Abstract: It is now well known that many problems in image understanding and multimedia content analysis can benefit from human computations and crowdsourcing techniques. In this talk, we’ll first examine a few influential works from the literature where explicit tasks are performed by motivated workers (through altruistic incentives or personal enjoyment) and then combined with content analysis methods. In the second part of the presentation, our recent results on ‘zoomable video players’ will be briefly presented. These examples particularly highlight the use of implicit tasks to naturally infer knowledge about the visual or multimedia content.

Short-CV: Vincent CHARVILLAT received the Eng. degree in Computer Science and Applied Mathematics from ENSEEIHT, Toulouse France and the M.Sc. in Computer Science  from the National Polytechnic Institute of Toulouse, both in 1994. He received the Ph.D. degree in Computer Science from the National Polytechnic Institute of Toulouse in 1997. He is currently a full professor at the University of Toulouse, IRIT research lab, ENSEEIHT Eng. School. Vincent CHARVILLAT is the head of  VORTEX research team at ENSEEIHT. His main research interests are visual processing and multimedia applications. Current topics of research include visual object processing, visual compositing, visual interaction design and crowdsourcing in multimedia.

Abstract:

The ubiquitous access to the Web and, more generally to digital contents has dramatically changed the “digital experience” everyone daily lives. However, the diversity of contexts (technical contexts, social contexts, personal contexts), the diversity of users, the diversity of digital contents have definitely made mandatory the (or at least, some) personalization of the users’ experience.
The notion of “Universal Multimedia Experience (UME)” has been coined to represent this attempt to put the user at the center of the content delivery process. The key idea that underpins this concept is the notion of adaptation: adaptation of the delivery process to the network conditions, adaptation of the type of content to the user’s preferences and profile, adaptation of the content itself to the user’s terminal capabilities and user’s activity, etc.
This talk will address some of the key issues related to multimedia content adaptation and multimedia quality of experience.
First, we will focus on the modeling of the user’s context. Indeed, a basic condition to adaptation is the capture (or the inference) and the representation of the user’s “context” i.e., the technical conditions (network, terminal), the user’s activity, the user’s intention, the user’s profile and preferences.
Then, the core of the talk will be dedicated to the specific issues of video content adaptation. By their isochronous nature; by the richness and complexity of the information they carry; by the multiplicity of their stakeholders (end user, creator, video broadcaster), video contents raise specific and complex issues related to both semantic, perceptual and even legal constraints and conflicts.
To address these issues, we will introduce the concept of Utility Function, which aims at integrating in one multi-dimensional optimization space, semantic constraints, user’s context characteristics and perceptual considerations.
As a side effect of this modeling of the video adaptation process, we will analyze how the enforcement of access control rules on video contents can be formalized as a problem of content adaptation.
Finally, we will investigate some still open issues related to video delivery optimization in P2P and delay-tolerant networks, complex multi-dimensional semantic constraints, visual aesthetics, privacy and security.
This talk will be illustrated by research works developed in the International Doctoral College and Federative Laboratory “Multimedia Distributed and Pervasive Secure Systems” (MDPS) which comprises researchers from the National Institute of Applied Sciences (INSA) of Lyon, France (Pr. L. Brunie’s team), the University of Passau (Pr. H. Kosch’s team), Germany and the University of Milan, Italy (Pr. E. Damiani’s team).

CV:

Lionel Brunie is full professor at the National Institute of Applied Sciences (INSA) of Lyon, France, where he leads the LIRIS DRIM research team.
With 10 permanent researchers and 15+ PhD students, the DRIM team is specialized in distributed data management, multimedia information systems, information retrieval, and security/privacy.
In 2007, along with Pr Harald Kosch (University of Passau, Germany), Lionel Brunie created the French-German doctoral college in “Multimedia Distributed and Pervasive Secure Systems (MDPS)”. MDPS was extended in 2009 to the University of Milan, Italy (Pr. Ernesto Damiani’s team). MDPS proposes both a framework for international co-supervised PhDs and a federative research institute that develops a joint research agenda.
Lionel Brunie’s main topics of interest include: data management in large scale and pervasive systems, collaborative multimedia information systems, security and privacy, e-health applications.

