School of
Information Technology and Electrical Engineering

Understanding User Context for Mobile Recommendation

Dr Tao Mei - Microsoft ResearchFri, 13/07/2012 - 15:00
Prof Heng Tao Shen

Mobile devices are becoming ubiquitous.  People use their phones as a personal concierge discovering and making decisions anywhere and anytime.  Understanding user intent on the go therefore becomes important for task completion on the phone.  While existing efforts have predominantly focused on understanding the explicit user intent expressed by a textual or voice query, in this talk we introduce recent advances for understanding user context for mobile recommendation.  In particular, we attempt to use geo-location and time as context signals to provide personalized entity recommendation on mobile devices.  The recommended entity types and entities are relevant to both users’ past behaviors and sensory context.  We show that the applications of this kind are effective to facilitate the exploration and discovery of surroundings for mobile users.


Tao Mei is a Researcher in Microsoft Research Asia.  His current research interests include multimedia information retrieval, computer vision, and multimedia applications such as search, advertising, social networking, and mobile applications.  He has published over 100 referred papers in these areas, and holds more than 30 filed or pending US applications.  He is the principle designer of the automatic video search system that achieved the best performance in the worldwide TRECVID evaluation in 2007. He received the Best Paper Awards in ACM Multimedia 2007 and 2009, the Best Demo Award in ACM Multimedia 2007, and the Best Poster Paper Award in IEEE MMSP 2008. His work on online advertising received Microsoft Research Technology Transfer Awards in 2010 and 2012.  Tao received the B.E. degree in automation and the Ph.D. degree in pattern recognition and intelligent systems from the University of Science and Technology of China, Hefei, in 2001 and 2006, respectively.

Seminar Type: 

ITEE Research Seminar