upadint site

1 files changed, 90 insertions, 122 deletions

diff --git a/site/datasets/verified/msceleb.csv b/site/datasets/verified/msceleb.csv
index d1a7ec8c..be5b063c 100644
--- a/site/datasets/verified/msceleb.csv
+++ b/site/datasets/verified/msceleb.csv
@@ -3,125 +3,93 @@ id,country,dataset_name,key,lat,lng,loc,loc_type,paper_id,paper_type,paper_url,t
 1,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,2011d4da646f794456bebb617d1500ddf71989ed,citation,https://pdfs.semanticscholar.org/2011/d4da646f794456bebb617d1500ddf71989ed.pdf,Transductive Centroid Projection for Semi-supervised Large-Scale Recognition,2018
 2,China,MsCeleb,msceleb,39.993008,116.329882,SenseTime,company,2011d4da646f794456bebb617d1500ddf71989ed,citation,https://pdfs.semanticscholar.org/2011/d4da646f794456bebb617d1500ddf71989ed.pdf,Transductive Centroid Projection for Semi-supervised Large-Scale Recognition,2018
 3,United States,MsCeleb,msceleb,39.2899685,-76.62196103,University of Maryland,edu,23dd8d17ce09c22d367e4d62c1ccf507bcbc64da,citation,https://pdfs.semanticscholar.org/23dd/8d17ce09c22d367e4d62c1ccf507bcbc64da.pdf,Deep Density Clustering of Unconstrained Faces ( Supplementary Material ),2018
-4,United States,MsCeleb,msceleb,37.3936717,-122.0807262,Facebook,company,628a3f027b7646f398c68a680add48c7969ab1d9,citation,https://pdfs.semanticscholar.org/628a/3f027b7646f398c68a680add48c7969ab1d9.pdf,Plan for Final Year Project : HKU-Face : A Large Scale Dataset for Deep Face Recognition,2017
-5,United States,MsCeleb,msceleb,37.4219999,-122.0840575,Google,company,628a3f027b7646f398c68a680add48c7969ab1d9,citation,https://pdfs.semanticscholar.org/628a/3f027b7646f398c68a680add48c7969ab1d9.pdf,Plan for Final Year Project : HKU-Face : A Large Scale Dataset for Deep Face Recognition,2017
-6,France,MsCeleb,msceleb,46.1476461,-1.1549415,University of La Rochelle,edu,153fbae25efd061f9046970071d0cfe739a35a0e,citation,,FaceLiveNet: End-to-End Networks Combining Face Verification with Interactive Facial Expression-Based Liveness Detection,2018
-7,China,MsCeleb,msceleb,26.89887,112.590435,University of South China,edu,98518fc368d7e1478cef40f5f8fd4468763645ad,citation,http://downloads.hindawi.com/journals/cin/2018/4512473.pdf,A Community Detection Approach to Cleaning Extremely Large Face Database,2018
-8,China,MsCeleb,msceleb,28.2290209,112.99483204,"National University of Defense Technology, China",mil,98518fc368d7e1478cef40f5f8fd4468763645ad,citation,http://downloads.hindawi.com/journals/cin/2018/4512473.pdf,A Community Detection Approach to Cleaning Extremely Large Face Database,2018
-9,China,MsCeleb,msceleb,39.9601488,116.35193921,Beijing University of Posts and Telecommunications,edu,6cdbbced12bff53bcbdde3cdb6d20b4bd02a9d6c,citation,https://arxiv.org/pdf/1811.12026.pdf,Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network,2018
-10,China,MsCeleb,msceleb,39.98177,116.330086,National Laboratory of Pattern Recognition,edu,e47f4a127f41c055fb7893ddc295932ead783c63,citation,https://arxiv.org/pdf/1709.03675.pdf,Adversarial Discriminative Heterogeneous Face Recognition,2018
-11,China,MsCeleb,msceleb,39.9082804,116.2458527,University of Chinese Academy of Sciences,edu,e47f4a127f41c055fb7893ddc295932ead783c63,citation,https://arxiv.org/pdf/1709.03675.pdf,Adversarial Discriminative Heterogeneous Face Recognition,2018
-12,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,2401cd5606c6bc5390acc352d00c1685f0c8af60,citation,https://arxiv.org/pdf/1809.01407.pdf,Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition,2018
-13,China,MsCeleb,msceleb,39.993008,116.329882,SenseTime,company,2401cd5606c6bc5390acc352d00c1685f0c8af60,citation,https://arxiv.org/pdf/1809.01407.pdf,Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition,2018
-14,Singapore,MsCeleb,msceleb,1.3484104,103.68297965,Nanyang Technological University,edu,2401cd5606c6bc5390acc352d00c1685f0c8af60,citation,https://arxiv.org/pdf/1809.01407.pdf,Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition,2018
-15,United States,MsCeleb,msceleb,42.718568,-84.47791571,Michigan State University,edu,b446bcd7fb78adfe346cf7a01a38e4f43760f363,citation,https://pdfs.semanticscholar.org/b446/bcd7fb78adfe346cf7a01a38e4f43760f363.pdf,To appear in ICB 2018 Longitudinal Study of Child Face Recognition,2017
