A Computational Perspective on Visual Attention
The derivation, exposition, and justification of the Selective Tuning model of vision and 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 on the book's Web site.
1100660353
A Computational Perspective on Visual Attention
The derivation, exposition, and justification of the Selective Tuning model of vision and 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 on the book's Web site.
50.0 In Stock
A Computational Perspective on Visual Attention

A Computational Perspective on Visual Attention

by John K. Tsotsos
A Computational Perspective on Visual Attention

A Computational Perspective on Visual Attention

by John K. Tsotsos

Paperback

$50.00 
  • SHIP THIS ITEM
    In stock. Ships in 1-2 days.
  • PICK UP IN STORE

    Your local store may have stock of this item.

Related collections and offers


Overview

The derivation, exposition, and justification of the Selective Tuning model of vision and 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 on the book's Web site.

Product Details

ISBN-13: 9780262543804
Publisher: MIT Press
Publication date: 06/22/2021
Pages: 328
Product dimensions: 7.00(w) x 9.00(h) x (d)

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).

Table of Contents

Preface xi

Acknowledgments xv

1 Attention-We All Know What It Is 1

But Do We Really? 1

Moving Toward a Computational Viewpoint 7

What Is Attention? 10

2 Computational Foundations 11

Attempting to Understand Visual Processing Capacity 11

The Language of Computation 14

Capacity Limits and Computational Complexity 16

Human Perception/Cognition and Computation 18

The Computational Complexity of Vision 21

Extending to Active Vision 29

Extending to Cognition and Action 32

Extending to Sensor Planning 32

Complexity Constrains Visual Processing Architecture 33

The Problems with Pyramids 38

Attention Is. … 51

3 Theories and Models of Visual Attention 53

The Elements of Visual Attention 54

A Taxonomy of Models 59

Other Relevant Ideas 75

Summary 78

4 Selective Tuning: Overview 81

The Basic Model 82

Saliency and Its Role in ST 86

Selective Tuning with Fixation Control 88

Differences with Other Models 93

Summary 96

5 Selective Tuning: Formulation 97

Objective 97

Representations 98

Neurons and Circuits for Selective Tuning 106

Selection 114

Competition to Represent a Stimulus 121

More on Top-Down Tracing 122

Inhibition of Return 124

Peripheral Priority Map Computation 124

Fixation History Map Maintenance 125

Task Guidance 126

Comparisons with Other Models 127

Summary 131

6 Attention, Recognition, and Binding 133

What Is Recognition? 134

What Is Visual Feature Binding? 139

Four Binding Processes 141

Binding Decision Process 145

Putting It All Together 146

Summary 149

7 Selective Tuning: Examples and Performance 151

P-Lattice Representation of Visual Motion Information 151

Priming 153

Results After a Single Feed-Forward Pass (Convergence Binding) 160

Results from a Single Feed-Forward Pass Followed by a Single Recurrent Pass (Full Recurrence Binding) 164

Attending to Multiple Stimuli (Type I Iterative Recurrence Binding) 166

Empirical Performance of Recurrence Binding (Localization) 168

Visual Search 174

Type II Iterative Recurrence Binding 186

Saliency and AIM 187

Summary 190

8 Explanations and Predictions 193

Explanations 195

Predictions with Experimental Support 205

Some Supporting Experiments 211

Summary 231

9 Wrapping Up the Loose Ends 233

The Loose Ends 236

Vision as Dynamic Tuning of a General-Purpose Processor 247

Final Words 248

Appendixes 251

A A Few Notes on Some Relevant Aspects of Complexity Theory 251

B Proofs of the Complexity of Visual Match 255

C The Representation of Visual Motion Processes 265

References 275

Author Index 297

Subject Index 305

What People are Saying About This

Jeffrey D. Schall

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.

Jeremy M. Wolfe

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.

Endorsement

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

From the Publisher

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

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

From the B&N Reads Blog

Customer Reviews