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 the discovery of common and salient foregrounds from two or more relevant images, and can be 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 cosaliency. Although numerous methods have been developed, a deep review of the literatures containing the co-saliency detection technique is still lacking. In this paper, we aim at providing a comprehensive review of the fundamentals, challenges, and applications of co-saliency detection. Specifically, this paper will provide the overview of some related computer vision works, review the history of co-saliency detection, summarize and categorize the major algorithms in this research area, discuss some open issues in this area, present the potential applications of co-saliency detection, and finally point out some unsolved challenges and promising future works. We expect that this review will be beneficial for both fresh and senior researchers in this field, and researchers working in other relevant fields to have a better understanding of what they can do with co-saliency detection in the future.