Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters
























6,147 Hits in 7.6 sec

Neural class-specific regression for face verification

Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj
2018 IET Biometrics  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.0 MB)
https://web.archive.org/web/20200907181533/https://arxiv.org/pdf/1708.09642v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2017 pre-print arXiv:1708.09642v1 fatcat:2c4i3g24kvbk7onirtgtusl74i
This allows us to derive linear, (reduced) kernel and neural network-based class-specific discriminant analysis methods using efficient batch and/or iterative training schemes, suited for large-scale learning  ...  While it has been shown that kernel-based Class-Specific Discriminant Analysis is able to provide excellent performance in small- and medium-scale face verification problems, its application in today's  ...  in the large-scale verification problem of YouTube Faces dataset.  ... 
doi:10.1049/iet-bmt.2017.0081 fatcat:3nzxrecxibeqpj3vewuoukbt74
DOAJ Multiple Versions
Citation

Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj. "Neural class-specific regression for face verification." IET Biometrics 7.1 (2018) 63-70

Surpassing Human-Level Face Verification Performance on LFW with GaussianFace

Chaochao Lu, Xiaoou Tang
2015 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.4 MB)
https://web.archive.org/web/20220629110613/https://ojs.aaai.org/index.php/AAAI/article/download/9797/9656

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

To enhance discriminative power, we introduced a more efficient equivalent form of Kernel Fisher Discriminant Analysis to DGPLVM.To speed up the process of inference and prediction, we exploited the low  ...  For the first time, the human-level performance in face verification (97.53%) on LFW is surpassed.  ...  Reformulating GPs for large-scale multi-task learning is non-trivial. To simplify calculations, we introduce a more efficient equivalent form of Kernel Fisher Discriminant Analysis (KFDA) to DGPLVM.  ... 
doi:10.1609/aaai.v29i1.9797 fatcat:c2g543keijdlxbumjaiubw3gaq
Citation

Chaochao Lu, Xiaoou Tang. "Surpassing Human-Level Face Verification Performance on LFW with GaussianFace." PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE 29.1 (2015)

Gabor wavelets and General Discriminant Analysis for face identification and verification

LinLin Shen, Li Bai, Michael Fairhurst
2007 Image and Vision Computing  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (571.9 kB)
https://web.archive.org/web/20110331213321/http://ima.ac.uk/papers/shen2006b.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL. The file type is application/pdf.

, Linear Discriminant Analysis, and Kernel Principal Component Analysis.  ...  A novel and uniform framework for both face identification and verification is presented in this paper.  ...  Kernel based methods [9] , exemplified by Kernel Principal Component Analysis (KPCA) [10, 11] , Kernel Fisher Discriminant Analysis (KFDA) [12, 13] and General Discriminant Analysis (GDA) [14] have  ... 
doi:10.1016/j.imavis.2006.05.002 fatcat:bvrbxtyfojagxivrzjk3okwyve
Citation

LinLin Shen, Li Bai, Michael Fairhurst. "Gabor wavelets and General Discriminant Analysis for face identification and verification." Image and Vision Computing 25.5 (2007) 553-563

Gabor-Based Kernel Partial-Least-Squares Discrimination Features for Face Recognition

Vitomir Štruc, Nikola Pavešić
2009 Informatica  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (345.6 kB)
https://web.archive.org/web/20201105002357/https://informatica.vu.lt/journal/INFORMATICA/article/541/file/pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

(LDA), kernel principal component analysis (KPCA) or generalized discriminant analysis (GDA) as well as combinations of these methods with Gabor representations of the face images.  ...  The paper presents a novel method for the extraction of facial features based on the Gabor-wavelet representation of face images and the kernel partial-least-squares discrimination (KPLSD) algorithm.  ...  , generalized discriminant analysis (GDA) (Baudat and Anouar, 2000) , kernel Fisher discriminant analysis (KFDA) (Yang, 2002) and kernel partial-least-squares discriminant analysis (KPDA) (Štruc et  ... 
doi:10.15388/informatica.2009.240 fatcat:4grgyhh4lvcbrlp7uiarquzqhm
Open Access
Citation

Vitomir Štruc, Nikola Pavešić. "Gabor-Based Kernel Partial-Least-Squares Discrimination Features for Face Recognition." Informatica 20.1 (2009) 115-138

