MMKM sponsored Events

MMKM Workshop on Future Directions in Multimedia Knowledge Management

Alex Hauptmann, Carnegie Mellon University (Multimedia Information Retrieval)
Frederic Fol Leymarie, Goldsmiths, University of London (the Arts)
Wolfgang Nejdl, University of Hanover (social media)
Maja Pantic, Imperial College London (multimodal HCI)
Thomas Seidl, RWTH Aachen (Multimedia Databases)
Steffen Staab, University of Koblenz-Landau (Semantic Web)
Ken Wood, Microsoft Research Cambridge (industrial applications)

Part1: VITALAS at the University of Sunderland [abstract]
Michael Oakes, Marco Palomino and Yan Xu
University of Sunderland
Part 2: Image Annotation with the AdaBoost Learning Algorithm [abstract]
Wei-Chao Lin, Michael Oakes and John Tait
University of Sunderland

GATE - Infrastructure for Text Mining and Natural Language Processing [abstract]
Valentin Tablan, Hamish Cunningham, Danica Damljanovic
University of Sheffield

A Knowledge Structuring Technique for Image Classification [abstract]
Le Dong and Ebroul Izquierdo
Queen Mary University of London

New Visual Information Classification and Clustering Approaches [abstract]
Tomas Piatrik, Uros Damnjanovic and Ebroul Izquierdo
Queen Mary University of London
Multimedia and Vision research Group

FlyTED and FlyWeb - Image Management and Integration for Scientific
Research [abstract]
Jun Zhao, Graham Klyne and David Shotton
Image Bioinformatics Research Group, Department of Zoology, University of Oxford

History and Foresight for Distance-Based Relevance Feedback in Multimedia
Databases [abstract]
Marc Wichterich, Christian Beecks and Thomas Seidl
Data management and data exploration group
RWTH Aachen University, Germany

Distributed Grid Computing for Multi-million Image Retrieval [abstract]
Christopher Town
University of Cambridge and Imense Ltd.

Interfacing Multimedia - Visualisation through Responsive Intuitive
Interfaces [abstract]
Janko Calic
I-Lab, Centre for Communications Systems Research, University of Surrey

Embedding Integrated Multimedia into Virtual Reality Environments [abstract]
Paulo Sampaio
Departamento de Matemática e Engenharias, Universidade da Madeira, Portugal

Content and Context in Digital Photo Retrieval [abstract]
Weiqi Yan (Queen's University Belfast)
Ramesh Jain (University of California, Irvine)

The MPEG Query Format: Unified Access to distributed Multimedia Retrieval
Systems [abstract]
Mario Döller and Harald Kosch (University of Passau, Germany)
Matthias Gruhne (Fraunhofer IDMT, Germany)
Ingo Wolf (Deutsche Telekom, Germany)

Multiresolution Segmentation for Video Surveillances [abstract]
Mohammed A-Megeed Salem and Beate Meffert
Signal Processing and Pattern Recognition Group
Department of Computer Science
Humboldt-Universität zu Berlin, Germany

Fashion and Apparel Browsing for Inspirational Content [abstract]
Annette A. Ward, Stephen J. McKenna, Ian W. Ricketts, Ruixuan Wang, Junwei Han, Wei Jia, University of Dundee; Paul Sergeant, Calico Jack; Anna Buruma, Peter Taylor, Liberty Fabrics; Mike Stapleton, Michael Selway, Graham Howard, System Simulation Ltd.; James Stevenson, Victoria & Albert Museum; Chris Wilkie, Nic Sheen, Advisory Members.

Communicating Meaning and Meeting Information Need within the Music
Industry [abstract]
Charles Inskip, Centre for Interactive Systems Research, Department Of Information Science, City University London, Northampton Square, LONDON, EC1V 0HB
Andy MacFarlane, Centre for Interactive Systems Research, Department Of Information Science, City University London, Northampton Square, LONDON, EC1V 0HB
Pauline Rafferty, Department of Information Studies, Llanbadarn Fawr, University of Wales, ABERYSTWYTH, Ceredigion, SY23 3AS, Wales

Communicating a Vision for Knowledge Sharing in Industry [abstract]
A.-S. Dadzie, V. Lanfranchi1 & D. Petrelli
The University of Sheffield

