Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint

1. Front Matter

   PDF

2. Embodiment of Attention

   1. The Embodied Dynamics of Emotion, Appraisal and Attention

      • Robert Lowe, Carlos Herrera, Anthony Morse, Tom Ziemke

      Pages 1-20

   2. The Role of Attention in Creating a Cognitive System

      • John G. Taylor

      Pages 21-41

   3. The Influence of the Body and Action on Spatial Attention

      • Catherine L. Reed, John P. Garza, Ralph J. Roberts Jr.

      Pages 42-58

   4. Abstraction Level Regulation of Cognitive Processing Through Emotion-Based Attention Mechanisms

      • Luís Morgado, Graça Gaspar

      Pages 59-74

   5. Embodied Active Vision in Language Learning and Grounding

      • Chen Yu

      Pages 75-90

   6. Language Label Learning for Visual Concepts Discovered from Video Sequences

      • Prithwijit Guha, Amitabha Mukerjee

      Pages 91-105

3. Cognitive Control of Attention

   1. Learning to Attend — From Bottom-Up to Top-Down

      • Hector Jasso, Jochen Triesch

      Pages 106-122

   2. An Attentional System Combining Top-Down and Bottom-Up Influences

      • Babak Rasolzadeh, Alireza Tavakoli Targhi, Jan-Olof Eklundh

      Pages 123-140

   3. The Selective Attention for Identification Model (SAIM): Simulating Visual Search in Natural Colour Images

      • Dietmar Heinke, Andreas Backhaus, Yarou Sun, Glyn W. Humphreys

      Pages 141-154

   4. A Bayesian Approach to Attention Control and Concept Abstraction

      • Saied Haidarian Shahri, Majid Nili Ahmadabadi

      Pages 155-170

4. Modeling of Saliency and Visual Search

   1. An Information Theoretic Model of Saliency and Visual Search

      • Neil D. B. Bruce, John K. Tsotsos

      Pages 171-183

   2. An Experimental Comparison of Three Guiding Principles for the Detection of Salient Image Locations: Stability, Complexity, and Discrimination

      • Dashan Gao, Nuno Vasconcelos

      Pages 184-197

   3. A Proto-object Based Visual Attention Model

      • Francesco Orabona, Giorgio Metta, Giulio Sandini

      Pages 198-215

   4. Context Driven Focus of Attention for Object Detection

      • Roland Perko, Aleš Leonardis

      Pages 216-233

   5. Color Saliency and Inhibition Using Static and Dynamic Scenes in Region Based Visual Attention

      • Muhammad Zaheer Aziz, Bärbel Mertsching

      Pages 234-250

   6. I See What You See: Eye Movements in Real-World Scenes Are Affected by Perceived Direction of Gaze

      • Monica S. Castelhano, Mareike Wieth, John M. Henderson

      Pages 251-262

5. Sequential Attention

   1. Selective Attention in the Learning of Viewpoint and Position Invariance

      • Muhua Li, James J. Clark

      Pages 263-276

   2. Generating Sequence of Eye Fixations Using Decision-Theoretic Attention Model

      • Erdan Gu, Jingbin Wang, Norman I. Badler

      Pages 277-292

   3. Reinforcement Learning for Decision Making in Sequential Visual Attention

      • Lucas Paletta, Gerald Fritz

      Pages 293-306

Attentionhasbeenrepresentingacorescienti?ctopicinthedesignofAI-enabled systems within the last decades. Today, in the ongoing debate, design, and c- putationalmodelingofarti?cialcognitivesystems,attentionhasgainedacentral position as a focus of research. For instance, attentional methods are considered in investigating the interfacing of sensory and cognitive information processing, for the organization of behaviors, and for the understanding of individual and social cognition in re?ection of infant development. Whilevisualcognitionplaysacentralroleinhumanperception,?ndingsfrom neuroscience and experimental psychology have provided strong evidence about theperception-actionnatureofcognition.Theembodiednatureofsensory-motor intelligence requires a continuous and focused interplay between the control of motor activities and the interpretation of feedback from perceptual modalities. Decision making about the selection of information from the incoming sensory stream – in tune with contextual processing on a current task and an agent’s global objectives – becomes a further challenging issue in attentional control. Attention must operate at interfaces between bottom-up driven world int- pretation and top-down driven information selection, thus acting at the core of arti?cial cognitive systems. These insights have already induced changes in AI-related disciplines, such as the design of behavior-based robot control and the computational modeling of animats. Today, the development of enabling technologiessuch as autonomous robotic systems,miniaturizedmobile–evenwearable–sensors,andambientintelligence systems involves the real-time analysis of enormous quantities of data. These data have to be processed in an intelligent way to provide “on time delivery”of the required relevant information. Knowledge has to be applied about what needs to be attended to, and when, and what to do in a meaningful sequence, in correspondence with visual feedback.

• Simulation
• active perception
• artificial intelligence
• autonomous robotics
• cognitive science
• computational vision
• computer vision
• concept learning
• context awareness
• entropy
• gist perception
• information theo
• learning
• robot
• robotics

• Joanneum Research, Forschungsgesellschaft mbH, Computational Perception Group,, Institute of Digital Image Processing, Graz, Austria

  Lucas Paletta

• Autonomous Intelligent Systems (AIS), Autonomous Robots Department, Fraunhofer Institute, Sankt Augustin, Germany

  Erich Rome

Policies and ethics