A Review of Co-saliency Detection Technique: Fundamentals, Applications, and Challenges

Co-saliency detection is a newly emerging and rapidly growing research area in computer vision community. As a novel branch of visual saliency, co-saliency detection refers to discovery of the common and salient foregrounds existed in two or more relevant images, and can be more widely used in many computer vision tasks. The existing co-saliency detection algorithms mainly consist of three components: extracting effective features to represent the image regions, exploring the informative cues or factors to characterize co-saliency, and designing effective computational framework to formulate co-saliency. Although enormous methods have been developed, a deep review of the literatures concerning about the co-saliency detection technique is still lacking. In this paper, we aim to provide a comprehensive review of the fundamentals, challenges, and applications in co-saliency detection area. Specifically, this paper provides the overview of some related computer vision works, reviews the history of co-saliency detection briefly, summarizes and categorizes the major algorithms in this research area, presents the potential applications of co-saliency detection, discusses some open issues in this research area, and finally points out some unsolved challenges and promising future works. It is our hope that this review will be beneficial for both the fresh and senior researchers in this field as well as researchers working in other relevant fields to have a better understanding about what they can do with co-saliency detection in the future.