Investigating the feasibility of image-based nose biometrics

Niv Zehngut, Felix Juefei-Xu, Rishabh Bardia, Dipan K. Pal, Chandrasekhar Bhagavatula, M. Savvides
2015 2015 IEEE International Conference on Image Processing (ICIP)  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.4 MB)
https://web.archive.org/web/20170829144147/https://users.ece.cmu.edu/~juefeix/felix_icip15_nose.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

In this study, we extract discriminative nasal features using Kernel Class-Dependence Feature Analysis (KCFA) based on Optimal Trade-off Synthetic Discriminant Function (OTSDF) filters.  ...  The search for new biometrics is never ending. In this work, we investigate the use of image based nasal features as a biometric.  ...  Experiment I: Large-scale Nose Biometrics vs. Face Biometrics In this experiment, we carry out the large-scale verification experiments by following the FRGC matching protocols.  ... 
doi:10.1109/icip.2015.7350853 dblp:conf/icip/ZehngutJBPBS15 fatcat:5wxwg4s7vjce5j3iodjvfinzy4
Citation

Niv Zehngut, Felix Juefei-Xu, Rishabh Bardia, Dipan K. Pal, Chandrasekhar Bhagavatula, M. Savvides. "Investigating the feasibility of image-based nose biometrics." 2015 IEEE International Conference on Image Processing (ICIP) (2015) 522-526

Surpassing Human-Level Face Verification Performance on LFW with GaussianFace [article]

Chaochao Lu, Xiaoou Tang
2014 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20200824140321/https://arxiv.org/pdf/1404.3840v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2014 pre-print
arXiv:1404.3840v1 fatcat:epp74ramubfuzoagly6n3yjnhe
2014 pre-print
arXiv:1404.3840v2 fatcat:37czis4xwrbwhjfeabghvs2mgq
For the first time, the human-level performance in face verification (97.53%) on LFW is surpassed.  ...  Face verification remains a challenging problem in very complex conditions with large variations such as pose, illumination, expression, and occlusions.  ...  Acknowledgements We would like to thank Deli Zhao and Chen Change Loy for their insightful discussions.  ... 
arXiv:1404.3840v3 fatcat:3s7wevwavfe7tdtg7s36ha5coy
Multiple Versions
Citation

Chaochao Lu, Xiaoou Tang. "Surpassing Human-Level Face Verification Performance on LFW with GaussianFace." arXiv (2014)

Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning

Zhiwu Huang, Ruiping Wang, Shiguang Shan, Xilin Chen
2015 Pattern Recognition  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.3 MB)
https://web.archive.org/web/20151123153841/http://vipl.ict.ac.cn:80/homepage/rpwang/publications/Face%20Recognition%20on%20Large-scale%20Video%20in%20the%20Wild%20with%20Hybrid%20Euclidean-and-Riemannian%20Metric%20Learning_PR2015.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL. The file type is application/pdf.

Extensive experimental results demonstrate that our method has a clear superiority over the state-of-the-art set-based methods for large-scale video-based face recognition.  ...  The proposed method is evaluated on four public and challenging large-scale video face datasets.  ...  Evaluation on video face verification Datasets For video face verification task, we conduct experiments on two challenging large-scale datasets: YouTube Face (YTF) [34] and Point-and-Shoot Face Recognition  ... 
doi:10.1016/j.patcog.2015.03.011 fatcat:sqr2cvioajdczbfmno3mnfonha
Citation

Zhiwu Huang, Ruiping Wang, Shiguang Shan, Xilin Chen. "Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning." Pattern Recognition 48.10 (2015) 3113-3124

Projection Metric Learning on Grassmann Manifold with Application to Video based Face Recognition

Zhiwu Huang, Ruiping Wang, Shiguang Shan, Xilin Chen
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (386.6 kB)
https://web.archive.org/web/20160309190956/http://vipl.ict.ac.cn:80/sites/default/files/papers/files/Projection%20Metric%20Learning%20on%20Grassmann%20Manifold%20with%20Application%20to%20Video%20based%20Face%20Recognition.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL. The file type is application/pdf.

