From Human Attention to Computational Attention | A Multidisciplinary Approach

Matei Mancas (u. a.)

ISBN 10: 3031842995 / ISBN 13: 9783031842993

Editore: Springer, 2025

From Human Attention to Computational Attention | A Multidisciplinary Approach | Matei Mancas (u. a.) | Buch | viii | Englisch | 2025 | Springer | EAN 9783031842993 | Verantwortliche Person für die EU: Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg, juergen[dot]hartmann[at]springer[dot]com | Anbieter: preigu Print on Demand. Codice articolo 133682986

Riassunto:

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.

 

Informazioni sull'autore:

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.

Dati bibliografici

Titolo: From Human Attention to Computational ...
Casa editrice: Springer
Data di pubblicazione: 2025
Legatura: Buch
Condizione: Neu
Edizione: seconda edizione