Cross-Media Knowledge Aquisition in X-Media Project [abstract]
Joao Magalhaes, Jose' Iria, Lei Xi, Mark Greenwood, Fabio Ciravegna

Distribution of Location References in Wikipedia [abstract]
Simon Overell, MMIS Group, Imperial College London
Stefan Rueger, MMIS Group, KMi, The Open University

Knowledge-Based Approach to Modality Choice [abstract]
Yulia Bachvarova, Betsy van Dijk, Anton Nijholt
Human Media Interaction Group, University of Twente The Netherlands

Projects in the MMKM space at Southampton [abstract]
Paul Lewis, University of Southampton

Applied MMKM Research at IT Innovation, University of Southampton [abstract]
Richard Beales, Richard Lowe, University of Southampton

Multimedia and Information Systems Group at the Open University [abstract]
MMIS group, Knowledge Media Institute, The Open University

Thurs 17 Jan 2008 Poster submission
Thurs 24 Jan 2008 Poster and travel award notification
Thurs 07 Feb 2008 Close of registration
Thurs 14 Feb 2008 Workshop

09:45-10:15 Arrival, registration, coffee [in cafeteria, ground floor, Berrill Building]

10:15-10:30 Prof Stefan Rueger, Welcome and Info on the MMKM Network: [Berrill lecture theatre]

Abstract. I will give a short summary of the MMKM network's aims and objectives, the supported activities in 2004-2008 and about funding opportunities for lab exhanges, student support for conference travel and support for workshops

10:30-12:00 position talks [Berrill lecture theatre]

10:30 Prof Frederic Fol Leymarie, Goldsmiths, University of London "The future of multimedia and the arts"

Abstract. I will present views on how the mixing of computing and the arts can help us devise new interfaces and new ways of thinking about information, data, perception (of the physical and the digital).

Our mind is our "basic" interface to the world. The only way we can get informed about the world is via this interface. An artist always feels challenged by the possibility to redefine this interface, expose it, warp it, extend it, possibly provoke us to re-think how we can deal with the (apparently) mounting levels of data we gather about the world on a daily basis to create knowledge.

For an artist, knowledge is not the mere re-presentation of data, but a path to connect interior views with nature. Data, information, become knowledge, acquire meaning only if one creates such meaning. What are the implications for our design of knowledge management systems?

I will suggest that in our efforts to design such systems, it can be fruitful to look on the side of the arts, collaborate with artists, and seek to better understand with their help how we transform data into knowledge.

11:00 Dr Alex Hauptmann, Carnegie Mellon University "The future of Multimedia Information Retrieval"

Abstract. Recent years have seen increasing popularity of video as a shared, searchable medium, with over 100 million daily views from YouTube clips as prime evidence. This talk will cover some of the successes in video retrieval research, focusing on broadcast content as the most extensively studied area. After beginning with a background of audio and video analysis, and spoken document retrieval, the talk will then discuss some current research issues, foremost of these is retrieval based on semantic concepts. One conjecture is that robust semantic concept classification could provide the means to close the semantic gap, that is to allow a characterization of visual or graphic content through natural language. This leads to an examination into the combination of knowledge sources for retrieval, relevance feedback and interfaces for retrieval. Semantic concepts also motivate new research in perspective and topic analysis that also applies to text documents. I will conclude by pointing out retrieval research opportunities in related areas, such as web video, multi-sensor digital human memory, and long-term surveillance.

11:30 Prof Thomas Seidl, RWTH Aachen "The future of multimedia databases and data mining"

Abstract. Multimedia data archives, databases, and web services grow from day to day with a high speed. In order to cope with the huge amount of data, new exploration models and scalable algorithms need to be developed. The expected changes of use also demand changes on the technology level. Starting with content-based retrieval based on complex distance functions including quadratic forms and Earth Movers' distance, interaction models such as incremental search and relevance feedback are discussed. New data mining approaches including subspace clustering, outlier mining, stream data mining, and anytime classification also will be applied to multimedia databases in the future. Following this trend, the underlying retrieval and mining technologies are highly demanded to be extended. Future developments will yield novel approximations, indexing techniques, and multi-step query processing in order to provide efficiency and scalability.