To leverage the kernel-based methods developed for Euclidean space, several recent methods have been proposed to embed the Grassmann manifold into a high dimensional Hilbert space by exploiting the well  ...  From the perspective of manifold learning, our method can be regarded as performing a geometry-aware dimensionality reduction from the original Grassmann manifold to a lower-dimensional, more discriminative  ...  Video based Face Verification For video face verification task, we conduct experiments on two challenging large-scale datasets: YouTube Face (YTF) [40] and Point-and-Shoot Face Recognition Challenge  ... 
doi:10.1109/cvpr.2015.7298609 dblp:conf/cvpr/HuangWSC15 fatcat:xcnbavicpbfiva3rvhy6ppmuh4
Citation

Zhiwu Huang, Ruiping Wang, Shiguang Shan, Xilin Chen. "Projection Metric Learning on Grassmann Manifold with Application to Video based Face Recognition." 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015) 140-149

Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos

Kihyuk Sohn, Sifei Liu, Guangyu Zhong, Xiang Yu, Ming-Hsuan Yang, Manmohan Chandraker
2017 2017 IEEE International Conference on Computer Vision (ICCV)  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.7 MB)
https://web.archive.org/web/20170909152726/http://faculty.ucmerced.edu/mhyang/papers/iccv2017_video_face_recognition.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

The framework utilizes large-scale unlabeled video data to reduce the gap between different domains while transferring discriminative knowledge from large-scale labeled still images.  ...  quality between the domains and the difficulty of curating diverse large-scale video datasets.  ...  The existence of video frames allows set-to-set comparison for verification, which opens up a new challenge for the face recognition problem.  ... 
doi:10.1109/iccv.2017.630 dblp:conf/iccv/SohnLZY0C17 fatcat:vmlbvljov5hpjeuwn4w5cdy5ai
Citation

Kihyuk Sohn, Sifei Liu, Guangyu Zhong, Xiang Yu, Ming-Hsuan Yang, Manmohan Chandraker. "Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos." 2017 IEEE International Conference on Computer Vision (ICCV) (2017) 5917-5925

Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos [article]

Kihyuk Sohn, Sifei Liu, Guangyu Zhong, Xiang Yu, Ming-Hsuan Yang, Manmohan Chandraker
2017 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (6.4 MB)
https://web.archive.org/web/20200826055319/https://arxiv.org/pdf/1708.02191v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

The framework utilizes large-scale unlabeled video data to reduce the gap between different domains while transferring discriminative knowledge from large-scale labeled still images.  ...  quality between the domains and the difficulty of curating diverse large-scale video datasets.  ...  The existence of video frames allows set-to-set comparison for verification, which opens up a new challenge for the face recognition problem.  ... 
arXiv:1708.02191v1 fatcat:s4uclmrsjrh4rnitafez5fofki
Citation

Kihyuk Sohn, Sifei Liu, Guangyu Zhong, Xiang Yu, Ming-Hsuan Yang, Manmohan Chandraker. "Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos." arXiv (2017)

Weighted Piecewise LDA for Solving the Small Sample Size Problem in Face Verification

Marios Kyperountas, Anastasios Tefas, Ioannis Pitas
2007 IEEE Transactions on Neural Networks  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (377.5 kB)
https://web.archive.org/web/20170809232832/http://poseidon.csd.auth.gr/papers/PUBLISHED/JOURNAL/pdf/kyperountas_TNN_2007.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

Index Terms-Face verification, linear discriminant analysis (LDA), small sample size (SSS) problem  ...  Initially, a set of weighted piecewise discriminant hyper-planes are used in order to provide a more accurate discriminant decision than the one produced by the traditional linear discriminant analysis  ...  INTRODUCTION INEAR discriminant analysis is an important statistical tool for pattern recognition, verification, and, in general, classification applications.  ... 
doi:10.1109/tnn.2006.885038 pmid:17385635 fatcat:jdivnrydmncgzexyscowrjqtxe
Citation

Marios Kyperountas, Anastasios Tefas, Ioannis Pitas. "Weighted Piecewise LDA for Solving the Small Sample Size Problem in Face Verification." IEEE Transactions on Neural Networks 18.2 (2007) 506-519

