Professor Song-Chun Zhu, UCLA
Song-Chum Zhu is a professor of Statistics and Computer Science at UCLA. His research interest includes Computer Vision, Laerning, the Interest of Vision and Arts. He received a B.S. degree from University of Science and Tehnology of China, 1991, MS. and Ph.D degrees from Harvard University in 1944 and 1996respectively (Ph.D. Advisor was Dr. David Mumford). He worked at Brown University, Stanford University, and Ohio State University before joining UCLA in 2002. He has co-authored more than 100 peer reviewed papers in computer vision, and received academic recognition including a David Marr Prize in 2003 for image parsing, twice Marr Prize honorary nominations in 1999 for texture modeling and 2007 for learning deformable templates. He is also a recipient of NSF Career award. ONR young investigator award. SloanResearch Fellow. In 2005, he founded an independent and non-profit organization - the Lotus Hill Research Institute in China as an open platform for international collaborations.
Statistical Modeling and Computing
Cognition and AI
Links to some Conferences / Workshops / Summer Schools that I am involved
Computer Vision and Pattern Recognition, Providence, Rhode Island, CVPR 2012
Int'l Workshop on Stochastic Image Grammar (SIG):
.... SIG workshop, with cvpr 2009 .... SIG workshop with iccv 2011 ... SIG tutorial with cvpr 2012
Summer Schools on Vision and Learning in China:
.... Lotus Hill 2005 .....Lotus Hill 2006 .... Lotus Hill 2008 .... Xi'an 2010
Symposium on Vision/Neural/Cognitive Science in Honor of David Mumford, 2007
6th Int'l Conference on EMMCVPR, 2007
Int'l Workshops on Statistical and Computational Theories of Vision (SCTV):
.... 1st SCTV, Fort Collins 1999, .... 2nd SCTV, Vancouver 2001 .... 3rd SCTV, Nice, France, 2003
*The photo was taken by photographer Reed Hutchinson, with oil style rendering by our software. A hi-res picture
reveals the brush strokes.
Song-Chun Zhu: Information Scaling and Perceptual Transitions in Natural Images and Video
Talk by Song-Chun Zhu of UCLA. Given to the Redwood Center for Theoretical Neuroscience at UC Berkeley on November 12, 2009.
Images and video are very high dimensional signals that reside in a wide spectrum of manifolds/subspaces of varying dimensions. In this talk, I will discuss two types of pure manifolds:
(i) implicit manifolds for high entropy patterns, like textures, modeled by Markov random fields, and
(ii) explicit manifolds for low entropy patterns, like textons and primitives, modeled by sparse coding.
I will show that these manifolds are connected through scaling (zooming), and present a unifying theory for learning probabilistic models by manifold pursuit through information projection. Then I will discuss how these manifolds are mixed to form middle entropy patterns, such as object templates, and integrated to generate a primal sketch representation for generic images as conjectured by David Marr in his influential book.
I will also show ongoing work on video primal sketch which integrates trackable motion, intrackable motion, and human actions.
Song-Chun Zhu received his BS degree from Univ. of Sci.& Tech. of China in 1991 and a PhD degree from Harvard University in 1996. He is a professor of Statistics and Computer Science at UCLA, and director of the Center for Vision, Learning, Cognition and Arts (VCLA@UCLA). His research interests include computer vision, statistical modeling and learning, cognition, and visual arts. He has received a number of honors, including the J.K. Aggarwal prize from the Intl Association of Pattern Recognition in 2008 for “contributions to a unified foundation for visual pattern conceptualization, modeling, learning, and inference”, the David Marr Prize in 2003 with Z. Tu et al. for image parsing, the Marr Prize honorary nominations i n 1999 for texture modeling and 2007 for object modeling with Y. Wu et al., a Sloan Fellowship in Computer Science in 2001, an NSF Career Award in 2001, and an ONR Young Investigator Award in 2001. He is a Fellow of IEEE.