Order Learning - An Overview

Order learning aims to learn the ordering relationship among objects by comparing them. Recently, several order learning techniques have achieved great performances on various computer vision tasks. In this paper, we provide an overview of these order learning techniques. First, we briefly discuss conventional rank estimation algorithms related to order learning. Second, we review the order learning techniques in detail. Third, we discuss the results of order learning on three vision applications: facial age estimation, historical color image (HCI) classification, and aesthetic quality assessment.