K.S. Fu Prize Winner of 2014

Jitendra Malik

"For contributions to fundamental algorithms and their theoretical underpinnings in computer vision"

Title: The Three R’s of Computer Vision: Recognition, Reconstruction and Reorganization

Time: Plenary talk Monday 25 Aug. 9:30-10:30

Abstract
We have seen remarkable progress in computer vision in recent years thanks to a virtuous confluence of better algorithms and models, faster computers, and the availability of large datasets. I will argue that further progress on the classic computational problems of computational vision: recognition, reconstruction and re-organization requires us to study the interaction among these processes. For example, recognition is reciprocally linked to re-organization, with bottom-up grouping processes generating candidates, which can be classified using top down knowledge, following which the segmentations can be refined again. Recognition of 3D objects could benefit from a reconstruction of 3D structure, and 3D reconstruction can benefit from object category-specific priors. I will sketch recent projects at UC Berkeley such as R-CNN (regions with CNN features), MCG (multiscale combinatorial grouping), SDS (simultaneous recognition and segmentation), and instance-level segmentation on RGB-D images, that have achieved state-of-art results on benchmark problems. Publications may be found at http://www.eecs.berkeley.edu/Research/Projects/CS/vision/

Biography
Jitendra Malik received his Bachelors degree in EE from Indian Institute of Technology, Kanpur in 1980 and the PhD degree in CS from Stanford University in 1985. In January 1986, he joined UC Berkeley, where he is currently the Arthur J. Chick Professor in the Department of EECS. He is also on the faculty of the department of Bioengineering, and the Cognitive Science and Vision Science groups.

Jitendra Malik's research group has worked on computer vision, computational modeling of human vision, computer graphics and the analysis of biological images. Several well-known concepts and algorithms arose in this research, such as anisotropic diffusion, normalized cuts, high dynamic range imaging, and shape contexts. According to Google Scholar, nine of his papers have received more than a thousand citations each. He has graduated 33 PhD students, many of whom are prominent researchers in academia and industry. He is a Fellow of the IEEE and ACM and a member of the National Academy of Engineering and the American Academy of Arts and Sciences. At ICCV 2013, he received the IEEE PAMI-TC Distinguished Researcher Award in Computer Vision.