Social media sharing properties, such as Flickr, Facebook and PicasaWeb, host billions of images and video, which have been annotated and shared among friends, or published in groups that cover a specific topic of interest. The availability of this mass amount of multimedia data based on the annotations and feedback by users creates a number of opportunities and research challenges and as well as many exciting real-world applications. Unlike conventional multimedia data, social media contains much rich user-generated information, including social connections, multimodal content and descriptions, location and comments in various forms (ranking, votes, likes). Therefore, many approaches have been developed, which are able to handle and process such heterogeneous information towards resolving long-standing challenges, e.g. multimedia understanding or towards improving recommendation and personalization techniques.

This workshop will continue the series of successful Workshops on Social Media in 2009 and 2010 and form a platform for the continued discussion of the key research issues in social multimedia. The workshop seeks contributions on various aspects of social media including papers on related theory, methodology, algorithms and issues associated to social media content creation, modeling, manipulation, content analysis, information extraction, storage, search, learning and mining. While the workshop places emphasis on theoretical contributions, we also welcome papers describing interesting applications and demos.