Modeling Visual Saliency in Images and Videos

Visual saliency, which distinguishes “interesting” visual content from others, plays an important role in multimedia and computer vision applications. This chapter starts with a brief overview of visual saliency as well as the literature of some popular models to detect salient regions. We describe two methods to model visual saliency – one in images and the other in videos. Specifically, we introduce a graph-based method to model salient region in images in a bottom-up manner. For videos, we introduce a factorization based method to model attention object in motion, which utilizes the top-down knowledge of cameraman for model saliency. Finally, future directions for visual saliency modeling and additional reading materials are highlighted to familiarize readers with the research on visual saliency modeling for multimedia applications.