CASIA OpenIR  > 智能感知与计算研究中心
Learning Structured Ordinal Measures for Video based Face Recognition
Ran He1,2; Tieniu Tan1,2; Larry Davis3; Zhenan Sun1,2
Source PublicationPattern Recognition
2018
Volume75Issue:0Pages:4-14
AbstractHandcrafted ordinal measures (OM) have been widely used in many computer vision problems. This pa- per presents a structured OM (SOM) method in a data driven way. SOM simultaneously learns ordinal filters and structured ordinal features. It leads to a structural distance metric for video-based face recog- nition. The SOM problem is posed as a non-convex integer program problem that includes two parts. The first part learns stable ordinal filters to project video data into a large-margin ordinal space. The second seeks self-correcting and discrete codes by balancing the projected data and a rank-one ordinal matrix in a structured low-rank way. Weakly-supervised and supervised structures are considered for the ordinal matrix. In addition, as a complement to hierarchical structures, deep feature representations are integrated into our method to enhance coding stability. An alternating minimization method is employed to handle the discrete and low-rank constraints, yielding high-quality codes that capture prior structures well. Experimental results on three commonly used face video databases show that our SOM method with a simple voting classifier can achieve state-of-the-art recognition rates using fewer features and samples.
KeywordLearning Structured Ordinal Measures
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20229
Collection智能感知与计算研究中心
Affiliation1.The National Laboratory of Pattern Recognition and CAS Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), CASIA
2.University of Chinese Academy of Sciences (UCAS)
3.The institute for advanced computer studies and the department of computer science, University of Maryland, College Park, MD 20742, United States
Recommended Citation
GB/T 7714
Ran He,Tieniu Tan,Larry Davis,et al. Learning Structured Ordinal Measures for Video based Face Recognition[J]. Pattern Recognition,2018,75(0):4-14.
APA Ran He,Tieniu Tan,Larry Davis,&Zhenan Sun.(2018).Learning Structured Ordinal Measures for Video based Face Recognition.Pattern Recognition,75(0),4-14.
MLA Ran He,et al."Learning Structured Ordinal Measures for Video based Face Recognition".Pattern Recognition 75.0(2018):4-14.
Files in This Item: Download All
File Name/Size DocType Version Access License
heran-Learning Struc(1737KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ran He]'s Articles
[Tieniu Tan]'s Articles
[Larry Davis]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ran He]'s Articles
[Tieniu Tan]'s Articles
[Larry Davis]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ran He]'s Articles
[Tieniu Tan]'s Articles
[Larry Davis]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: heran-Learning Structured Ordinal Measures for Video based Face Recognition.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.