Der Rückblick zum TEWI-Kolloquium von Dr. Oge Marques am 21-05-2013 beinhaltet die Videoaufzeichnung sowie die Folien:

Video

[iframe height=“350″ src=“http://video.aau.at/video.php?video=ftf_marques2.mp4″]

Slides

[iframe src=“http://www.slideshare.net/slideshow/embed_code/22430761″ width=“476″ height=“400″ frameborder=“0″ marginwidth=“0″ marginheight=“0″ scrolling=“no“]

Abstract:
There are many challenging problems in computer vision for which state-of-the-art solutions fall short of performing perfectly. The realization that many of these tasks are arduous for computers yet are relatively easy for humans has inspired many researchers to approach those problems from a human computation viewpoint, using methods that includecrowdsourcing and games – often called ‘games with a purpose’ (GWAPs). The talk discusses how we can use human computation (in general) and particularly games to help uncover hidden aspects of visual perception and use these findings to improve computer vision solutions to related problems. It particularly highlights two examples of our recent work on the topic:
1.   Guess That Face (with Mathias Lux and Justyn Snyder, CHI 2013): a face recognition game that reverse engineers the human biological threshold for accurately recognizing blurred faces of celebrities under time-varying conditions.
2.   Ask’N’Seek (with Vincent Charvillat and Axel Carlier, ECCV 2012): an object detection and labeling game that asks users to guess the location of a hidden region within an image with the help of semantic and topological clues and uses the information collected from game logs, combined with results from content analysis algorithms, to feed a machine learning algorithm that outputs the outline of the most relevant regions within the image and their names.

Short CV:
Oge Marques is an Associate Professor in the Department of Computer & Electrical Engineering and Computer Science at Florida Atlantic University (FAU) (Boca Raton, Florida). He received his Ph.D. in Computer Engineering from FAU in 2001. He has more than 20 years of teaching and research experience in the fields of image processing and computer vision, in different countries (U.S., Austria, Brazil, Netherlands, Spain, France, and India), languages (English,Portuguese,Spanish), and capacities.He is the (co-) author of more than 50 refereed journal and conference papers and several books in these topics, including the textbook Practical Image and Video Processing UsingMATLAB (Wiley, 2011). His research interests are in the area of intelligent processing of visual information, which combines the fields of image processing, computer vision, image retrieval, machine learning, serious games, and human visual perception. He is particularly interested in the combination of human computation and machine learning techniques to solve computer vision problems.

He is a senior member of both the ACM and IEEE, and a member of the IEEE Computer Society, IEEE Education Society, IEEE Signal Processing Society, and the honor societies of Tau Beta Pi, Sigma Xi, Phi Kappa Phi, and Upsilon Pi Epsilon.

Der Rückblick zum TEWI-Kolloquium und Antrittsvorlesung von Prof. Dr. Martin Pinzger am 24.04.2013 beinhaltet die Videoaufzeichnung sowie die Folien:

Video

[iframe height=“350″ src=“http://video.aau.at/video.php?video=rv_pinzger.mp4″]

Slides

[iframe src=“http://www.slideshare.net/slideshow/embed_code/22430443″ height=“400″ width=“476″ frameborder=“0″ marginwidth=“0″ marginheight=“0″ scrolling=“no“]

Abstract: Software is omnipresent. It is key to successful businesses and has become key to our social activities. As many systems, also software systems need to change in order to stay successful on the market. However, these changes cause software systems to become larger in size and more complex as described by Lehman’s Laws of Software Evolution. As a consequence, more resources are needed to maintain, or in general, evolve a software system. Evolving software systems is therefore mastering change and system complexity. The goal of my research and teaching is to provide software engineers with means to master this challenge.

