PristupačnostWelcome to the Center of Excellence for Computer Vision (CRV) at the University of Zagreb Faculty of Electrical Engineering and Computing. The center promotes collaboration between its members in the topics of computer vision and image understanding, pattern recognition and digital image processing and analysis.
Center of Excellence for Computer Vision (CRV)
A public lecture under title "Computer vision and visual recognition: Historical perspective and recent results" will be given by professor Jean Ponce, INRIA, NYU Center for Data Science.
The lecture will be on Friday, 9th November 2018 from 10:45-12:15 in Grey Hall of the Faculty of Electrical Engineering and Computing, University of Zagreb.
Professor Ponce is a distinguished researcher in the computer vision area and IEEE Fellow. During his career, he worked at top institutions including MIT, Stanford University, the University of Illinois at Urbana-Champaign and INRIA. He is a co-author of a well-known textbook "Computer Vision: A Modern Approach".
A lecture abstract and a short biography of professor Ponce are in the detailed news content. The lecture is organized in collaboration with the French Institute in Zagreb.
Title: Computer vision and visual recognition: A historical perspective and some recent developments
Abstract
The aim of computer vision is to automatically interpret the content of digital imagery, and one of its most important aspects is visual recognition ("is this the picture of a dog?", "what do the characters of the movie do in this shot?"). I will give a brief historical overview of the field and of recent achievements, notably obtained through the use of supervised machine learning techniques, which often given excellent results but require cumbersome and costly manual annotation. I will then focus on recent work aimed at minimizing the annotation effort with weakly supervised methods exploiting instead the metadata that often accompanies images and videos (such as the script and subtitles of films and tv series), and completely unsupervised methods that operate directly on images to discover their visual content.
Short Biography
Jean Ponce is a Research Director at Inria and a Visiting Researcher at the NYU Center for Data Science, on leave from Ecole normale supérieure (ENS) / PSL Research University, where he is a Professor, and served as Director of the Computer Science department from 2011 to 2017.
Dr. Ponce graduated in Mathematics from ENS Cachan in 1982. He received his "Doctorat de Troisieme cycle" (PhD degree) and his "Doctorat d'Etat" (Habilitation degree) in Computer Science in 1983 and 1988 from the University of Paris Sud Orsay. Before joining ENS and Inria, Jean Ponce held positions at MIT, Stanford, and the University of Illinois at Urbana-Champaign, where he was a Full Professor until 2005. Jean Ponce's research spans Computer Vision, Machine Learning, and Robotics. He is an IEEE Fellow and a Sr. Member of the Institut Universitaire de France. He served as editor-in-chief for the International Journal of Computer Vision from 2003 to 2008, and chaired the IEEE Conference on Computer Vision and Pattern Recognition in 1997 and 2000, and the European Conference on Computer Vision in 2008. Jean Ponce is the recipient of two US patents, an ERC Advanced Grant, and the 2016 IEEE CVPR Longuet-Higgins Prize. He is also the author of "Computer Vision: A Modern Approach", a textbook translated in Chinese, Japanese, and Russian, and he is (slowly) writing a new textbook, "Geometric Foundations of Computer Vision".