12:00-13:30 Lunch, Poster session and networking [Berrill Cafe and Berrill Foyer]

13:30-15:30 position talks [Berrill lecture theatre]

13:30 Prof Wolfgang Nejdl, L3S, University of Hanover "So how can I ask for it?"

Abstract. More and more information is available both on our personal computers and on the Web, and the current search engines do a great job to make it accessible. Exploiting information structures as well as social information can make them still better. In this talk I will present some ongoing work at L3S addressing these challenges, done in the context of three projects focusing on personal information management and search (NEPOMUK and iSearch) as well as audio-visual and social search (PHAROS). Regarding information structures, I will talk about ongoing work aiming at querying large amounts of heterogeneous structured data without requiring detailed schema knowledge to formulate appropriate queries. Regarding social information, I will discuss first experiments on music recommendation and retrieval, using tags and user profiles from Last.fm.

14:00 Prof Steffen Staab, University of Koblenz-Landau "A Bright Future for Multimedia in the Semantic Web"

Abstract. It is a common, well-worn wisdom in multimedia research that the semantics of a multimedia object is not found in the object alone, but it is determined also by the context, in which it has been created, in which it is used and in which it is interpreted. In the past, only few dimensions of context could be defined and for the ones that were defined they went often unused. Semantic Web technologies are radically changing this picture. So far, Semantic Web technologies have mostly been used to define the content of a multimedia object, with Semantic Web technologies being in place right now, we have the possibility of tracing the context of multimedia objects in a comprehensive manner, yielding new possibilities and new challenges for existing multimedia as well as for existing Semantic Web technologies.

14:30 Dr Ken Wood, Deputy Director, Microsoft Research Cambridge "Multimedia retrieval for real people"

Abstract. In this talk I will give an overview of some past and current work in content-based retrieval of multimedia objects, including my own work and that of others. I will develop the thesis that state-of-the-art techniques for automatic analysis and indexing of multimedia content are less important than the careful design of browsing interfaces based on the needs of real users, i.e. people other than engineers and computer scientists.

15:00 Prof Maja Pantic, Imperial College London "The Future of Multimedia and Multimodal Interfaces"

Abstract. It is widely believed that the next shift in computing technology will be embedding computers into our homes, transportation means, and working spaces. If this prediction is to come true, then next generation computing should be about anticipatory user interfaces that should be human-centered, built for humans based on human models. They should transcend the traditional keyboard and mouse to include natural interactive functions including understanding and emulating human behaviors such as affective and social signaling. This talk discusses a number of components of human behavior, how they might be integrated into computers, and how far we are from enabling computers to understand human behavior.

15:30-16:00 coffee & refreshments [Berrill cafe]

16:10-16:40 Panel session "Future directions in Multimedia Knowledge Management"

16:40-16:50 Wrap-up and close

Stefan Rueger (website)
Dawei Song (website)

Workshop: Semantic Image Retrieval - The User Perspective

26-27 March 2007, University of Brighton, UK

The semantic gap is now familiar as that rift in the image retrieval landscape between the information that can be extracted automatically from a digitised image and the interpretation that humans might place upon the image. Widely perceived as a barrier to progress, interest in bridging the gap is running high. Thus far, however, most of the research effort is directed only at attempting to interpret the digitised raw image in terms of objects and scenes to which textual labels may be applied. That leaves unspanned the great conceptual distance between object labelling and the high-level human reasoning which situates those objects appropriately in the semantic space within which the great majority of real user queries are formulated. True semantic image retrieval occupies these further reaches of the semantic gap, the focus of this conference lies in this difficult region. Registration is free.

More...  List of invited speakers

MMKM Workshop: Multimedia Knowledge Management: Industry meets academia

Knowledge Media Institute of the Open University Milton Keynes, United Kingdom
8 Jan 2007

News: poster session programme is now available

News: workshop webcast will take place at this location.