In this inauguration lecture, I outline several challenges of evolving software systems and present the ideas and findings from my recent research to address them. In particular, I show how we can use the history of software projects to identify critical parts of a software system and how we can use visualization techniques to help software engineers to understand the implementation of large, complex software systems including large spreadsheets.

CV: Martin Pinzger is Professor of Software Engineering and head of the Software Engineering Research Group at the University of Klagenfurt. His research interests cover various topics in designing and evolving software systems. He holds a PhD in Computer Science from the Vienna University of Technology, worked as a Senior Research Associate at the University of Zurich, and as an Assistant Professor at the Delft University of Technology. He is a recipient of the prestigious Dutch NWO Vidi grant and co-founder of the TU Delft start-up Infotron.

Abstract:

The use of software development methods (SDM) in software industry proves beneficial as it contributes to higher quality of both, the process and its product, i.e. the developed software. Despite these evident benefits, the studies on the maturity of the software development discipline show that a large percent of software development companies do not have their SDMs documented and those that have, do not really follow them or do not follow them rigorously. This problem has been recognized as one of the key reasons for failures in software development projects and a contributor to the low quality of software. In this talk I will introduce a novel approach that could help to improve the maturity of software development processes. The approach is based on the method engineering principles taking into account the limitations that hinder its use in practice. The main objective of our research is to show that the method engineering concepts which have been developed in the last few decades but never really penetrated to practice are applicable in real settings and that could contribute to software industry.

About the Speaker:

Marko Bajec is an Associate Professor at the University of Ljubljana, Faculty of Computer and Information Science. He is a member of the Department for Informatics where he delivers courses on Information Systems and Databases. Marko’s research interests mostly focus on IS Development and IT Governance. Since 2009, he has been on the position of the Head of the Laboratory for Data Technologies where he manages research in data technologies in relation to IS development and management. In his past research Marko has developed different approaches and methods that help measuring, formalizing, and improving software development processes. For his achievements in transferring knowledge to industry he has got several awards and recognitions. Marko Bajec is vice-president of Slovenian society INFORMATICA and Slovenian representative of IFIP TC 2 – Software: Theory and Practice. He is also a founder and co-owner of the university spin-off Optilab, which has become the leading Slovenian provider of solutions and services for fraud management in the insurance business.

Vortragender:
Assoc.-Prof. Dr.-Ing. György WERSÉNYI
Széchenyi István University, Györ, Hungary
Faculty of Engineering Sciences
Department of Telecommunications

Abstract:
Virtual Reality Simulators create a multisensory 3D space for subjects by using visual screens and auditory displays. In this multimedia presence, audio plays a significant role. Users often wear headphones and a virtual sound space is rendered with directional information.
In order to achieve this, psychoacoustic measurements, implementation of digital filters, subjective listening tests etc. are required. The whole process raises several problems, so information technology and engineering solutions may help reducing errors, inconvenience or even price.
Besides basic research questions about the human spatial hearing, measurement and playback systems support the development of assistive applications, devices mostly focused on people with disabilities, such as rehabilitation, sports or the community of the visually impaired.

Kurzbio:
György Wersényi was born in Györ, Hungary, in 1975. He received the M.Sc. degree in electrical engineering from the Technical University of Budapest, Hungary, in 1998 and the Ph.D. degree from the Brandenburgische Technische Universitat (BTU) Cottbus, Germany, in 2002. He has been a member of the Department of Telecommunications at the Szechenyi Istvan University, Hungary, since 2002.
He is an associate professor at the field of telecommunications, audio and video broadcast, and electroacoustics. His current research includes spatial hearing, listening tests, virtual audio displays, acoustic measurement, and dummy-head techniques.
Dr. Wersenyi is a member of the Audio Engineering Society, the Hungarian Telecommunication Society, and board member of the International Community for Auditory Display (ICAD).