Read more
The new edition of this popular book introduces the study of attention, focusing on attention modeling, and addressing such themes as saliency models, signal detection, and different types of signals, including real-life applications. The first edition was written at a moment when the Deep Learning Neural Network (DNNs) techniques were just at their beginnings in terms of attention. Deep learning has recently become a key factor in attention prediction on images and video, and attention mechanisms have become key factors in deep learning models. The second edition tackles the arrival of DNNs for attention computing in images and video, and also discusses the attention mechanisms within DNNs (attention modules, transformers, grad-cam-based saliency maps, etc.). From Human Attention to Computational Attention 2nd Edition also explores the parallels between the brain structures and the DNN architectures to reveal how biomimetics can improve the model designs. The book is truly multi-disciplinary, collating work from psychology, neuroscience, engineering, and computer science.
List of contents
1 Why modeling attention in computers?, M. Mancas, V. Ferrera, N. Riche.- 2 What is attention?, M. Mancas.- 3 How to measure attention?, M. Mancas, V. Ferrera.- 4 Where: Human attention networks and their dysfunctions after brain damage, T. Seidel Malkinson, P. Bartolomeo.- 5 Attention and Signal Detection: A Practical Guide, V. Ferrera.- 6 Effects of Attention in Visual Cortex: Linking Single Neuron Physiology to Visual Detection and Discrimination, V. Ferrera.- 7 Modeling attention in engineering, M. Mancas.- 8 Bottom-Up Visual Attention for Still Images: a Global View, F. Stentiford.- 9 Bottom-up saliency models for still images: a practical review, N. Riche and M. Mancas.- 10 Bottom-up saliency models for videos: a practical review, N. Riche and M. Mancas.- 11 Databases for saliency models evaluation, N. Riche.- 12 Metrics for saliency models validation, N. Riche.- 13 Study of parameters affecting visual saliency assessment, N. Riche.- 14 Saliency models evaluation, N. Riche.- 15 Object-based Attention: cognitive and computational perspectives, A. Belardinelli.- 16 Multimodal saliency models for videos, Antoine Coutrot, Nathalie Guyader.- 17 Towards 3D visual saliency modelling, J. Leroy, N. Riche.- 18 Applications of saliency models, M. Mancas, O. Le Meur.- 19 Attentive Content-Based Image Retrieval, D. Awad, V. Courboulay, A. Revel.- 20 Saliency and Attention for Video Quality Assessment, D. Culibrk.- 21 Attentive Robots, S. Frintrop.- 22 Attention modeling: what are the next steps?, M. Mancas, V. Ferrera, N. Riche.- Index.
About the author
Matei Mancas, PhD, is Senior Researcher, Numediart Institute for Creative Technologies, University of Mons, Mons, Belgium.
Vincent P. Ferrara, PhD, is Professor, Department of Neuroscience, Zuckerman Institute, Columbia University, New York, New York
Antoine Coutrot, PhD, is Tenured Researcher, Centre National de la Recherche Scientifique, Laboratoire d’InfoRmatique en Image et Systèmes d’information, Lyon, France.
Summary
The new edition of this popular book introduces the study of attention, focusing on attention modeling, and addressing such themes as saliency models, signal detection, and different types of signals, including real-life applications. The first edition was written at a moment when the Deep Learning Neural Network (DNNs) techniques were just at their beginnings in terms of attention. Deep learning has recently become a key factor in attention prediction on images and video, and attention mechanisms have become key factors in deep learning models. The second edition tackles the arrival of DNNs for attention computing in images and video, and also discusses the attention mechanisms within DNNs (attention modules, transformers, grad-cam-based saliency maps, etc.). From Human Attention to Computational Attention 2nd Edition also explores the parallels between the brain structures and the DNN architectures to reveal how biomimetics can improve the model designs. The book is truly multi-disciplinary, collating work from psychology, neuroscience, engineering, and computer science.
