Predicting Multiple Attributes via Relative Multi-task Learning

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 1027 - 1034
• Main Authors: Chen, Lin, Zhang, Qiang, Li, Baoxin
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Accuracy; Computer vision; Conferences; Correlation; Cost function; Gain; Joints; Learning; Mathematical analysis; Mathematical models; Pattern recognition; Ranking; Training; Vectors

Relative attributes learning aims to learn ranking functions describing the relative strength of attributes. Most of current learning approaches learn ranking functions for each attribute independently without considering possible intrinsic relatedness among the attributes. For a problem involving m...