Top Scientists to Give Keynote Addresses at IEEE Computer Vision and Pattern Recognition Conference

LOS ALAMITOS, Calif., 2 June 2015 — The 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) will be held at the Hynes Convention Center in Boston, Massachusetts on June 7–12th, 2015, drawing over 1900 attendees from around the world. The annual CVPR event comprises the main conference, several co-located workshops and short courses, and includes leading keynote speakers and technology demonstrations.

Co-sponsored by IEEE Computer Society, CVPR 2015 is the premier conference for computer scientists and engineers engaged in the discovery and development of computer vision algorithms. These algorithms include automated recognition of objects and humans, motion tracking, video analysis, robot vision, computational photography, three-dimensional scene reconstruction and biometrics. Innovative applications of the work include: human/computer interactive devices, monitoring and surveillance, biomedical devices, advanced manufacturing, art analysis and archiving, smart cars and intelligent highways.

The conference is a showcase for the great strides that computer vision has made in recent years and its direct value to companies like Google, Amazon, Microsoft, Apple, many startups and government agencies.  Each year, industry involvement in CVPR rises dramatically and the conference includes exhibits from companies showing the latest commercial products.

Top scientists in the field will give keynote addresses: Professor Yann Lecun of Facebook AI Research and New York University will give a plenary talk on “What’s Wrong with Deep Learning?”, and  Professor Jack Gallant from the University of California at Berkeley will discuss “Reverse Engineering the Human Visual System.”  The workshop keynote speakers include: Marc Pollefeys (ETH Zurich), Kyros Kutulakos (University of Toronto), Guna Seetharaman (Air Force Research Laboratory),  Margrit Betke (Boston University), John M. Irvine, (Charles Stark Draper Laboratory), Aswin Sankaranarayanan (Carnegie Mellon University), and Jason J. Corso (University of Michigan).

The conference includes technology demonstrations from research groups presenting their latest systems in an interactive forum. Demonstrations include titles such as “Privacy Preserving Vision Sensors,” “Translating Videos to Natural Language,” and “Patient Activity Recognition in a Hospital Room Using Kinect V2.” Tutorial titles include “Computer Vision for Visual Effects,” “ImageNet Large Scale Visual Recognition Challenge Tutorial,” “Applied Deep Learning for Computer Vision with Torch,” and “Applied Math as Applied in Cinema.”

The main CVPR conference will take place June 8–10, 2015. Workshops and tutorials will be held on June 7 and June 11-12. For further information about the conference or press passes, please contact the conference organizer Nicole Finn ( or the publicity chair Kristin Dana (