MediaMixer partner CERTH would like to announce the availability of our new on-line video analysis service. This is a REST service that receives the URL of a video and automatically performs temporal segmentation of it to shots and scenes, and annotation of each shot with concepts from our sample concept pool (comprising a few hundred concepts). The entire analysis process is several times faster than real-time. This service uses our fast video shot and scene segmentation software (a restricted version of this software can be downloaded from, together with our latest edition of concept-based video annotation software.

 A short video, demonstrating the use of our new video analysis service, can be found at

 You can ask for free access to this service for testing purposes (i.e., for limited time and a limited number of videos), by sending an email to remember to mention your full name and university / company affiliation!)

The MediaMixer project ended at the close of April 2014! The goal has always been to support industry and academia in understanding and taking up innovative multimedia technology – for media analysis, semantic annotation, rights management and media fragments. We hope you too found some benefit in the past months from our communications and content.

However, it is certainly not the end of MediaMixer’s benefits for you and your organisation since all materials, presentations and videos created by MediaMixer have been collected and are on line. We hope this will form an useful and valuable collection for you and your colleagues now and in the future.

We remain keen to hear your feedback and suggestions for our online materials, and you can contact us at any time via the form at MediaMixer remains at your service! We will continue to tweet from @project_mmixer about events and materials of MediaMixer relevance, so that you can continue to explore media mixing for your research or your business.


Sometimes it’s difficult to know where to start: well, how about ONE MINUTE of your time if you still need a brief summary of what MediaMixer is all about? Just click over to and 69 seconds later we trust you are better informed!

Next up is short explanations of each technology and use case. That’s why we recorded the MediaMixer Webinars! Firstly, coordinator Lyndon Nixon grounds the reason for MediaMixer. Then our technical partners describe the technologies that make it possible. Finally, our use case partners give short insights into the benefits for their domains that MediaMixer technology enabled. All in anything from 17 to 68 minutes, and at


MediaMixer technologies cover media analysis, annotation, fragmentation, rights management and re-use. Our experts share their knowledge about these technologies in several forms for you. Firstly, our final Core Technology Report provides a definitive summary of each technology area in one chapter and recommends tools and services you can start with today. Get the PDF FREE at

Then our January Winter School featured hour long talks on media analysis, annotation and rights management which were recorded and are available at

Last and not least, our April Tutorial at the World Wide Web Conference (WWW2014) covered the three key pillars of analysis, annotation and re-use. Our slides are at


Technology is a means to an end, and that end is bringing benefits to business and solving organizational problems. MediaMixer worked with several industry domains to produce use cases and demonstrators, which focused on the areas of media owners (copyright management), media producers (TV newsrooms) and media distributors (e-learning video platform).

The Use Case white papers, videos and demos provide all you need to know about MediaMixer technology benefits for each domain:


MediaMixer addressed wider application to industry uptake in the form of facilitating knowledge and technology transfer through an Innovation Day in April in London. The event brought together MediaMixer events with key industry representatives (among others: FOCAL, Getty Images, Pearson, Sound and Vision) from media archives and producers. Panel discussions and lightning talks focused on the barriers to uptake of innovative multimedia technology from the industry perspective, but also revealed how the industry is recognizing future challenges through digitisation and sharing of online media bring the need for new technological solutions. All the presentations and post-event video interviews are available alongside a summary of the event at


If that all wasn’t enough… well, our Community Portal will remain the one-stop-shop for all your MediaMixer needs! Find collected onto dedicated pages all the information about our use cases and technologies as well as tables of all our materials and showcases, and the best thing: FROM NOW ALL CONTENT IS PUBLIC AND FREE TO ACCESS!


The final Webinar of MediaMixer on the topic of “MediaMixer for e-learning: the VideoLecturesMashup” is now available at Tanja Zdolšek of the Jožef Stefan Institute highlights the MediaMixer benefits for the e-learning video platform VideoLectures.NET.

The ‘VideoLecturesMashup’ is capable of accepting a specific learning topic as input and produces as a result a mashup of fragments of learning materials from the site addressing that topic, ordered in a meaningful way. The mashup is specifically addressable and hence bookmarkable/saveable for subsequent reference and viewing. The talk reflects on the new learning opportunities realised for online learners as a result of the MediaMixer technology.

