Multimodal Computational Attention for Scene Understanding and Robotics

This book presents state-of-the-art computationalattention models that have been successfully tested in diverse applicationareas and can build the foundation for artificial systems to efficientlyexplore, analyze, and understand natural scenes. It gives a comprehensive overview of the most recentcomputational attention models for processing visual and acoustic input. Itcovers the biological background of visual and auditory attention, as well as bottom-up and top-down attentionalmechanisms and discusses various applications. In the first part new approachesfor bottom-up visual and acoustic saliency models are presented and applied tothe task of audio-visual scene exploration of a robot. In the second part theinfluence of top-down cues for attention modeling is investigated.