Spectral attribute learning for visual regression. (June 2017)

• Record Type: Journal Article
• Authors: Chen, Ke; Jia, Kui; Zhang, Zhaoxiang; Kämäräinen, Joni-Kristian
• Is Part Of: Pattern recognition. Volume 66(2017:Jun.)
• Page Start: 74
• Page End: 81
• Publication Date: 2017-06
• Subjects: Facial age estimation -- Crowd counting -- Head pose estimation -- Spectral learning -- Attributes -- Regression; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.01.009
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: A number of computer vision problems such as facial age estimation, crowd counting and pose estimation can be solved by learning regression mapping on low-level imagery features. We show that visual regression can be substantially improved by two-stage regression where imagery features are first mapped to an attribute space which explicitly models latent correlations across continuously-changing output. We propose an approach to automatically discover "spectral attributes" which avoids manual work required for defining hand-crafted attribute representations. Visual attribute regression outperforms direct visual regression and our spectral attribute visual regression achieves state-of-the-art accuracy in multiple applications. Abstract : Highlights: Spectral attributes avoid manually-engineered attribute construction. Spectral attributes handle multiple correlated regression outputs. Spectral attributes achieve state-of-the-art performance on various benchmarks.