What problems do Yahoo!, Microsoft, Huawei, Technicolor, NHK and Videolectures see in the future of multimedia? Try to address them by working with some of the largest multimedia collections available, including: hundred’s of thousands of training images per class for classification (Yahoo!), 1,000 video clips of raw broadcast video footage for beauty detection (NHK), 3D data of multi-view video streams, multiple humans and actions (Huawei/3DLife), 10.6 GB of training data for image retrieval (Microsoft), 17 hours of lecture videos and >1000 slides (MediaMixer/VideoLectures.NET) and TV archives (Technicolor).
The Multimedia Grand Challenge is a set of problems and issues from these industry leaders, geared to engage the multimedia research community in solving relevant, interesting and challenging questions about industry's current and future needs and applications for multimedia.
The Grand Challenge was first presented as part of ACM Multimedia 2009 and has established itself as a prestigious competition in the multimedia community. This year's conference will continue the tradition, with both ongoing and brand new challenges.
The 2013 Multimedia Grand Challenges are:
* NHK – Where is beauty? Grand Challenge
* Technicolor - Rich Multimedia Retrieval from Input Videos Grand Challenge
* Yahoo! – Large-scale Flickr-tag Image Classification Grand Challenge
* Huawei/3DLife - 3D Human Reconstruction and Action Recognition Grand Challenge
* MediaMixer/VideoLectures.NET - Semantic VideoLectures.NET Segmentation Service Grand Challenge
* MSR-Bing Grand Challenge on Image Retrieval
* Significantly address one of the challenges posted on the Grand Challenge web site.
* Depict working, presentable systems or demos, using the Grand Challenge dataset where provided.
* Describe why the system presents a novel and interesting solution.
The finalists will be selected by a committee consisting of academia and industry representatives, based on novelty, presentation and scientific interest of the approaches and, for the evaluation-based challenges, on the performance against the task.
Preference is given to results that are reproducible by the research community, e.g. where the data and the source code is made available publicly.
The finalists will be published in the proceedings and presented in a special event during the MM 2013 conference in Barcelona. Based on the presentation, winners will be selected for Grand Challenge awards. At the conference, authors of accepted submissions will introduce the idea to the audience, give a quick demo, and take difficult questions from the judges. Based on the presentation and the submission, a team of judges will select the top contributors.
DEADLINE: July 1st, 2013.
For more information and submission guidelines visit: