14,897 Hits in 7.2 sec

Two-Stage Nonnegative Sparse Representation for Large-Scale Face Recognition

Ran He, Wei-Shi Zheng, Bao-Gang Hu, Xiang-Wei Kong
2013 IEEE Transactions on Neural Networks and Learning Systems  
This paper proposes a novel nonnegative sparse representation approach, called two-stage sparse representation (TSR), for robust face recognition on a large-scale database.  ...  More importantly, a significant reduction of computational costs is reached in comparison with sparse representation classifier; this enables the TSR to be more suitable for robust face recognition on  ...  ACKNOWLEDGMENT The authors would like to thank the Associate Editor and the reviewers for their valuable comments and advice.  ... 
doi:10.1109/tnnls.2012.2226471 pmid:24808205 fatcat:l4zt22t6nbfwdbsb4npa6j7ln4

Attention-Set based Metric Learning for Video Face Recognition [article]

Yibo Hu, Xiang Wu, Ran He
2017 arXiv   pre-print
Our method achieves state-of-the-art performance for the task of video face recognition on the three widely used benchmarks including YouTubeFace, YouTube Celebrities and Celebrity-1000.  ...  Face recognition has made great progress with the development of deep learning.  ...  For each pair of face videos, a similarity score is calculated by cosine distance metric.  ... 
arXiv:1704.03805v3 fatcat:sewqamsrovbiparxvsoge3eywe

Bilevel Distance Metric Learning for Robust Image Recognition

Jie Xu, Lei Luo, Cheng Deng, Heng Huang
2018 Neural Information Processing Systems  
Metric learning, aiming to learn a discriminative Mahalanobis distance matrix M that can effectively reflect the similarity between data samples, has been widely studied in various image recognition problems  ...  In this paper, we integrate both feature extraction and metric learning into one joint optimization framework and propose a new bilevel distance metric learning model.  ...  Bilevel Distance Metric Learning Sparse representations prove to be an effective feature for classification.  ... 
dblp:conf/nips/XuLDH18 fatcat:5tjdms6wqbd4jjgzvijq66tm4i

Representation Learning with Smooth Autoencoder [chapter]

Kongming Liang, Hong Chang, Zhen Cui, Shiguang Shan, Xilin Chen
2015 Lecture Notes in Computer Science  
Experimental results verify the effectiveness of the representations learned by our approach in image classification and face recognition tasks.  ...  In this paper, we propose a novel autoencoder variant, smooth autoencoder (SmAE), to learn robust and discriminative feature representations.  ...  Besides the traditional global metrics, some local metrics can also be used to compute the weight function.  ... 
doi:10.1007/978-3-319-16808-1_6 fatcat:ca5ydjwn4bfiznx6anghvr62qi

Face recognition using localized features based on non-negative sparse coding

Bhavin J. Shastri, Martin D. Levine
2006 Machine Vision and Applications  
This paper presents Non-Negative Sparse Coding (NNSC) applied to learning facial features for face recognition.  ...  This paper presents Non-Negative Sparse Coding (NNSC) applied to the learning of facial features for face recognition and a comparison is made with the other part-based techniques, Non-negative Matrix  ...  Acknowledgements The authors would like to thank the National Sciences and Engineering Research Council of Canada for its financial assistance.  ... 
doi:10.1007/s00138-006-0052-0 fatcat:ynuqv4h4pnhzva6wxhzfdtvkoe

Ensemble of Sparse Cross-Modal Metrics for Heterogeneous Face Recognition

Jing Huo, Yang Gao, Yinghuan Shi, Wanqi Yang, Hujun Yin
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
In particular, a weak sparse cross-modal metric learning method is firstly developed to measure distances between samples of two modalities.  ...  In this paper, a new method named as ensemble of sparse cross-modal metrics is proposed for tackling these challenging issues.  ...  Huo is also supported by a scholarship from the China Scholarship Council as a one-year visiting student at the University of Manchester.  ... 
doi:10.1145/2964284.2964311 dblp:conf/mm/HuoGSYY16 fatcat:vsmndkfdg5fotjko5qmlp662da

Commute time guided transformation for feature extraction

Yue Deng, Qionghai Dai, Ruiping Wang, Zengke Zhang
2012 Computer Vision and Image Understanding  
First, it introduces the usage of a robust probability metric, i.e., the commute time (CT), to extract visual features for face recognition via a manifold way.  ...  Owing to these positive properties, when applied to face recognition, the proposed CTG method outperforms other state-of-the-art algorithms on benchmark datasets.  ...  Berkeley for their constructive suggestions on sparse representation. This work was supported by the National Basic Research Project (  ... 
doi:10.1016/j.cviu.2011.11.002 fatcat:spdplrv5ufhonm3f22m2s33tgu

A Supervised Low-Rank Method for Learning Invariant Subspaces

Farzad Siyahjani, Ranya Almohsen, Sinan Sabri, Gianfranco Doretto
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
In addition, we show how the approach is equivalent to a local metric learning, where the local metrics (one for each class) are learned jointly, rather than independently, thus avoiding the risk of overfitting  ...  We evaluated the approach for face recognition with highly corrupted training and testing data, obtaining very promising results.  ...  [50] instead learns a discriminative dictionary for a sparse and low-rank representation.  ... 
doi:10.1109/iccv.2015.480 dblp:conf/iccv/SiyahjaniASD15 fatcat:ycaj7ni63nbu5galuwfvt76kzu

