SemanticMetadata.net

Two new research papers published

Two research contributions of me and my colleagues finally made their way online. The paper Adaptive Visual Information Retrieval by Changing Visual Vocabulary Sizes in Context of User Intentions by Marian Kogler, Oge Marques and me investigates how the size and generation process of visual word vocabularies influences retrieval for different degrees of intentionality, being a clear search intent, a surfing intent and a browsing intent. The paper Which Video Do You Want to Watch Now? Development of a Prototypical Intention-based Interface for Video Retrieval by Christoph Lagger, Oge Marques and me presents selected results of a large scale study on the motivations of video consumption on the internet.

Social Media, Tagging and Images Semantics

Recently there was quite a buzz around the whole social media topic. Many researchers saw indications that the willingness or people to share and annotate content might lead to new ways of indexing, searching and consuming multimedia. The biggest problems with the buzz is … that it’s BIG Many research groups produced even more papers and with the rising number of papers the scientific impact got smaller and smaller. However Neela Sawant, Jia Li and James Z. Wang took a close look at more than 200 papers and provide a survey on part of the topic with the journal article “Automatic image semantic interpretation using social action and tagging data” in the Multimedia Tools and Applications journal.

Links

• Paper at Springerlink
• PDF at stanford.edu

CfP Special Session on User Intentions @ WIAMIS 2011

Special Session at the WIAMIS 12th International Workshop on Image Analysis for Multimedia Interactive Services, April 13-15, 2011, Delft, The Netherlands

User Intentions in Image Production, Sharing, and Retrieval

The lifecycle of images and other types of visual information contains numerous actions that are triggered by user intentions and goals. Every little action, from content production to retrieval of previously stored visual information, takes the user a step forward towards a state where a user assumes that a goal has been achieved. Examples of such intentions are “learn how to tie a tie”, “be entertained” or “show video of a holiday to relatives”.

With the advent of social systems and its social multimedia networks, the actions of a user have become more and more transparent. Comments, ratings, recommendations, search queries and history, upload activity logs, and communication records can be analyzed to infer a user’s goal. This goal can then be used to leverage retrieval of multimedia content and to better adapt multimedia systems to users’ needs. Moreover, the goals of content producers and providers can be analyzed and matched with the goals of the content consumers.

Content-based analysis, indexing and search of visual information often does not take the user’s intentions into account. Research activity on the user roles in multimedia systems has, so far, focused on specific topics (e.g., “personalized multimedia delivery” or “adaptive multimedia systems”). Investigating the actual intentions or goals of a user throughout the lifecycle of image production, sharing, and retrieval is a fairly young research topic that has just recently started to attract attention from the multimedia research community.

In this special session we want to bring together researchers and practitioners from the visual information retrieval, image analysis and multimedia systems research. We aim to discuss recent scientific advances and also first results of greenhouse work on user intentions in multimedia.

Submission

Submission deadline is Dec 10, 2011. Additional information is available at http://www.wiamis2011.org/

Topics of interest include (but are not limited to)

• User intentions in visual content production
• User intentions in visual content sharing
• User intentions in visual information retrieval
• User intentions and image sharing in social networks
• Models and taxonomies for user intentions in multimedia in narrow domains (e.g., medical imaging, video surveillance, how-to videos, etc.)
• Multimedia metadata for user intentions
• Analysis and mining of user goals and intentions
• Studies on user goals, motivations and intentions in multimedia  systems
• Methods to leverage user intentions in multimedia applications

Organizers

• Mathias Lux, Klagenfurt University, Austria (mlux [at] itec [dot] uni-klu [dot] ac [dot] at)
• Oge Marques, Florida Atlantic University, USA (omarques [at] fau [dot] edu)

ACM Multimedia Call for Volunteers out …

ACM Multimedia – taking place in Firenze, Italy, last week of Oct. – still is in need for student volunteers. I personally think this is a great opportunity to learn about big conferences and the community. If you are interested ensure to send your bid until Oct. 7th 2010. Find the call here.

Links

• http://www.acmmm10.org/volunteers/

SOMA World Games event – you’re invited!

In the course of the SOMA project we invite *you* on April 22nd, 2010 to the „SOMA World Games“ event. On four different stages four different games will be played:

• Rockband,
• Singstar,
• Wii Sports Ressort &
• Tony Hawk Ride.

Be there and join our games!

Why? We want to investigate how multimedia content is created in such a social event, and how this content can be used for our self-organizational approach of detecting and presenting “situations of interest” (as, e.g., “crowd formation”).

This means that you will become photographed and filmed. But do not worry, the gathered content is just used for our research purposes and will not be published elsewhere.

When? Thursday, April 22nd, 2010, from 17.00 to 23.00

Where? Lakeside Labs GmbH, Lakeside B04b, 1st floor, 9020 Klagenfurt

Please register for this social event in our doodle poll under http://www.doodle.com/vnw6sy5t7zgkae2i if you like to participate. There will be also plenty to eat and drink. We are looking forward to seeing you!

