Visual Saliency Computation

This book covers fundamental principles and computational approaches relevant to visual saliency computation. As an interdisciplinary problem, visual saliency computation is introduced in this book from an innovative perspective that combines both neurobiology and machine learning. The book is also well-structured to address a wide range of readers, from specialists in the field to general readers interested in computer science and cognitive psychology. With this book, a reader can start from the very basic question of "what is visual saliency?" and progressively explore the problems in detecting salient locations, extracting salient objects, learning prior knowledge, evaluating performance, and using saliency in real-world applications. It is highly expected that this book will spark a great interest of research in the related communities in years to come.

Written to be easily understood by a wide range of readers, from specialists in the field of visual saliency computation to general readers interested in computer science and cognitive psychology Offers a foreword by Zhengyou Zhang, included in the front matter and is freely available for perusal on SpringerLink Introduces concepts step-by-step, starting from visual saliency and progressively exploring the problems in modeling saliency, extracting salient objects, mining prior knowledge, evaluating performance, and using saliency in real-world applications

Inhalt
Benchmark and evaluation metrics.- Location-based visual saliency computation.- Object-based visual saliency computation.- Learning-based visual saliency computation.- Mining cluster-specific knowledge for saliency ranking.- Removing label ambiguity in training saliency model.- Saliency-based applications.- Conclusions and future work.