About lyndon.nixon@sti2.org

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 http://mklab.iti.gr/project/video-shot-segm), 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 http://youtu.be/FLTRZu-V97I

 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 shotsegmentation@iti.gr(please remember to mention your full name and university / company affiliation!)

CERTH just publicly released version 1.2 of its software for the automatic temporal segmentation of videos. This extends the previous versions by integrating algorithms for video scene segmentation and keyframe selection (up to 5 most representative keyframes of each scene are identified), on top of the segmentation to shots that is also performed by the released software. The new algorithmic additions do not affect the processing speed, which remains at least 2-3 times faster than real-time processing (depending on the processing capability of the graphics card) for the entire video analysis chain (i.e., shot segmentation, scene segmentation and keyframe selection).

The development and release of this software was supported by EU research projects LinkedTV (http://www.linkedtv.eu/) and MediaMixer (http://www.mediamixer.eu/).

The software is available for download at http://mklab.iti.gr/project/video-shot-segm

Related technical papers:

– E. Apostolidis, V. Mezaris, “Fast Shot Segmentation Combining Global and Local Visual Descriptors”, Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 2014. (available at http://www.iti.gr/~bmezaris/publications/icassp14_preprint.pdf)

– P. Sidiropoulos, V. Mezaris, I. Kompatsiaris, H. Meinedo, M. Bugalho, I. Trancoso, “Temporal video segmentation to scenes using high-level audiovisual features”, IEEE Transactions on Circuits and Systems for Video Technology, vol. 21, no. 8, pp. 1163-1177, August 2011. (available at http://www.iti.gr/~bmezaris/publications/csvt11_preprint.pdf)

Related demos:



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 http://mediamixer.eu/contact. 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 https://www.youtube.com/watch?v=McAlxWtXabE 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 http://mediamixer.eu/live/.


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 http://community.mediamixer.eu/documents/coretechnologyset/

Then our January Winter School featured hour long talks on media analysis, annotation and rights management which were recorded and are available at http://videolectures.net/wmpa2014_dublin/

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 http://mediamixer.eu/tutorial.


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 http://mediamixer.eu/innovate/


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!

Bookmark http://community.mediamixer.eu

In April 2014, MediaMixer gave a tutorial on “Remixing Media on the Web” at the World Wide Web Conference 2014 (WWW2014). The tutorial addressed 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. All slides from the tutorial are now available at the tutorial webpage.


The final Webinar of MediaMixer on the topic of “MediaMixer for e-learning: the VideoLecturesMashup” is now available at http://videolectures.net/mediamixer_zdolsek_videolectures_mashup/. 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 http://mediamixer.eu/live

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 http://mediamixer.eu/live

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 http://videolectures.net/mediamixer_media_fricke/

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 http://mediamixer.eu/live 

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

Firstly, an acknowledgement that we successfully held our Winter School on Multimedia Processing and Applications at the beginning of this year co-located with the MMM2014 conference in Dublin. 30 international attendees, mostly PhDs and young researchers, were present for a set of technology centred presentations by MediaMixer experts and industry centred presentations by research project leaders in areas such as broadcasting, digital preservation and the Internet of Things.

The student Siriwat Kasamwattanarote from the National Institute of Informatics, Tokyo, Japan won the school Best Poster award for work done on “Tell me about TV commercials of this product”.

The Winter School talks covered the latest technological developments in the area of multimedia processing (media analysis, media annotation, media rights management) and of emerging multimedia applications (in the Sensor Web, audiovisual archives, TV broadcasting, digital preservation and e-learning domains). We didn’t want to keep this purely for the 30 attending students, so now all of the talks are published online courtesy of VideoLectures.NET: