Workshop Home

Welcome to the 2012 KDD Mutimedia Data Mining (MDM) workshop homepage!

The workshop will bring together experts in the analysis of digital media content, multimedia databases, knowledge engineers and domain experts from different applied disciplines with potential in multimedia data mining.  A new theme of this edition of the workshop is to present and discuss how multimedia is integrated into people’s daily life. Since mobile devices have been the most popular platform for multimedia applications, and these applications are often enhanced with geographical locations, we want to focus this workshop on both mobile and geo applications and data mining.


For more information on KDD, please visit: http://www.kdd.org/kdd2012/


Updates:



Workshop at a Glance:


As evidenced by the success of the previous editions of MDM/KDD, there is an increasing interest in new techniques and tools that can detect and discover patterns, in multimedia data, that can lead to new knowledge. Big data and large scale analytics is a fundamental problem within computer science.  The accelerating data avalanche is gaining unimpeded momentum that is increasing the volume and variety of information.  Specifically, a growing and increasingly relevant component of today’s corpora of information is multimedia data.  Within the knowledge discovery and data mining community and as  evidenced  by  the  success  of  the  previous decade of  the Workshop,  there  is an  increasing  interest in  new techniques  and tools that can detect and discover patterns in multimedia data, that can  lead  to  new knowledge.  Multimedia information is ubiquitious, a digital capsule, deliverable, artful, and empirical.  An enabler for multimedia data and a new focus for the workshop examined content acquisition and delivery within mobile devices.  Consumer grade tablets, cell phones, and cameras provide affordable multimedia devices for sound, video, and image.  For example, in tablet computing, forward facing cameras capture video and images that can be edited for individual use and published to social media sites.  Business and events such as the 2011 Wimbledon, provide the science of tennis, scores, and statistics to mobile devices so that patrons can enjoy streaming updates of simultaneous matches.  Theme parks such as Walt Disney publish park information in the form of text, sound, video, and images that is accessible by mobile devices.

Of particular interest are ideas that relate to:
  • Emerging technology of data mining for mobile applications.
  • Emerging technology of data mining on media rich platforms and location enhanced environments (location based services like Foursquare, mobile maps, navigation systems, GIS applications).
  • Multimedia data mining across platforms, including web and mobile devices.
  • Mining large datasets of user generated content with a geographical dimension.
  • Scalable mobile multimedia computing.
  • Scalable mobile visual search.
  • Predictive and prescriptive multimedia data modeling.
  • Privacy preserving data mining.
  • Mining multimedia time series.
  • Multi-objective multimedia data mining.
  • Anomaly and outlier detection in multimedia databases.
  • Merging and integration of mining results from different sources (e.g, ensembles, fusion techniques, etc.).
  • Scalable data mining techniques for large-scale multimedia databases.
  • Human-computer interfaces for multimedia data mining.
  • Topic and event discovery in large multimedia repositories.


Important Dates:

  • Submissions Due (extended!): May 30, 2012 (Wednesday) May 22, 2012 (Tuesday) May 13, 2012 (Sunday) 
  • Acceptance Notification (postponed): June 13, 2012 June 8, 2012 (Friday) 
  • Camera-ready Due: June 13, 2012 (Wednesday)

Google Site Translator