Seminar Announcement
Vision, Brain, Computation and Attention: What You Really Need to Know
Dr. John Tsotsos of York University
Wednesday, February 14, 2018 · 1:00PM · HEC 101
Abstract
The Selective Tuning model for vision and attention, under development since 1987, started life as a
model of some aspects of visual attention in humans that might have utility in machine vision,
especially as it applies to how algorithms deal with the combinatorics of visual processing. It has
expanded over the years to include many elements of vision and visual cognition beyond attention,
directly relevant to both theories of human perception as well as to machine vision. I will briefly
describe the model and discuss its place within the large space of theories of vision as well as its
relevance to computer vision. Selective Tuning was conceived through the application of the classic
scientific method and the reasons why this approach remains as relevant as ever, even in this age of
data-driven solutions, will be examined. I will also overview the new evidence we have recently
discovered that supports critical predictions of the model. These findings point towards a very
different conceptualization of visual processing than the current accepted wisdom. Specifically, they
argue for vision as an active process, one that achieves its generalization to the enormous breadth of
possible scenarios by dynamically selecting what to sense and tuning its architecture and processing
for the task and input of the moment.
Biography
John Tsotsos is Distinguished Research Professor of Vision Science at York University. He received his
doctorate in Computer Science from the University of Toronto. After a postdoctoral fellowship in
Cardiology at Toronto General Hospital, he joined the University of Toronto on faculty in Computer
Science and in Medicine. In 1980 he founded the Computer Vision Group at the University of Toronto,
which he led for 20 years. He was recruited to York University in 2000 as Director of the Centre for
Vision Research. He has been a Canadian Heart Foundation Research Scholar, Fellow of the Canadian
Institute for Advanced Research, Canada Research Chair in Computational Vision and is an IEEE Fellow.
He received many awards and honours including several best paper awards, the 2006 Canadian Image
Processing and Pattern Recognition Society Award for Research Excellence and Service, the 1st
President's Research Excellence Award by York University in 2009, and the 2011 Geoffrey J. Burton
Memorial Lectureship from the United Kingdom's Applied Vision Association for significant contribution
to vision science. He was elected as Fellow of the Royal Society of Canada in 2010 and was awarded its
2015 Sir John William Dawson Medal for sustained excellence in multidisciplinary research, the first
computer scientist to be so honoured. His current research focuses on a comprehensive theory of visual
attention in humans. A practical outlet for this theory embodies elements of the theory into the vision
systems of mobile robots.
