Video

Slides

Abstract

Mobile Visual Search (MVS) is a fascinating research field with many open challenges and opportunities which have the potential to impact the way we organize, annotate, and retrieve visual data (images and videos) using mobile devices. This talk is structured in four parts:

(i) MVS — opportunities: where I present recent and relevant numbers of the mobile computing market, particularly in the field of photography apps, social networks, and mobile search.

(ii) Basic concepts: where I explain the basic MVS pipeline and discuss the three main MVS scenarios and associated challenges.

(iii) Advanced technical details: where I explain technical aspects of feature extraction, indexing, descriptor matching, and geometric verification, discuss the state of the art in these fields, and comment on open problems and research opportunities.

(iv) Examples and applications: where I show recent and significant examples of academic research (e.g., Stanford Product Search System) and commercial apps (e.g., Google Goggles, oMoby, kooaba) in this field.

Video

Slides

Abstract

This talk will present SPLAY, an integrated system that facilitates the design, deployment and testing of large-scale distributed applications. Unlike existing systems, SPLAY covers all aspects of the development and evaluation chain. It allows developers to express algorithms in a concise, simple language that highly resembles pseudo-code found in research papers. The execution environment has low overheads and footprint, and provides a comprehensive set of libraries for common distributed systems operations. SPLAY is freely available from http://www.splay-project.org/.

Video

Slides

Abstract:

With the growing amount of images, videos, and music, the task to support users in exploring multimedia databases is of ever-increasing importance. That is why numerous content-based browsing approaches have been developed. They support users in searching and browsing for multimedia objects in an interactive and playful way. In terms of query performance, however, these browsing approaches are frequently limited to small-to-moderate size databases. The question of how to efficiently browse large-scale multimedia databases yet remains to be answered.

In this talk, I will provide an overview of efficient query processing techniques applicable to content-based browsing systems. To this end, I will first introduce the domain of adaptive distance-based similarity measures and show how to model image similarity in a flexible way. I will then present recent developments for efficient exploration query processing by means of similarity-based visualizations and metric indexing. Finally, I will show how to browse millions of multimedia objects in a few seconds.

Abstract:  

Mobile Visual Search (MVS) is a fascinating research field with many open challenges and opportunities which have the potential to impact the way we organize, annotate, and retrieve visual data (images and videos) using mobile devices. This talk is structured in four parts:
(i) MVS — opportunities: where I present recent and relevant numbers of the mobile computing market, particularly in the field of photography apps, social networks, and mobile search.

(ii) Basic concepts: where I explain the basic MVS pipeline and discuss the three main MVS scenarios and associated challenges.

(iii) Advanced technical details: where I explain technical aspects of feature extraction, indexing, descriptor matching, and geometric verification, discuss the state of the art in these fields, and comment on open problems and research opportunities.

(iv) Examples and applications: where I show recent and significant examples of academic research (e.g., Stanford Product Search System) and commercial apps (e.g., Google Goggles, oMoby, kooaba) in this field.

Dr. Oge Marques is an Associate Professor and Associate Chairman in the Department of Computer and Electrical Engineering & Computer Science at Florida Atlantic University in Boca Raton, Florida. He is currently a guest professor with ITEC at Klagenfurt University. He received his Ph.D. in Computer Engineering from Florida Atlantic University in 2001, his Masters in Electronics Engineering from Philips International Institute / Eindhoven University of Technology (Eindhoven, NL) in 1989 and his Bachelor’s Degree in Electrical Engineering from UTFPR (Curitiba, Brazil), where he also taught for more than 10 years before moving to the USA. He has been teaching undergraduate and graduate students for more than 20 years. His research experience has been mostly in the fields of image processing and computer vision. He is the (co-) author of four books in these topics, including the recently released textbook “Practical Image and Video Processing Using MATLAB” (Wiley-IEEE Press, 2011). He is a Senior Member of both the IEEE and the ACM.

