstract
The pervasiveness of amateur wearable and handheld cameras has been revolutionizing the way private and public events are captured and shared. This explosion of content from social cameras and their shared user-generated videos offers the opportunity for new ways of analysing and timely reporting stories that range from music concerts and sports events to disaster scenes and protests. However, this large amount of increasingly available videos and their varying quality makes the selection and editing very difficult thus strongly limiting the opportunity to harvest the value of these user-generated videos. This talk will cover audio-visual methods for the automated grouping and synchronisation of multi-view user-generated videos in unconstrained scenarios. I will present ways to align these videos on a global timeline and show how to automatically edit them to produce a coherent final cut.



 

 

Gesture Interaction with Virtual Humans and Social Robots

Daniel Thalmann
Nanyang Technological University
Singapore
 

Brief Bio

Prof. Daniel Thalmann is with the Institute for Media Innovation at the Nanyang Technological University in Singapore. He is a pioneer in research on Virtual Humans and one of the most highly cited scientists in Computer Graphics.. His current research interests include Real-time Virtual Humans in Virtual Reality, crowd simulation, and 3D Interaction. Daniel Thalmann has been the Founder of The Virtual Reality Lab (VRlab) at EPFL, Switzerland, Professor at The University of Montreal and Visiting Professor/ Researcher at CERN, University of Nebraska, University of Tokyo, and National University of Singapore. He is coeditor-in-chief of the Journal of Computer Animation and Virtual Worlds, and member of the editorial board of 6 other journals. Daniel Thalmann was member of numerous Program Committees, Program Chair and CoChair of several conferences including IEEE VR, ACM VRST, ACM VRCAI, CGI, and CASA. Daniel Thalmann has published more than 500 papers in Graphics, Animation, and Virtual Reality. He is coeditor of 30 books, and coauthor of several books including 'Crowd Simulation' (second edition 2012) and 'Stepping Into Virtual Reality' (2007), published  by Springer. He received his PhD in Computer Science in 1977 from the University of Geneva and an Honorary Doctorate (Honoris Causa) from University Paul- Sabatier in Toulouse, France, in 2003. He also received the Eurographics Distinguished Career Award in 2010 and the 2012 Canadian Human Computer Communications Society Achievement Award.


Abstract

In this lecture, we will discuss the interaction with autonomous  Virtual Humans and Social Robots based on Gesture Recognition. We will first cover the various methods of capturing gestures and understanding them. In particular, we will present  an interactive system based on a novel combination of sensors. It allows one person to interact with a virtual human or a social robot using natural body language. The virtual human or the robot understands the meaning of human upper body gestures and expresses itself by using a combination of body movements, facial expressions and verbal language. We will also emphasize how hand pose tracking and gesture recognition are useful for human-computer interaction, while a major problem is the lack of discriminative features for compact hand representation. We will present robust hand parsing scheme to extract a high-level description of the hand from the depth image. Finally, we will discuss interaction with Virtual Groups and Crowds.



 

 

Topological and Feature-based Visualization

Gerik Scheuermann
Universtät Leipzig
Germany
 

Brief Bio

Gerik Scheuermann is Full Professor of Image and Signal Processing at the University of Leipzig, Germany, since 2004. He received his PhD in Computer Science from TU Kaiserslautern in 1999 where he also served as assistant professor from 2001 to 2004. His research interests center around all areas of visualization including visual analytics. He has also worked on Clifford algebra, topological data analysis, and information theoretic methods. He published more than 180 papers on these topics. He received best paper awards at TopoInVis 2011, PacificVis 2012 and PacificVis 2014. He served on numerous Program Committees, and as Paper Co-Chair for EuroVis 2008, IEEE SciVis 2011, and IEEE SciVis 2012. Currently, he acts as Paper Co-Chair of IEEE PacificVis 2015. He organized TopoInVis 2007, AGACSE 2008, and EuroVis 2013. He is currently Associated Editor of The Visual Computer and IEEE Computer Graphics and Applications. In the past, he served on the editorial board of IEEE Transactions on Visualization and Computer Graphics.


Abstract
Visualization is one of the most important applications of computer graphics. It has become a valuable tool for nearly all areas of science, engineering, and even the humanities. Essentially, visualization exploits computer graphics to ease human access to digital data. As data and its graphical representation exceeds the capacity of human eyes and brains, reduction techniques become a necessity. Topological and feature based techniques are among the most successfull solutions to this dilemma. The lecture will draw the line from early work to current trends. Modern research looks into unsteady field data, multifields, and uncertainty. In addition, we will shed light on the growing number of application domains that can profit from topological and feature oriented visualization. While early work centered around classical fluid dynamics, biochemistry, medicine, and even computer science are now among these disciplines.



