Keynote Speakers

Computer vision is a rich source of important yet intractable optimization problems. Over the past decade, researchers have shown that many such problems can be efficiently solved by graph cuts. Graph cut algorithms combine elegant theoretical properties with compelling experimental results. I will focus on the difficult but important challenge of solving rank-deficient linear inverse systems. Such systems arise in many important image-processing applications, and can be solved with convex optimization methods by assuming the output should be globally smooth. More realistic assumptions, such as piecewise smoothness, lead to intractable optimization problems. I will present some preliminary evidence that graph cuts can be effective for an important class of linear inverse systems. This is joint work with several collaborators, but primarily Ashish Raj (Cornell).

Ramin Zabih is Professor of Computer Science and Radiology at Cornell University, where he has twice received teaching awards. He earned B.S. and M.S. degrees from MIT, and his Ph.D. degree from Stanford University. Since 2001 he has also held a joint appointment at Cornell's Weill Medical School. His research interests lie in early vision and its applications, especially in medicine. He is best known for his work on the use of graph cuts for computer vision. Two of his papers with Vladimir Kolmogorov on this topic received Best Paper awards at the European Conference on Computer Vision in 2002. He served as program co-chair for the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) in 2007, and has been an area chair or program committee member for most of the main vision conferences for the past decade. He has been an associate editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence since 2005, and beginning in 2009 will serve as its editor-in-chief.

We address the problem of large scale image search, for which many recent methods use a bag-of-features image representation. We shows the sub-optimality of such a representation for matching descriptors and derive a more precise representation based on 1) Hamming embedding (HE) and 2) weak geometric consistency constraints (WGC). HE provides binary signatures that refine the matching based on visual words. WGC filters matching descriptors that are not consistent in terms of angle and scale. HE and WGC are integrated within an inverted file system and are efficiently exploited even in the case of very large datasets. Experiments performed on a dataset of one million images show a significant improvement due to the binary signatures and the weak geometric consistency constraints, as well as their efficiency. Estimation of the full geometric transformation, i.e., a re-ranking step on a short list of images, is complementary to our weak geometric consistency constraints and allows to further improve the accuracy. This is joint work with H. Jegou and M. Douze.

Cordelia Schmid holds a M.S. degree in Computer Science from the University of Karlsruhe and a Doctorate, also in Computer Science, from the Institut National Polytechnique de Grenoble (INPG). Her doctoral thesis on "Local Greyvalue Invariants for Image Matching and Retrieval" received the best thesis award from INPG in 1996. She received the Habilitation degree in 2001 for her thesis entitled "From Image Matching to Learning Visual Models". Dr. Schmid was a post-doctoral research assistant in the Robotics Research Group of Oxford University in 1996-1997. Since 1997 she has held a permanent research position at INRIA Rhône-Alpes, where she is a research director and directs the INRIA team called LEAR for LEArning and Recognition in Vision. Dr. Schmid is the author of over eighty technical publications. She has been an Associate Editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence (2001-2005) and for the International Journal of Computer Vision (2004-), and she was program chair of the 2005 IEEE Conference on Computer Vision and Pattern Recognition. In 2006, she was awarded the Longuet-Higgins prize for fundamental contributions in computer vision that have withstood the test of time. She is a senior member of IEEE.