Re-using Media on the Web
learn how to annotate and interlink online media fragments for new applications
at the World Wide Web (WWW) Conference 2014, Seoul, S Korea,
on April 8, 2014. (14:00 – 17:30) in Room R 301B
This tutorial will address the state of the art in the area of online media analysis, annotation and linking, reflecting that a number of Web-based specifications and technologies are now emerging that in combination can provide the technical solution for media owners to be enabled to manage and re-use their online media at a fragment level.
The combination of these specifications and technologies can form a full online media workflow able to support media fragmentation and re-use, which opens means to derive new value from media to media owners and new models for media acquisition and use for media consumers. Hence the awareness of and ability to use these specifications and technologies will be of great importance to future curators and publishers of online media.
- Session 1: Media fragment analysis and creation
Speaker: Vasileios Mezaris (CERTH)
Summary: Explain approaches to visual, audio and textual media analysis to automatically generate meaningful media fragments out of a media resource. Demonstrate latest results in the areas of video fragmentation, visual conceopt and event detection, face detection, object re-detection, and the use of speech recognition and keyword extraction from text for supporting multimedia analysis.
- Session 2: Media fragment specification and semantics
Speaker: Raphaël Troncy (EURECOM)
Summary: Introduce the W3C Media Fragment URI specification. Highlight how media fragments can be incorporated into known media description schema, with a focus on the W3C Media Ontology and the Open Annotation Model. Extensions to these ontologies to more richly link media fragments to the concepts they represent.
- Session 3: Media fragment re-mixing and playout
Speaker: Lyndon Nixon (MODUL)
Summary: A number of novel application ideas will be introduced based on the media fragment creation, specification and rights management technologies. Semantic search and retrieval allows us to organize sets of fragments by topical or conceptual relevance. These fragment sets can then be played out in a non-linear fashion to create a new media re-mix. We look at a server-client implementation supporting Media Fragments, before allowing the participants to take the sets of media they have selected and create their own re-mix.
Goals of the tutorial
Topics of interest include: Online video, audio and textual media analysis; Media annotation and semantic description; Multimedia search and retrieval; HTML5-based media fragment playout.
This tutorial will approach these topics, which often address media resources as atomic objects, from the viewpoint of media fragment re-use and re-mixing in different domains, and introduce ideas of novel applications of media fragment re-use and re-mixing based on such technologies. Hence we consider the subject of great importance to the online multimedia community to highlight the state of the art in addressing media at the fragment level and the new possibilities media fragment technology can introduce for media owners and consumers. The covered Web-based specifications and technologies are still very much at an “early adoption” stage, even within the research community let alone the commercial industry, so it is important to communicate their existence, explain their use and point to existing tools and services handling them. This is part of the goal of the MediaMixer project which supports this tutorial. We believe that by training Web media researchers in these specifications and technologies, they can better apply their use within their own research (helping make results more interchangable and interoperable too) and since many will move on to enter industry, we can also help bring awareness of these technologies into the online media industry.
Dr. Vasileios Mezaris received the Diploma and the Ph.D. degree in Electrical and Computer Engineering from the Aristotle University of Thessaloniki, Thessaloniki, Greece, in 2001 and 2005, respectively. He is a Senior Researcher (Researcher B) with the Information Technologies Institute / Centre for Research and Technology Hellas, Thessaloniki, Greece. His research interests include image and video analysis, event detection in multimedia, machine learning for multimedia analysis, content-based and semantic image and video retrieval, medical image analysis. He is the co-author of 26 papers in refereed international journals, 12 book chapters, two patents and more than 90 papers in international conferences. Since 2012 he also serves as an Associate Editor for the IEEE Transactions on Multimedia.More details and publications at http://www.iti.gr/~bmezaris/
Dr Nixon is Senior Researcher in the New Media Technology group at the MODUL University Vienna as of 1st October 2013. He is responsible for the EU projects LinkedTV (www.linkedtv.eu) – as Scientific Coordinator – and MediaMixer (www.mediamixer.eu) – as Project Coordinator. He also teaches (MBA) on Media Asset Management and Re-use. His research domain since 2001 is semantic technology and multimedia, with a focus on automated media interlinking, and he has co-authored 73 refereed papers and co-organised 31 workshops or conference tracks to date. More details and publications at https://sites.google.com/site/lyndonnixon/home
Assistant professor in EURECOM (Sophia Antipolis, France) leading the Multimedia Semantics research group. Raphaël Troncy is also co-chair of the W3C Media Fragments Working Group and W3C Incubator Group on Multimedia Semantics. He is involved in many National (ACAV, Datalift) and European (K-Space, Petamedia, ALIAS, LinkedTV, OpenSEM) projects dealing with multimedia analysis and semantic web technologies in social media. Raphaël Troncy is an expert in audio visual metadata and in combining existing metadata standards (such as MPEG-7) with current Semantic Web technologies. More details and publications at http://www.eurecom.fr/en/people/troncy-raphael