Our colleague Vasileios Mezaris (CERTH) will hold the next live Webinar on 14 November (1100 CET) at http://www.mediamixer.eu/live.  It is titled “Fragmenting your Media Assets meaningfully – media analysis for fragment detection and extraction“.

The Webinar will discuss a set of video processing techniques for media fragment creation and annotation. These include techniques for the temporal segmentation of the video into shots and scenes, the re-detection of appearances of specific objects throughout the video, and the detection of concepts that describe the temporal video fragments. Such techniques are the first step towards converting the raw video material into meaningful media fragments.

Join the live presentation and discuss with us via Twitter @project_mmixer. Webinars are also recorded and will be available online at http://mediamixer.eu/live later. MediaMixer community members receive regular mails reminding them of MediaMixer activities – join free at http://community.mediamixer.eu 


In today’s Grand Challenge session at ACM Multimedia 2013, two paper-solutions for the MediaMixer / VideoLectures.NET challenge on temporal segmentation of e-learning videos were presented:

1) MUST VIS system (IDIAP Switzerland) offers an appealing visualisation of video-to-video and segment-to-segment linking based on video analysis and tagging, and their associations. A first demo was presented which can be seen at http://portal.klewel.com/graph

2) The Hasso Platner Institute (HPI) presented a solution based purely on OCR analysis of the accompanying lecture slides, using common partners to provide for solutions for Global and Partial Segmentation of the video, being more accurate than the use of shot segmentation techniques relying on transitions between video frames. The slideset is available at http://www.yanghaojin.com/research/ACM-MM-GC-DEMO/

While the global Grand Challenge winners will be announced tonight, the MediaMixer project has already selected their Grand Challenge winner, and congratulates IDIAP Switzerland on an appealing visualisation of video fragment associations which can be of great usability value in our VideoLecturesMashup demonstrator. The authors win a chance to visit the VideoLectures team in Ljubljana, Slovenia and collaborate with us on a new version of VideoLecturesMashup!

 


MediaMixer is pleased to announce a Call for Multimedia Grand Challenge Solutions: Participate in the MediaMixer/VideoLectures.NET Temporal Segmentation and Annotation Grand Challenge, and win a trip to Ljubljana, Slovenia!

to be held at ACM Multimedia 2013, Barcelona, Spain, October 21-25, 2013

offical Grand Challenge page:
http://acmmm13.org/submissions/call-for-multimedia-grand-challenge-solutions/mediamixervideolectures-net-grand-challenge/

CHALLENGE DESCRIPTION
———————

VideoLectures.NET mostly hosts lectures 1 to 1.5h long linked with slides and enriched with metadata and additional textual contents. With automatic temporal segmentation and annotation of the video we would gain on efficiency of our video search engine and be able to provide users with the ability to search for sections within a video, as well as recommend similar content. This would mean that the challenge participants develop tools for automatic segmentation of videos that could then be implemented in VideoLectures.NET.

The criteria for the evaluation of the proposed solutions to this challenge include the quality of the segmentation and the annotations, the duration of the required processing in time, and the ease of integration of the proposed solutions into VideoLectures.NET.

A dataset of Videos from VideoLectures.NET will be provided. Participants are also free to use additional datasets for testing their approaches, in addition to the videos provided by the Challenge organizers.

SUBMISSIONS AND PUBLICATION OF RESULTS
————————————–
Submissions should depict working, presentable systems or demos, using the provided grand challenge dataset, and should describe why the system presents a novel and interesting solution.

The submissions (max 4 pages) should be formatted according to ACM Multimedia formatting guidelines. Multimedia Grand Challenge reviewing is Double-blind so authors shouldn’t reveal their identity in the paper. The finalists will be selected by a committee consisting of academia and industry representatives, based on novelty, presentation, scientific interest of the approach and performance against the task.

Finalist submissions will be published in the conference proceedings, and will be presented in a special event during the ACM Multimedia 2013 conference in Barcelona, Spain. At the conference, finalists will be requested to introduce their solutions, give a quick demo, and take questions from the judges and the audience. Winners will be selected for Multimedia Grand Challenge awards based on their presentation. An additional prize (sponsored by Technicolor) will be awarded to the most innovative multimodal solution, and a special MediaMixer prize will be awarded to the best solution presented for the MediaMixer/VideoLectures.NET Challenge.

IMPORTANT DATES
—————
Challenge Dataset: Already available!
Paper Submission Deadline: July 1, 2013
Notification of Acceptance: July 29, 2013
Camera-Ready Submission Deadline: August 12, 2013

SUBMIT AND WIN A TRIP TO LJUBLJANA
———————————-

MediaMixer is pleased to sponsor a prize for the Grand Challenge. The best solution – as determined by the evaluation criteria and subject to final decision by the challenge organizers – wins the submitting author(s) a trip to beautiful Ljubljana, Slovenia!

The winners are invited to visit the offices of VideoLecture.NET, meet the team over lunch and discuss how their solution may be integrated into the next release of the video portal. The rest of their stay they are free to explore Slovenia’s capital city.

The prize is reimbursement of flight and hotel costs for up to *2* persons (at least one of whom MUST be a named author of the winning paper) to Ljubljana, Slovenia. The flight taken must be in economy class and the hotel stay no more than 2 nights, and a maximum reimbursement amount of 1000€ can be claimed, subject to the provision of original receipts.

INTERESTED?
——–
The first step is to contact us, we will answer any questions you have and most importantly we can give you access to the MediaMixer/VideoLectures.NET Challenge dataset.
Tanja Zdolsek, tanja.zdolsek AT ijs.si
Vasileios Mezaris, bmezaris AT iti.gr