This talk will present SPLAY, an integrated system that facilitates the design, deployment and testing of large-scale distributed applications. Unlike existing systems, SPLAY covers all aspects of the development and evaluation chain. It allows developers to express algorithms in a concise, simple language that highly resembles pseudo-code found in research papers. The execution environment has low overheads and footprint, and provides a comprehensive set of libraries for common distributed systems operations. SPLAY is freely available from http://www.splay-project.org/.

CV: Pascal Felber received his M.Sc. and Ph.D. degrees in Computer Science from the Swiss Federal Institute of Technology. From 1998 to 2002, he has worked at Oracle Corporation and Bell-Labs (Lucent Technologies) in the USA. From 2002 to 2004, he has been an Assistant Professor at Institut EURECOM in France. Since October 2004, he is a Professor of Computer Science at the University of Neuchâtel, Switzerland, working in the field of dependable and distributed systems. He has published over 80 research papers in various journals and conferences.

With the growing amount of images, videos, and music, the task to support users in exploring multimedia databases is of ever-increasing importance. That is why numerous content-based browsing approaches have been developed. They support users in searching and browsing for multimedia objects in an interactive and playful way. In terms of query performance, however, these browsing approaches are frequently limited to small-to-moderate size databases. The question of how to efficiently browse large-scale multimedia databases yet remains to be answered.

In this talk, I will provide an overview of efficient query processing techniques applicable to content-based browsing systems. To this end, I will first introduce the domain of adaptive distance-based similarity measures and show how to model image similarity in a flexible way. I will then present recent developments for efficient exploration query processing by means of similarity-based visualizations and metric indexing. Finally, I will show how to browse millions of multimedia objects in a few seconds.

Kurzfassung:

Selbstorganisierende Systeme findet man in vielen Bereichen wie zum Beispiel der Biologie, Chemie, Physik, Soziologie und Ökonomie. Als gemeinsamen Nenner findet man hier jeweils Agenten, welche durch einfaches Zusammenspiel im Gesamten ein robustes, leistungsfähiges System formen, welches komplexe Aufgaben lösen kann.

Solche Systeme sind typischerweise nicht über einen ursprünglichen Entwurf eines Systems hervorgegangen, sondern haben sich evolutionär entwickelt. Bemerkenswert ist auch der Anteil an kooperativem Verhalten, der in vielen Systemen – wie zum Beispiel in Insektenstaaten – zu finden ist ; hier gibt ein Agent oft einen persönlichen Vorteil zugunsten des Schwarms auf. Auch diese Entwicklung kann evolutionär erklärt werden.

In der Technik sind Methoden zum Erzeugen von selbstorganisierenden kooperativen Systemen interessant. Gerade durch die zunehmende Miniaturisierung und Vernetzung von Komponenten stoflen herkömmliche Entwurfs- und Steuermechanismen nämlich an ihre Grenze. In den Lakeside Labs wird daher im Rahmen von mehreren Projekten an der technischen Umsetzung von selbstorganisierenden Systemen geforscht.

Wilfried Elmenreich (born 1973) is a senior postdoc researcher at the Mobile Systems Group of the Institute of Networked and Embedded Systems at the University of Klagenfurt, Austria. He is also affiliated with the Lakeside Labs, a research cluster investigating self-organizing networked systems. His interests include wireless sensor networks, real-time systems and protocols, energy systems, and self-organizing systems. He studied at the Engineering School for Electrotechnics and Control in Weiz, Austria and graduated at the Vienna University of Technology (TU Wien) where he received a Master’s degree in computer science in 1998 and a Ph.D. degree in technical sciences in 2002. From 1999 to 2007, he was a research and teaching staff member at the Institute of Computer Engineering at TU Wien. In 2008, he was granted the habilitation (venia docendi) from the Vienna University of Technology. Wilfried was a visiting researcher at the Vanderbilt University in 2005, at the Embedded Systems and Operating Systems group at the Otto-von-Guericke-Universität Magdeburg in 2006, and at the CISTER/IPP-Hurray Research Unit at the Polytechnic Institute of Porto in 2007. Wilfried Elmenreich was editor of 4 books and published over 100 papers in the field of networked and embedded systems. He is a Senior Member of IEEE. His Erdös Number is 3.

Festkolloquium

am Freitag, dem 28. Oktober 2011, ab 14 Uhr im Raum z.1.09 (Zentralgebäude) der Alpen-Adria-Universität Klagenfurt, Universitätsstraße 65-67, 9020 Klagenfurt am Wörthersee

Programm:

14.00 Uhr: Begrüßung und Grußworte

14.30 Uhr: Univ. Prof. Dr. Harald Niederreiter, Österreichische Akademie der Wissenschaften und King Fahd University of Petroleum & Minerals, Saudi Arabien „Algebra und Kryptographie: eine glückliche Verbindung“

16.00 Uhr: Univ. Prof. Dr. Dietmar Dorninger, Dekan der Fakultät für Mathematik und Geoinformation der TU Wien und Ao. Univ. Prof. i. R. Dr. Hermann Kautschitsch, Alpen-Adria-Universität Klagenfurt „Winfried Müller: Unser Weggefährte an der TU Wien und an der Universität Klagenfurt“

anschließend Imbiss und Erfrischungen

Um Anmeldung wird bis 21.10.2011 gebeten an:

Frau Anita Wachter, Bakk.a phil.
Institut für Mathematik, Alpen-Adria-Universität Klagenfurt
Universitätsstraße 65-67, 9020 Klagenfurt am Wörthersee
Tel. ++43 (0) 463 2700 3103, Fax. ++43 (0) 463 2700 3199
anita.wachter@uni-klu.ac.at

Hinweise zur Anfahrt finden Sie unter: http://www.uni-klu.ac.at/lage/inhalt/231.htm

Informationen zu Übernachtungsmöglichkeiten: http://www.klagenfurt-tourismus.at

ABSTRACT

This talk provides an overview of the dataflow interchange format (DIF) project at the University of Maryland. DIF is a textual language for specifying mixed-­grain dataflow representations of signal processing applications.

A wide variety of signal processing domains is targeted by the DIF project, including applications for processing signals in the audio, speech, wireless communications, image, and video processing domains. A major theme in the DIF project is facilitating experimentation with interactions between different dataflow modeling techniques and associated transformations that exploit specific properties of these techniques. One way that DIF achieves this is by allowing designers to specify subgraphs of a design in terms of specific dataflow modeling techniques, such as synchronous, cyclo-­static, and parameterized dataflow, through corresponding keywords in the language. DIF also incorporates a new dataflow model of computation called enable-­invoke dataflow, which is geared towards high expressive power, functional simulation, rapid prototyping, quasi-­static scheduling, and efficient refinement into more specialized dataflow models.

SHUVRA S. BHATTACHARYYA

is a Professor in the Department of Electrical and Computer Engineering, University of Maryland at College Park. He holds a joint appointment in the University of Maryland Institute for Advanced Computer Studies (UMIACS). He is coauthor or coeditor of six books and the author or coauthor of more than 150 refereed technical articles. His research interests center around architectures, methodologies, software techniques, and tools for design of signal processing systems. He received the B.S. degree from the University of Wisconsin at Madison, and the M.S. and Ph.D. degrees from the University of California at Berkeley. He has held industrial positions as a Researcher at the Hitachi America Semiconductor Research Laboratory (San Jose, California), and Compiler Developer at Kuck & Associates (Champaign, Illinois). He has held a visiting research position at the US Army Research Laboratory (Rome, New York). He has served as Chair of the IEEE Signal rocessing Society Technical Committee on Design and Implementation of Signal Processing Systems. He is a Fellow of the IEEE.