Locality-constrained group sparse representation for robust face recognition

Yu-Wei Chao, Yi-Ren Yeh, Yu-Wen Chen, Yuh-Jye Lee, Yu-Chiang Frank Wang
2011 2011 18th IEEE International Conference on Image Processing  
This paper presents a novel sparse representation for robust face recognition.  ...  We advance both group sparsity and data locality and formulate a unified optimization framework, which produces a locality and group sensitive sparse representation (LGSR) for improved recognition.  ...  In [4] , a sparse representation classification (SRC) was proposed for face recognition.  ... 
doi:10.1109/icip.2011.6116666 dblp:conf/icip/ChaoYCLW11 fatcat:s54h6c364vdprdwgvvzijvcwke

Robust Spectral Clustering via Sparse Representation [chapter]

Xiaodong Feng
2018 Recent Applications in Data Clustering  
While sparse representation proves its effectiveness for compressing high-dimensional signals, existing spectral clustering algorithms based on sparse representation use those sparse coefficients directly  ...  Spectral clustering via sparse representation has been proposed for clustering high-dimensional data.  ...  It has been widely used to machine learning and computer vision, such as image classification [38] , semi-supervised multiview distance metric learning [39] , human action recognition [40] , complex  ... 
doi:10.5772/intechopen.76586 fatcat:zcrqwtf6yba5niv2o74j6vvjnu

Neighborhood Preserved Sparse Representation for Robust Classification on Symmetric Positive Definite Matrices [article]

Ming Yin, Shengli Xie, Yi Guo, Junbin Gao, Yun Zhang
2016 arXiv   pre-print
Due to its promising classification performance, sparse representation based classification(SRC) algorithm has attracted great attention in the past few years.  ...  As such, there is still no satisfactory approach to conduct classification task for symmetric positive definite (SPD) matrices which is very useful in computer vision.  ...  Classification via Sparse Representation Sparse representation based classification(SRC) has been well-known as its robustness to face recognition [24] .  ... 
arXiv:1601.07336v1 fatcat:56bbzilfwjdx7gbdfhybc364ye

Efficient lp-norm multiple feature metric learning for image categorization

Shuhui Wang, Qingming Huang, Shuqiang Jiang, Qi Tian
2011 Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11  
The aim is to learn the Mahalanobis matrices for each independent feature and their non-sparse l p -norm weight coefficients simultaneously by maximizing the margin of the overall learned distance metric  ...  In this paper, we propose an efficient distance metric learning model which adapts Distance Metric Learning on multiple feature representations.  ...  We propose a new distance metric learning method which learns an overall distance metric by optimizing a set of Mahalanobis matrix for several feature representations at one time.  ... 
doi:10.1145/2063576.2063894 dblp:conf/cikm/WangHJT11 fatcat:vlbnokzbira5thplxzkgtflfla

EPML: Expanded Parts Based Metric Learning for Occlusion Robust Face Verification [chapter]

Gaurav Sharma, Frédéric Jurie, Patrick Pérez
2015 Lecture Notes in Computer Science  
We propose a novel Expanded Parts based Metric Learning (EPML) model for face verification.  ...  We show quantitatively, by experiments on the standard benchmark dataset Labeled Faces in the Wild (LFW), that the model works much better than the traditional method of face representation with metric  ...  [20] suggested detecting occluded regions using Fast-Weighted Principal Component Analysis (FW-PCA) and using the occluded regions for weighting the blocks for face representation. Alyuz et al.  ... 
doi:10.1007/978-3-319-16817-3_4 fatcat:2yvqyz6mh5fgxe5j2p5kavprp4

Linear Representation-based Methods for Image Classification: A Survey

Jianhang Zhou, Shaoning Zeng, Bob Zhang
2020 IEEE Access  
ACKNOWLEDGMENT This document is the result of a research project funded by the University of Macau (MYRG2019-00006-FST).  ...  For multiview face recognition, the joint sparse representation-based classification (JSRC) [116] was proposed, where it constructed a shared sparse coefficient for different views of an individual's  ...  The proposed self-paced joint sparse representation (SPJSR) learned the weight of each neighbor approximation and sparse coefficient in a self-paced scheme.  ... 
doi:10.1109/access.2020.3041154 fatcat:rjjplxhjv5alveg5aum635sxgi

A Novel Spatially Confined Non-Negative Matrix Factorization for Face Recognition

Han Foon Neo, Andrew Beng Jin Teoh, David Chek Ling Ngo
2005 IAPR International Workshop on Machine Vision Applications  
In this paper, a novel method for facial representation called Spatially Confined Non-Negative Matrix Factorization (SFNMF) is presented.  ...  SFNMF derived a significant set of basis which allows a non-subtractive representation of images and these bases manifest localized features.  ...  pattern set, whose aim is to produce a most expressive subspace for face representation and recognition.  ... 
dblp:conf/mva/NeoTN05 fatcat:oevpvyuj4vcbflxmev6hzdygpu
« Previous Showing results 1 — 15 out of 14,897 results