Spectral attribute learning for visual regression

doi:10.1016/j.patcog.2017.01.009

	Spectral attribute learning for visual regression
	Chen, Ke 1; Jia, Kui 2; Zhang, Zhaoxiang3 ; Kamarainen, Joni-Kristian 1; Kui Jia
刊名	PATTERN RECOGNITION
	2017-06-01
卷号	66 期号:0 页码:74-81
关键词	Facial Age Estimation Crowd Counting Head Pose Estimation Spectral Learning Attributes Regression
DOI	10.1016/j.patcog.2017.01.009
文献子类	Article
英文摘要	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.
WOS关键词	AGE ESTIMATION ; PERSON REIDENTIFICATION
WOS研究方向	Computer Science ; Engineering
语种	英语
WOS记录号	WOS:000397371800009
资助机构	Academy of Finland(267581 ; 298700)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/14035]
专题	自动化研究所_类脑智能研究中心
通讯作者	Kui Jia
作者单位	1.Tampere Univ Technol, Dept Signal Proc, Tampere, Finland 2.South China Univ Technol, Sch Elect & Informat Engn, Guangzhou, Guangdong, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Chen, Ke,Jia, Kui,Zhang, Zhaoxiang,et al. Spectral attribute learning for visual regression[J]. PATTERN RECOGNITION,2017,66(0):74-81.
APA	Chen, Ke,Jia, Kui,Zhang, Zhaoxiang,Kamarainen, Joni-Kristian,&Kui Jia.(2017).Spectral attribute learning for visual regression.PATTERN RECOGNITION,66(0),74-81.
MLA	Chen, Ke,et al."Spectral attribute learning for visual regression".PATTERN RECOGNITION 66.0(2017):74-81.