The SOMA Team

CfP: Modeling Social Media

Markus Strohmaier has pointed out the following CfP to me: International Workshop on Modeling Social Media 2010 (MSM’10). It takes place June 13th, 2010, and is co-located with Hypertext 2010, Toronto, Canada. Submission deadline is April 9th, 2010 and topics are

• new modeling techniques and approaches for social media
• models of propagation and influence in twitter, blogs and social tagging systems
• models of expertise and trust in twitter, wikis, newsgroups, question and answering systems
• modeling of social phenomena and emergent social behavior
• agent-based models of social media
• models of emergent social media properties
• models of user motivation, intent and goals in social media
• cooperation and collaboration models
• software-engineering and requirements models for social media
• adapting and adaptive hypertext models for social media
• modeling social media users and their motivations and goals
• architectural and framework models
• user modeling and behavioural models
• modeling the evolution and dynamics of social media

More information can be found on the workshop home page.

Links

• http://kmi.tugraz.at/workshop/MSM10/

WS on Multimedia Metadata (WMM’09) – Proceedings

Just in case someone missed it: the workshop proceedings of our last multimedia community workshop:

• Case Studies on Context-aware Mobile Multimedia Services -Timo Ojala
• Content-Based Image Retrieval Systems – Reviewing and Benchmarking -Harald Kosch and Paul Maier
• Delivery Context Descriptions – A Comparison and Mapping Model -Christian Timmerer, Johannes Jabornig, and Hermann Hellwagner
• A Novel Tool for Quick Video Summarization using Keyframe Extraction Techniques -Mathias Lux, Klaus Schöffmann, Oge Marques, and Laszlo Böszörmenyi
• Authoring Interactive Mobile Services Using MPEG-7 and MPEG-4 LASeR -Albert Hofmann, Andreas Kriechbaum, and Werner Bailer
• An User Study on Rich Media Mobile Guide Applications – Omar Choudary, Benoit Baccot, Romulus Grigoras, Vincent Charvillat
• What Algorithms for Urban Routing on Mobile Devices? -Tristram Gräbener, Alain Berro, and Yves Duthen
• Towards the Use of Multimedia Contents to Represent Events in Vehicular Ad Hoc Networks – Nicolas Cenerario, Thierry Delot, Sergio Ilarri
• A Multimedia Service with MPEG-7 Metadata and Context Semantics – Yiwei Cao, Ralf Klamma, and Maziar Khodaei
• A Standards-Based Generic Approach for Complex Multimedia Management -Anna Carreras, Ruben Tous, Eva Rodríguez, Jaime Delgado, Giovanni Cordara, Gianluca Francini, and Diego Gibellino
• Contribution to the Modelling of Multimedia Metadata in a Distributed Architecture -Ana-Maria Manzat, Florence Sedes, and Romulus Grigoras
• Media Center Oriented Linux Operating System -Tudor Miu, Olivia Stanescu, Ana Constantin, Sorin Lacriteanu, Roxana Grigore, Domnina Burca, Tudor Constantinescu, and Alexandru Radovici
• A Multi-level Access Control Scheme For Multimedia Database – Vanessa El-Khoury

via CEUR-WS.org/Vol-441 – Multimedia Metadata (WMM’09).

ISM 2009: deadline extension

The deadline for full paper submission of the ISM 2009 (IEEE International Symposium on Multimedia) has been extended to July 12th. So we all can reconsider submitting there

Links

• http://ism2009.eecs.uci.edu/

Self Organizing Multimedia Architecture (SOMA) – The Project

Currently we are working a lot on a research project funded by a Carinthian agency. The project goes on for 3 years (2.5 years left) and has enough funds to pay 4 PhDs and 1 post doc researcher. Here is the description and the link to the blog:

The project Self-organizing Multimedia Architecture (SOMA) aims to capture the whole life-cycle of multimedia content in a single architecture for large distributed multimedia information systems. In SOMA we focus on scenarios where events, which we understand as “limited time periods of special importance”, are a central concept. Examples for such scenarios are sports events stretching over time, where start, finish or critical parts of a race are possible events, or traffic monitoring, where events like traffic jams or accidents have to be reported and investigated.

via Project Description | Self Organizing Multimedia Architecture.

WIAMIS 2008 talk: Video summarization through acceleration

With the contribution “Redundancy Removing by Adaptive Acceleration and Event Clustering for Video Summarization” Bernard Mérialdo presented a very interesting approach to video summarization. Beside other methods the video is accelerated. Based on the overall motion the actual amount of acceleration is adapted. Furthermore they apply hierarchical clustering on fixed size segments to select most important parts. Therefore the video is faster when not very much motion is going on and slower if fast motion is characteristics for a video segment. Nice added value was hat he described the RUSHES track of TRECVID and the evaluation process. Experts evaluate the accuracy of the summaries and weight them with extraction time and size of the summary.