Leo Guibas: 2015 AI Workshop

 

Thursday April 30, 2015
Location: Fisher Conference Center, Arrillaga Alumni Center

"Networks of Shapes and Images"

Abstract:

We show how to build networks between visual data sets, such as images, videos, 3D scans, or 3D models that can be used to transport information between the data. In these networks, nodes are vector spaces of functions expressing useful properties of the data and edges are linear operators that can transfer functions, exploiting correspondencies and similarities between related data sets. The networks can be used in performing operations on individual data sets better, or in further assessing relationships between them, exploiting the "wisdom of the collection." Examples include entity extraction from images or videos, 3D segmentation, the propagation of annotations and labels among images/videos/3D models, variability analysis in a collection of shapes, etc. By creating societies of data sets and their associations in a globally consistent way, we enable a certain joint understanding of the data that provides the powers of abstraction, analogy, compression, error correction, and summarization. Ultimately, useful semantic structures simply emerge from these map networks, with little or no supervision.


Bio:

Leonidas Guibas obtained his Ph.D. from Stanford under the supervision of Donald Knuth. His main subsequent employers were Xerox PARC, DEC/SRC, MIT, and Stanford. He is currently the Paul Pigott Professor of Computer Science (and by courtesy, Electrical Engineering) at Stanford University. He heads the Geometric Computation group and is part of the Graphics Laboratory, the AI Laboratory, the Bio-X Program, and the Institute for Computational and Mathematical Engineering. Professor Guibas’ interests span geometric data analysis, computational geometry, geometric modeling, computer graphics, computer vision, robotics, ad hoc communication and sensor networks, and discrete algorithms. Some well-known past accomplishments include the analysis of double hashing, red-black trees, the quad-edge data structure, Voronoi-Delaunay algorithms, the Earth Mover’s distance, Kinetic Data Structures (KDS), Metropolis light transport, heat-kernel signatures, and functional maps. Professor Guibas is an ACM Fellow, an IEEE Fellow and winner of the ACM Allen Newell award.