All MediaMixer Webinars are listed at

MediaMixer is pleased to initiate again in 2014 an ACM Multimedia 2014 Grand Challenge on the topic of Temporal segmentation and annotation of lecture videos. This follows on from the successful challenge in 2013.

The challenge is driven by the fact that VideoLectures.NET mostly hosts lectures 1 to 1.5 h long linked with slides and enriched with transcripts, metadata and additional textual contents. With automatic temporal segmentation and annotation of the video fragments, the VideoLectures.NET portal would gain in efficiency of the video search engine and would be able to provide users with the option to search for sections within a video, as well as would be able to recommend similar content to its users. This year the challenge again requires challenge participants to develop tools for the automatic segmentation and annotation of videos that could then be implemented in VideoLectures.NET. Extending lest year’s challenge definition and evaluation methodology, this year we will provide the challenge participants not only with a set of lecture videos and associated multimedia materials (e.g. slides, transcripts) but also with ground truth temporal segmenatation of the videos; the challenge participants will be asked to also report results against this ground truth. The ground truth data will be generated via crowdsourcing, which will be organized in advance by the challenge organizers.

Submission deadline is June 29, 2014. Contact the Grand Challenge organisers now to participate! 

MediaMixer is pleased to invite you to attend the MEDIAMIXER INNOVATION DAY AT THE INNOVATION THROUGH KNOWLEDGE TRANSFER 2014 EVENT, LONDON (UK), APRIL 4 2014. This short one day event will:

  • present case studies in the new challenges and possibilities emerging from an online, annotated and shared media ecosystem
  • highlight success stories of companies benefiting from knowledge transfer of cutting edge technology
  • help media companies  better understand the innovations in multimedia solutions that are emerging and relevant to their media systems and workflows as they face the challenge of media scales, complexity and disruptions in the classical media value chains
  • give you the opportunity to meet MediaMixer experts who are at the event to guide discussions and are available for one-to-one meetings after the presentation sessions

Event schedule and confirmed contributors are listed at the Innovation Day website.

Registration covers the whole InKT14 event including conference dinner! InnovationKT 2014 is an international conference focussing on innovation, entrepreneurship and knowledge transfer between research organisations and businesses.

The next Webinar has been confirmed to take place LIVE on March 31, 1330 CET. Tanja Zdolsek of JSI will talk about the VideoLecturesMashup demonstrator implemented in the MediaMixer project.

The ‘VideoLecturesMashup’ is capable of accepting a specific learning topic as input and produces as a result a mashup of fragments of learning materials from the site addressing that topic, ordered in a meaningful way. The mashup is specifically addressable and hence bookmarkable/saveable for subsequent reference and viewing. The talk will reflect on the new learning opportunities realised for online learners as a result of the MediaMixer technology and the benefits for the e-learning video platform VideoLectures.NET

All Webinars are broadcast live at

Rolf Fricke (CONDAT) held a Webinar on ‘Media Fragment Re-use as a Benefit: a use case in the newsroom’. He presented a solution for a Broadcast Newsroom which gives support to news editors by recommending video snippets from heterogeneous footage related to the current working focus. The presentation is now online at

Roberto Garcia (U Lleida) held a Webinar on ‘Semantic Management of your Media Fragments Rights’. He presented how semantic technologies make it possible to go beyond Digital Rights Management and, because it is possible to model copyright through the whole media value chain, manage media rights from creation or remix to end-user consumption.

The presentation is now accessible:

All our Webinars are available via 

The next Webinar will be March 31st at 1330 CET!