Face Verification Across Age Progression Using Discriminative Methods

Haibin Ling, S. Soatto, N. Ramanathan, D.W. Jacobs
2010 IEEE Transactions on Information Forensics and Security  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (724.3 kB)
https://web.archive.org/web/20170809020358/http://www.vision.cs.ucla.edu/papers/lingSRJ10.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

We found surprisingly that the added difficulty of verification produced by age gaps becomes saturated after the gap is larger than four years, for gaps of up to ten years.  ...  Face verification in the presence of age progression is an important problem that has not been widely addressed.  ...  Face verification as a two-class classification problem has been studied for general face analysis tasks. For example, Moghaddam et al.  ... 
doi:10.1109/tifs.2009.2038751 fatcat:bfe7yg7hqja2np2zqmjx5mwc54
Citation

Haibin Ling, S. Soatto, N. Ramanathan, D.W. Jacobs. "Face Verification Across Age Progression Using Discriminative Methods." IEEE Transactions on Information Forensics and Security 5.1 (2010) 82-91

Nonlinear Metric Learning with Deep Independent Subspace Analysis Network for Face Verification

Xinyuan CAI, Chunheng WANG, Baihua XIAO, Yunxue SHAO
2013 IEICE transactions on information and systems  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20181031020900/https://www.jstage.jst.go.jp/article/transinf/E96.D/12/E96.D_2830/_pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL. The file type is application/pdf.

learning architecture, face verification  ...  Face verification is the task of determining whether two given face images represent the same person or not.  ...  However, for images belonging to a specific object class, such as faces, this assumption is no longer reasonable.  ... 
doi:10.1587/transinf.e96.d.2830 fatcat:tdbjoki6vjcvdhaxmqfrjjviby
Citation

Xinyuan CAI, Chunheng WANG, Baihua XIAO, Yunxue SHAO. "Nonlinear Metric Learning with Deep Independent Subspace Analysis Network for Face Verification." IEICE transactions on information and systems E96.D.12 (2013) 2830-2838

Regularized Kernel Discriminant Analysis With a Robust Kernel for Face Recognition and Verification

S. Zafeiriou, G. Tzimiropoulos, M. Petrou, T. Stathaki
2012 IEEE Transactions on Neural Networks and Learning Systems  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (254.0 kB)
https://web.archive.org/web/20210718041857/https://nottingham-repository.worktribe.com/1007943/1/tzimiroTNN12.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

We propose a robust approach to discriminant kernel-based feature extraction for face recognition and verification.  ...  We show, for the first time, how to perform the eigen analysis of the within-class scatter matrix directly in the feature space.  ...  To cope with such phenomena, recent research on feature extraction for face recognition and verification has focused on nonlinear kernel-based extensions to linear discriminant analysis (LDA) [4] , [  ... 
doi:10.1109/tnnls.2011.2182058 pmid:24808557 fatcat:277esc2wmvglth3t43xanpklzm
Citation

S. Zafeiriou, G. Tzimiropoulos, M. Petrou, T. Stathaki. "Regularized Kernel Discriminant Analysis With a Robust Kernel for Face Recognition and Verification." IEEE Transactions on Neural Networks and Learning Systems 23.3 (2012) 526-534

An Adaptive Face Recognition System Based on a Novel Incremental Kernel Nonparametric Discriminant Analysis

2019 KSII Transactions on Internet and Information Systems  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (560.0 kB)
https://web.archive.org/web/20200506185908/http://www.itiis.org/digital-library/manuscript/file/22080/TIISVol13No4-22.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

This paper introduces an adaptive face recognition method based on a Novel Incremental Kernel Nonparametric Discriminant Analysis (IKNDA) that is able to learn through time.  ...  A comparative evaluation of the IKNDA is performed for face recognition, besides, for other classification endeavors, in a decontextualized evaluation schemes.  ...  Moreover, it requires large storage space and leads to increased training time, chiefly, for large scale datasets. Thus, incremental learning strategy is required.  ... 
doi:10.3837/tiis.2019.04.022 fatcat:zdmcgbk3rbajpaaddddcbtatli
Citation

"An Adaptive Face Recognition System Based on a Novel Incremental Kernel Nonparametric Discriminant Analysis." KSII Transactions on Internet and Information Systems 13.4 (2019)

« Previous Showing results 1 — 15 out of 6,147 results