Karen Spärck Jones lecture 2015

Automatic understanding of the visual world

Dr Cordelia Schmid

Artificial intelligence (AI) is the intelligence exhibited by machines or software. One of the central problems of AI research is machine perception, i.e. the ability to understand the visual world based on the input from sensors such as cameras. Computer vision is the area which analyzes visual input. A few selected sub-problems are facial recognition, object recognition and activity recognition.

In this talk, Dr Schmid will present recent progress in visual understanding, for the most part due to the design of robust visual representations and learned models capturing the variability of the visual world. Progress has resulted in technology for a variety of applications and a few such examples will be presented. The gap between human and machine performance is still enormous, and so future research necessary to reduce this gap will also be discussed.

Main lecture

Q&A

About the speaker

Since 1997 Dr Schmid has been the Research Director and Head of the LEAR (LEArning and Recognition in Vision) project team at INRIA Grenoble Rhone-Alpes; prior to this she was a postdoctoral research assistant in the Robotics Research Group of Oxford University between 1996 and 1997. In 2013 she was awarded a European Research Council advanced grant. In 2006 and 2014 she was awarded the Longuet-Higgins prize for fundamental contributions in computer vision that have withstood the test of time.

She holds an MSc degree in computer science from the University of Karlsruhe and a doctorate in computer science from the Institut National Polytechnique de Grenoble (INPG). Her doctoral thesis "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". The author of over a hundred technical publications and a Fellow of IEEE, she has been an Associate Editor for its journal Transactions on Pattern Analysis and Machine Intelligence (2001 to 2005) and for the International Journal of Computer Vision (2004 to 2012). Additionally, she has been Editor-in-Chief of the latter (2013 to the present); a program chair of IEEE’s CVPR conference (2005) and of the European Conference on Computer Vision (2012); as well as a general chair of IEEE CVPR 2015.