Professor Yi Ma of Shanghai Tech University was invited to give a talk on “Pursuit of Low-dimensional Structures in High-dimensional Data” in “Tsinghua Information Forum” on campus in the afternoon, September 12. It attracted nearly 100 students and researchers from School of Information Science and Technology, School of Medicine of Tsinghua, together with those from institutes of CAS.

In this talk, Professor Ma presented a big picture of a new class of models and techniques that can effectively model and extract rich low-dimensional structures in high-dimensional data such as images and videos. The results and tools he showed actually generalized to a large family of low-complexity structures with decomposable regularizers. He also illustrated how these new mathematical models and tools could bring disruptive changes to solutions to many challenging tasks in computer vision, image processing, and pattern recognition, as well as in web documents, image tags, microarray data, audio/music analysis, and graphical models processing.

Professor Ma received his Bachelors’ degree in Automation and Applied Mathematics from Tsinghua University (Beijing, China) in 1995, a Master of Science degree in EECS in 1997, a Master of Arts degree in Mathematics in 2000, and a PhD degree in EECS in 2000, all from the University of California at Berkeley. From 2000 to 2011, he was an Assistant and Associate Professor at the EECS, University of Illinois at Urbana-Champaign. From 2009 to early 2014, he was a Principal Researcher and the Research Manager of the Visual Computing group at Microsoft Research in Beijing. His main research interest is in computer vision, high-dimensional data analysis, and systems theory. He has been associate editors of several international journals such as IEEE T-PAMI, IEEE T-IT, IJCV, SIAM journal on Imaging Sciences etc. He served as a Program Chair for ICCV 2013 and will be a General Chair for ICCV 2015. He is a Fellow of IEEE.