MediaMixer will show its solution for online video lectures during OCW Global (23-25 April 2014, Ljubljana, The conference schedule has now been published, and there will be two chances to see MediaMixer, the first focused more on the technology and the second more on the use case:

Mediamixer – Community set-up and networking for the reMIXing of online MEDIA fragments

  • Apr 23 @ 2:00 pm – 2:40 pm
  • Dissemination track
  • Silver room

Video Lectures Mashup – remixing learning materials for topic-centred learning across collections (Lyndon Nixon, Tanja Zdolsek, Ana Fabjan and Peter Kese)

  • Apr 24 @ 5:30 pm – 6:00 pm
  • Research and Technology
  • White room 1

Early registration is available until 15 Feb at

Happy New Year from project MediaMixer! Next week is also the next Webinar, on January 14th (2pm CET) our use case partners will present their use of MediaMixer technology: a Semantic Newsroom enables the news editor to access on demand relevant video snippets around the in-focus news story, while VideoLecturesMashup is capable of accepting a specific learning topic as input and produces as a result a mashup of fragments of learning materials from the site addressing that topic, ordered in a meaningful way. The talk will reflect on the new learning opportunities realised for online learners as a result of the MediaMixer technology. All Webinars are broadcast live at and available afterwards courtesy of VideoLectures.NET (

MediaMixer is pleased to announce its tutorial on “re-using media on the Web” has been accepted for the program of the World Wide Web Conference 2014, taking place in Seoul, Korea in April 7-11 2014.

This will be an opportunity for Web developers and media professionals to receive direct, hands-on experience in using MediaMixer technologies  to annotate and interlink online media fragments to support new applications.

Register now to ensure your place. Full registration (with conference) or discounted registration (for workshops and tutorials only) options are available.


Topic and description of the tutorial

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.

Alone the need to raise the visibility of these individual Web-based specifications and technologies,
part of the remit of the MediaMixer project which will support this tutorial, would motivate the
tutorial for researchers and practitioners in the multimedia domain: the W3C Media Fragment
specification offers a chance to have a standard URL-based expression for media fragments across
the Web, the W3C Media Ontology and Open Annotation Models with their fragment re-use
specific extensions in projects like LinkedTV offer the possibility of interchangable and machine
reusable semantic media descriptions across repositories, , support for media fragments and the
related specifications needs to be built into multimedia search and retrieval systems and HTML5-
based media playout technology with the first early adopters being visible. On top of this, 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.

Intended audience

The target audience is researchers from the different areas of Web multimedia research that deal
with the analysis, organization and indexing of online multimedia content, with an interest of being
enabled to better do so at fragment level, as well as developers of novel applications for the re-use
and re-mixing of media fragments which can be of benefit to media owners, providers and
consumers. The participants of the tutorial will gain an insight into the current state-of-the-art of
research on multimedia fragments and remixing. The participants will also have the opportunity to
hands-on use different tools for the purpose and create their own media re-mix.


Our tutorial is focused on intermediate skilled Web media researchers and professionals. It will
assume a basic knowledge in the principles around media analysis, annotation, management, search
and presentation but not assume the use of any specific technologies or standards.

Duration and program

We plan a half day tutorial of three one hour blocks plus breaks.

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 redetection,
and the use of speech recognition and keyword extraction from text for supporting
multimedia analysis.
Session 2: Media fragment specification and semantics
Speaker: Benoit Huet (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.


  • Vasileios Mezaris (CERTH-ITI)

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.

  • Benoit Huet (EURECOM)

Dr. Benoit Huet is Associate Professor in the multimedia information processing group of Eurecom
(France). He received his BSc degree in computer science and engineering from the Ecole
Superieure de Technologie Electrique (Groupe ESIEE, France) in 1992. He received his DPhil
degree in Computer Science from the University of York (UK) for his research on the topic of
object recognition from large databases. He was awarded the HDR (Habilitation to Direct
Research) from the University of Nice Sophia Antipolis, France in October 2012 on the topic of
Multimedia Content Understanding Bringing Context to Content. He is associate editor for
Multimedia Tools and Application (Springer), Multimedia Systems (Springer) and has been guest
editor for a number of special issues (EURASIP Journal on Image and Video Processing, IEEE
Multimedia). He regularly serves on the technical program committee of the top conference of the
field (ACM MMICMR, IEEE ICME). He is chairing the IEEE MMTC Interest Group on Visual
Analysis, Interaction and Content Management (VAIG). He is vice-chair of the IAPR Technical
Committee 14 Signal Analysis for Machine Intelligence.

  • Lyndon Nixon (MODUL University Vienna)

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 (
– as Scientific Coordinator – and MediaMixer ( – 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 coauthored 73 refereed papers and co-organised 31 workshops or conference tracks to date.