Skip to main content

About this book

This book presents state-of-the-art computational attention models that have been successfully tested in diverse application areas and can build the foundation for artificial systems to efficiently explore, analyze, and understand natural scenes. It gives a comprehensive overview of the most recent computational attention models for processing visual and acoustic input. It covers the biological background of visual and auditory attention, as well as bottom-up and top-down attentional mechanisms and discusses various applications. In the first part new approaches for bottom-up visual and acoustic saliency models are presented and applied to the task of audio-visual scene exploration of a robot. In the second part the influence of top-down cues for attention modeling is investigated.

Table of Contents


Chapter 1. Introduction

We immediately spot a warning triangle on a street or a black sheep in a flock. Yet, although we know what we are looking for, it can take us minutes to find Waldo, who blends into a crowd of nondescript people.
Boris Schauerte

Chapter 2. Background

Although in principle all attention models serve the same purpose, i.e. to highlight potentially relevant and thus interesting—that is to say “salient”—data, attention models can differ substantially in which parts of the signal they mark as being of interest.
Boris Schauerte

Chapter 3. Bottom-Up Audio-Visual Attention for Scene Exploration

We can differentiate between two attentional mechanisms: First, overt attention directs the sense organs toward salient stimuli to optimize the perception quality.
Boris Schauerte

Chapter 4. Multimodal Attention with Top-Down Guidance

In many situations, people want to guide our attention to specific objects or aspects in our environment.
Boris Schauerte

Chapter 5. Conclusion

In addition to the discussion and presentation of future work in Sects. 3.​6 and 4.​5, let us briefly summarize our contributions and provide an outlook on ongoing and future work to conclude this book.
Boris Schauerte


Additional information

Premium Partner

image credits