A Computational Perspective on Visual Attention
Although William James declared in 1890, “Everyone knows what attention is,” today there are many different and sometimes opposing views on the subject. This fragmented theoretical landscape may be because most of the theories and models of attention offer explanations in natural language or in a pictorial manner rather than providing a quantitative and unambiguous statement of the theory. They focus on the manifestations of attention instead of its rationale. In this book, John Tsotsos develops a formal model of visual attention with the goal of providing a theoretical explanation for why humans (and animals) must have the capacity to attend. He takes a unique approach to the theory, using the full breadth of the language of computation--rather than simply the language of mathematics--as the formal means of description. The result, the Selective Tuning model of vision and attention, explains attentive behavior in humans and provides a foundation for building computer systems that see with human-like characteristics. The overarching conclusion is that human vision is based on a general purpose processor that can be dynamically tuned to the task and the scene viewed on a moment-by-moment basis.
Tsotsos offers a comprehensive, up-to-date overview of attention theories and models and a full description of the Selective Tuning model, confining the formal elements to two chapters and two appendixes. The text is accompanied by more than 100 illustrations in black and white and color; additional color illustrations and movies are available by clicking the Supplemental Content link in the navigation panel to the left.
About the Author
John K. Tsotsos is Professor of Computer Science and Engineering, Distinguished Research Professor of Vision Science, Canada Research Chair in Computational Vision at York University, and a Fellow of the Royal Society of Canada (FRSC).
"John Tsotsos manages to achieve the difficult task of striking a good balance between an extensive overview and greater depth given the interdisciplinary nature of the theme. This book is a must read for Ph.D students who are working in this area, as it explicitly states several open topics of research and even offers overt hints and methods to address them."—Cognitive Systems Research
“The algorithmic architecture of Tsotsos’ updated selective tuning model will have immediate appeal for computational neuroscientists...” — Thilo Womelsdorf, Trends in Cognitive Sciences
"This readable and scholarly book offers fresh insights for novices and experts alike. The author's Selective Tuning model of visual attention provides a framework that integrates the various expressions of visual attention and the biology of the visual system grounded in the logic of computation."
Jeffrey D. Schall, E. Bronson Ingram Professor of Neuroscience, Vanderbilt University, and Director, Vanderbilt Vision Research Center
"In addition to a giving us comprehensive presentation of John Tsotsos's important theory of visual attention, this book provides an excellent grounding in the fundamental issues, as seen from a rigorous, computational point of view."
Jeremy M. Wolfe, Professor of Ophthalmology and Radiology, Harvard Medical School, and Director, Visual Attention Lab, Brigham and Women's Hospital