Introduction
The purpose of this workshop is to look at multimedia knowledge management from the perspectives of industry and academia in a rapidly changing digital world: communities create huge resources (wikiversity and -pedia, Flickr photo sharing); video is available in virtually unlimited quantity (youtube); broadcasters brace themselves for video-on-demand rather than linear channels; personalisation is on the rise not only at online-shop portals and iTune playlists but also in specific drugs for your genes; folksonomies replace taxonomies; thresholds of making web-services a business vanish as storage space and cpu-time become scalable commodities (the amazon cloud, web 2.0); people discover the long tail, where all is made available and the difficulty is "just" to find it. All these have an impact on the industries that are involved in any kind of multimedia knowledge management and the corresponding academic counterparts alike.

This workshop is designed to bring together people from industry and academia to share knowledge, explore possible interactions, understand different perspectives, and take first steps towards developing future collaborations.

Poster Submission
We welcome posters describing your work/research interests/thoughts/ideas pertinent to multimedia knowledge management, from a wide range of disciplines and perspectives such as databases, digital libraries, information retrieval, search engines, computer vision, audio processing, human computer interaction, visualisation, data mining etc

Please submit an author list, a title and a one-paragraph abstract for your poster to Dawei Song (d.song+at+open.ac.uk) by 8 Dec 2006. If accepted, this information will appear on the web and you should then bring an A1-poster to be displayed on 8 Jan. Poster numbers are limited, please consider submitting only one poster per group.

Funding
MMKM is able to provide funding support (covering travel and accommodation) for a number of UK-based young researchers (e.g., PhD students, postdocs and early career academics). Young researchers from groups who submit a poster get preference for travel funding. Applicants should indicate their current status (students, postdocs, or junior lecturers) and requests for funding through this page by 8 Dec 2006. Later requests are possible, but may not be granted.

Important Dates
Fri 8th Dec 2006   Poster submission/travel award requests
Fri 15th Dec 2006   Poster and travel award notification
Wed 20th Dec 2006  Close of registration
Mon 8th Jan 2007   Workshop

Travel info
Please see this link.

Organisers
Stefan Rueger (s.rueger)
Dawei Song (Dawei Song)

Knowledge Media Institute
and Centre for Research in Computing
The Open University, UK
Walton Hall
Milton Keynes
MK7 6AA
United Kingdom

http://kmi.open.ac.uk

Workshop Programme, 8 Jan

0950-1020: Arrival, registration, coffee [in cafeteria, ground floor, Berrill Building]

1020-1030: Introduction and welcome (Stefan Rueger) [Berrill lecture theatre]

1030-1200: Industry talks [Berrill lecture theatre]

• BBC Archives (Steve Jupe): The BBC's Digital Media Initiative
• BT (Li-Qun Xu): Digital Convergence: The challenges and opportunities for BT's Future in Networked Multimedia Services
• Kodak European Research (Alan Payne): Digital Transformation in the Consumer Imaging Industry
• Motorola Labs (Jonathan Teh): Personal content management in a mobile environment

1200-1330: Lunch and networking [location tbc]

1330-1500: Posters from academic institutions [the Old Lecture Theatre - note different location]

1500-1520: coffee & refreshments [in cafeteria, ground floor, Berrill Building]

1520-1650: Industry talks [Berrill lecture theatre]

• Museums, Libraries and Archives Council (David Dawson): Building Digital Museums, Libraries and Archives
• System Simulations Ltd (George Mallen): From mono to multi, reflections on the evolution of digital cultural heritage.
• FAST Search and Transfer (Ian Parry): Emerging MM opportunities in the Enterprise Search Market
• Yahoo! Research Europe (Roelof van Zwol): Yahoo! and the Power of Social Media

First International Workshop on Adaptive Information Retrieval

• Adaptive retrieval and result presentation
• Interactive multimedia retrieval
• Test collection building for the evaluation of adaptive systems

The workshop takes place on 14th October 2006 in Glasgow, UK. More...

[Updated]: Visual Categorisation and Image Management Systems 

The workshop will be held at the University of Sunderland, St. Peter’s Campus, on the 28th June 2006. It will comprise invited lectures, oral presentations and a plenary discussion.

More information can be found in this flyer or on the workshop website.

Semantic Interoperability for e-Research in the Sciences, Arts and Humanities

MMKM EWIMT 2005 Workshop 

More...

MMKM Adaptive Multimedia Retrieval Workshop in Glasgow

More...

The network has officially kicked off