 

 

From Single Object to Contextual Authentication - A New Challenge in Multimedia Forensics and Beyond

Mauro Barni
Universita` di Siena
Italy
 

Brief Bio
Mauro Barni graduated in electronic engineering at the University of Florence in 1991. He received the PhD in Informatics and Telecommunications in October 1995. He has carried out his research activity for almost 20 years first at the Department of Electronics and Telecommunication of the University of Florence, then at the Department of Information Engineering and Mathematical Sciences of the University of Siena where he works as associate Professor. During the last decade, his activity has focused on digital image processing and information security, with particular reference to the application of image processing techniques to copyright protection (digital watermarking) and authentication of multimedia (multimedia forensics). Lately he has been studying the possibility of processing signals that has been previously encrypted without decrypting them (signal processing in the encrypted domain – s.p.e.d.).
He is author/co-author of about 270 papers published in international journals and conference proceedings, he holds three patents in the field of digital watermarking and one patent dealing with anticounterfeiting technology. His papers on digital watermarking have significantly contributed to the development of such a theory in the last decade as it is demonstrated by the large number of citations some of these papers have received. The overall citation record of M. Barni amounts to an h-number of 42 according to Scholar Google search engine. He is co-author of the book “Watermarking Systems Engineering: Enabling Digital Assets Security and other Applications”, published by Dekker Inc. in February 2004. He is editor of the book “Document and Image Compression” published by CRC-Press in 2006.
He has been the chairman of the IEEE Multimedia Signal Processing Workshop held in Siena in 2004, and the chairman of the IV edition of the International Workshop on Digital Watermarking. He was the technical program chairman of the 2005 edition of the Information Hiding Workshop, the VIII edition of the International Workshop on Digital Watermarking and the V edition of the IEEE Workshop on Information Forensics and Security (WIFS 2013). He is the technical program co-chair of ICASSP 2014, to be held in Florence. In 2008, he was the recipient of the IEEE Signal Processing Magazine best column award. In 2010 he was awarded the IEEE Transactions on Geoscience and Remote Sensing best paper award.
He was the founding editor in chief of the EURASIP Journal on Information Security. He is part of the editorial board of the IEEE Signal Processing Magazine. He has served for 9 years as associate editor of the IEEE Trans. on Circuits and system for Video Technology and for 3 years the IEEE Transactions on Information Forensics and Security. In the past he served as associate editor of the IEEE Signal Processing Magazine (column and forum section), the IEEE Signal Processing Letters, the IEEE Transactions on Multimedia, the Eurasip Journal of Applied Signal Processing and the IET Proceedings on Information Security.
From 2010 to 2011, Prof. Barni has been the chairman of the IEEE Information Forensic and Security Technical Committee (IFS-TC) of the IEEE Signal Processing Society. He has been a member of the IEEE Multimedia Signal Processing technical committee and of the conference board of the IEEE Signal Processing Society. Mauro Barni is a fellow member of the IEEE and senior member of EURASIP. He was appointed distinguished lecturer by the IEEE Signal Processing Society for the years 2013-2014.
He participated to several National and European research projects on diverse topics, including digital watermarking, information security, signal processing in the encrypted domain and multimedia forensics. He is currently leading the VIPP (Visual Information Processing and Protection) group of the Telecommunication Laboratory of the Information Engineering Department at the University of Siena (http://clem.dii.unisi.it/~vipp/). The group currently consists of 7-10 members including faculty members, graduate and undergraduate students.


Abstract
Multimedia forensics (MF) is a rather new discipline aiming at collecting evidence about the past history of multimedia documents, including the identification of the source of the document, the distinction between computer generated and natural images, the detection of traces left by the application of certain processing tools like resampling or JPEG compression, the modification of the semantic content of the document through cut and paste or copy-move operations. So far MF researchers have focused on the analysis of single isolated documents, however it is easy to realize that, in most cases, content truthfulness and authenticity must be decided upon by analysing it in the context wherein the content is used and by the light of the available context-relevant knowledge and information.  Such an observation leads to the formulation of a new challenging research trend, namely contextual authentication of multimedia contents. Early works in this sense include detection of cut and paste operations in large dataset of images, and image phylogeny, whereby the relationship between images (and videos) found on the web are looked for so to build a so-called dependency graph or multimedia family tree. It is the goal of this talk to summarize the fundamentals of Multimedia Forensics, present the open issues this field is currently facing with and discuss the main challenges set by multimedia contextual authentication.



footer