MM2012: The Multimedia Grand Challenge goes into its fourth year

MM2012: The Multimedia Grand Challenge goes into its fourth year

What problems do Google, HP, NHK, NTT, Technicolor, and other companies see driving the future of multimedia? The Multimedia Grand Challenge is a set of problems and issues from these industry leaders, geared to engage the Multimedia research community towards solving relevant, interesting, and challenging questions in the multimedia industry's 2-5 year horizon. The Grand Challenge was first presented as part of ACM Multimedia 2009 and in 2012 is having its fourth edition. Researchers are encouraged to submit working systems in response to these challenges to win the grand Challenge competition!

This year's challenges are partially continuation of earlier challenges so progress can be measured, while there are also a number of brand new challenges. The set of current challenges is as follows:

Google Challenge

Automatic Music Video Generation.

This challenge considers the automatic generation of cool and entertaining soundtracks for user-generated videos and automatic generation of interesting music videos.

3DLife / Huawei Challenge

Realistic Interaction In Online Virtual Environments.

This challenge calls for demonstrations of technologies that support real-time realistic interaction between humans in online virtual environments. A dataset related to a scenario in which an expert salsa teacher is performing over the Internet is provided. Motion data should be used to animate a realistic avatar of the teacher in an online virtual ballet studio.

HP challenge

Understanding the Emotional Impact of Images and Videos.

This challenge considers methods akin to the way professionals enhance the emotional value of imagery when creating websites, magazine covers, and printed advertisement with a special focus on understanding emotional impact and how this comes about.

NHK Challenge

Where is beauty? Video Segment Extraction Based on Aesthetic Quality Assessment.

This challenge asks for solutions to automatically recognize beautiful scenes in broadcast programs where the solution should both define beauty as well as providings the means to find it in video data.

NTT Docomo Challenge

Event Understanding through Social Media and its Text-Visual Summarization.

This challenge is seeking innovative techniques for data-mining on social media to retrieve, summarize, and visualize events for a selected topic such as a local event.

Technicolor Challenge

Audiovisual Recognition of Specific Events. 

This challenge aims at exploring tools to search multimedia databases based on audio-visual queries in non-professional environments with wildly unstructured repositories by exploiting and combining several information channels.

Submission and awards

We encourage you to consider the challenges and submit your contribution to the ACM Multimedia 2012 Grand Challenge track.

The submissions must:

• Significantly address one of the industry challenges posted on the Grand Challenge web site.
• Depict working, presentable systems or demos.
• Describe why the system presents a novel and interesting solution.

Submit contributions or solutions described in a 4-page paper to the ACM Multimedia 2012 Grand Challenge track by May 14 through https://cmt.research.microsoft.com/ACMMM2012/

A number of solutions will be selected as finalists and invited to describe their work, demonstrate their solution and argue for the paper's success in the Grand Challenge Session in Nara. Each finalist will have several minutes to present their case. This year, every finalist team will receive a cash award equivalent to one student registration fee. Final winner(s) will be chosen by industry scientists, engineers and business luminaries based on the presentations.

See you in Nara!