-16,United Kingdom,MsCeleb,msceleb,51.3791442,-2.3252332,University of Bath,edu,26567da544239cc6628c5696b0b10539144cbd57,citation,https://arxiv.org/pdf/1811.12784.pdf,The GAN that Warped: Semantic Attribute Editing with Unpaired Data,2018
-17,United Kingdom,MsCeleb,msceleb,51.49887085,-0.17560797,Imperial College London,edu,40bb090a4e303f11168dce33ed992f51afe02ff7,citation,http://openaccess.thecvf.com/content_cvpr_2017_workshops/w33/papers/Deng_Marginal_Loss_for_CVPR_2017_paper.pdf,Marginal Loss for Deep Face Recognition,2017
-18,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,4cdb6144d56098b819076a8572a664a2c2d27f72,citation,https://arxiv.org/pdf/1806.01196.pdf,Face Synthesis for Eyeglass-Robust Face Recognition,2018
-19,China,MsCeleb,msceleb,39.9082804,116.2458527,University of Chinese Academy of Sciences,edu,4cdb6144d56098b819076a8572a664a2c2d27f72,citation,https://arxiv.org/pdf/1806.01196.pdf,Face Synthesis for Eyeglass-Robust Face Recognition,2018
-20,United States,MsCeleb,msceleb,39.2899685,-76.62196103,University of Maryland,edu,872dfdeccf99bbbed7c8f1ea08afb2d713ebe085,citation,https://arxiv.org/pdf/1703.09507.pdf,L2-constrained Softmax Loss for Discriminative Face Verification,2017
-21,United States,MsCeleb,msceleb,42.718568,-84.47791571,Michigan State University,edu,3011b5fce49112228711a9e5f92d6f191687c1ea,citation,https://arxiv.org/pdf/1803.09014.pdf,Feature Transfer Learning for Deep Face Recognition with Long-Tail Data,2018
-22,United Kingdom,MsCeleb,msceleb,51.49887085,-0.17560797,Imperial College London,edu,1929863fff917ee7f6dc428fc1ce732777668eca,citation,https://arxiv.org/pdf/1712.04695.pdf,UV-GAN: Adversarial Facial UV Map Completion for Pose-Invariant Face Recognition,2018
-23,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,d949fadc9b6c5c8b067fa42265ad30945f9caa99,citation,https://arxiv.org/pdf/1710.00870.pdf,Rethinking Feature Discrimination and Polymerization for Large-scale Recognition,2017
-24,China,MsCeleb,msceleb,31.30104395,121.50045497,Fudan University,edu,5a259f2f5337435f841d39dada832ab24e7b3325,citation,,Face Recognition via Active Annotation and Learning,2016
-25,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,5a259f2f5337435f841d39dada832ab24e7b3325,citation,,Face Recognition via Active Annotation and Learning,2016
-26,China,MsCeleb,msceleb,39.993008,116.329882,SenseTime,company,c72a2ea819df9b0e8cd267eebcc6528b8741e03d,citation,https://arxiv.org/pdf/1708.09687.pdf,Quantifying Facial Age by Posterior of Age Comparisons,2017
-27,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,c72a2ea819df9b0e8cd267eebcc6528b8741e03d,citation,https://arxiv.org/pdf/1708.09687.pdf,Quantifying Facial Age by Posterior of Age Comparisons,2017
-28,United States,MsCeleb,msceleb,39.2899685,-76.62196103,University of Maryland,edu,b6f758be954d34817d4ebaa22b30c63a4b8ddb35,citation,https://arxiv.org/pdf/1703.04835.pdf,A Proximity-Aware Hierarchical Clustering of Faces,2017
-29,United States,MsCeleb,msceleb,42.718568,-84.47791571,Michigan State University,edu,19fa871626df604639550c6445d2f76cd369dd13,citation,https://arxiv.org/pdf/1805.02283.pdf,DocFace: Matching ID Document Photos to Selfies,2018
-30,United States,MsCeleb,msceleb,32.87935255,-117.23110049,"University of California, San Diego",edu,d35534f3f59631951011539da2fe83f2844ca245,citation,https://arxiv.org/pdf/1705.07904.pdf,Semantically Decomposing the Latent Spaces of Generative Adversarial Networks,2017
-31,United States,MsCeleb,msceleb,37.43131385,-122.16936535,Stanford University,edu,d35534f3f59631951011539da2fe83f2844ca245,citation,https://arxiv.org/pdf/1705.07904.pdf,Semantically Decomposing the Latent Spaces of Generative Adversarial Networks,2017
-32,United States,MsCeleb,msceleb,40.4441619,-79.94272826,Carnegie Mellon University,edu,d35534f3f59631951011539da2fe83f2844ca245,citation,https://arxiv.org/pdf/1705.07904.pdf,Semantically Decomposing the Latent Spaces of Generative Adversarial Networks,2017
-33,Canada,MsCeleb,msceleb,49.2767454,-122.91777375,Simon Fraser University,edu,b301fd2fc33f24d6f75224e7c0991f4f04b64a65,citation,https://arxiv.org/pdf/1803.06340.pdf,Faces as Lighting Probes via Unsupervised Deep Highlight Extraction,2018
-34,China,MsCeleb,msceleb,28.2290209,112.99483204,"National University of Defense Technology, China",mil,b301fd2fc33f24d6f75224e7c0991f4f04b64a65,citation,https://arxiv.org/pdf/1803.06340.pdf,Faces as Lighting Probes via Unsupervised Deep Highlight Extraction,2018
-35,United States,MsCeleb,msceleb,42.3614256,-71.0812092,Microsoft Research Asia,company,b301fd2fc33f24d6f75224e7c0991f4f04b64a65,citation,https://arxiv.org/pdf/1803.06340.pdf,Faces as Lighting Probes via Unsupervised Deep Highlight Extraction,2018
-36,United Kingdom,MsCeleb,msceleb,51.7534538,-1.25400997,University of Oxford,edu,70c59dc3470ae867016f6ab0e008ac8ba03774a1,citation,https://arxiv.org/pdf/1710.08092.pdf,VGGFace2: A Dataset for Recognising Faces across Pose and Age,2018
-37,China,MsCeleb,msceleb,39.9041999,116.4073963,"Beijing, China",edu,7fa4e972da46735971aad52413d17c4014c49e6e,citation,https://arxiv.org/pdf/1709.02940.pdf,How to Train Triplet Networks with 100K Identities?,2017
-38,China,MsCeleb,msceleb,39.94976005,116.33629046,Beijing Jiaotong University,edu,d7cbedbee06293e78661335c7dd9059c70143a28,citation,https://arxiv.org/pdf/1804.07573.pdf,MobileFaceNets: Efficient CNNs for Accurate Real-time Face Verification on Mobile Devices,2018
-39,Singapore,MsCeleb,msceleb,1.2962018,103.77689944,National University of Singapore,edu,fca9ebaa30d69ccec8bb577c31693c936c869e72,citation,https://arxiv.org/pdf/1809.00338.pdf,Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition,2018
-40,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,fca9ebaa30d69ccec8bb577c31693c936c869e72,citation,https://arxiv.org/pdf/1809.00338.pdf,Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition,2018
-41,Japan,MsCeleb,msceleb,35.6992503,139.7721568,"Hitachi, Ltd., Tokyo, Japan",company,3b4da93fbdf7ae520fa00d39ffa694e850b85162,citation,,Face-Voice Matching using Cross-modal Embeddings,2018
-42,China,MsCeleb,msceleb,30.19331415,120.11930822,Zhejiang University,edu,85860d38c66a5cf2e6ffd6475a3a2ba096ea2920,citation,,Celeb-500K: A Large Training Dataset for Face Recognition,2018
-43,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,6fed504da4e192fe4c2d452754d23d3db4a4e5e3,citation,https://arxiv.org/pdf/1702.06890.pdf,Learning Deep Features via Congenerous Cosine Loss for Person Recognition,2017
-44,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,6f5309d8cc76d3d300b72745887addd2a2480ba8,citation,,KinNet: Fine-to-Coarse Deep Metric Learning for Kinship Verification,2017
-45,China,MsCeleb,msceleb,40.00229045,116.32098908,Tsinghua University,edu,09ad80c4e80e1e02afb8fa4cb6dab260fb66df53,citation,,Feature Learning for One-Shot Face Recognition,2018
-46,United States,MsCeleb,msceleb,40.4441619,-79.94272826,Carnegie Mellon University,edu,c71217b2b111a51a31cf1107c71d250348d1ff68,citation,https://arxiv.org/pdf/1703.09912.pdf,One Network to Solve Them All — Solving Linear Inverse Problems Using Deep Projection Models,2017
-47,United Kingdom,MsCeleb,msceleb,51.7534538,-1.25400997,University of Oxford,edu,05ee231749c9ce97f036c71c1d2d599d660a8c81,citation,https://arxiv.org/pdf/1810.09951.pdf,GhostVLAD for set-based face recognition,2018
-48,United States,MsCeleb,msceleb,45.57022705,-122.63709346,Concordia University,edu,db374308655256da1479c272582d7c7139c97173,citation,https://arxiv.org/pdf/1811.11080.pdf,MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices,2018
-49,United States,MsCeleb,msceleb,33.5866784,-101.87539204,Electrical and Computer Engineering,edu,db374308655256da1479c272582d7c7139c97173,citation,https://arxiv.org/pdf/1811.11080.pdf,MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices,2018
-50,United States,MsCeleb,msceleb,36.0678324,-94.1736551,University of Arkansas,edu,db374308655256da1479c272582d7c7139c97173,citation,https://arxiv.org/pdf/1811.11080.pdf,MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices,2018
-51,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,de7d36173f9ca0e89e7a1991d541aed7c65127ea,citation,https://arxiv.org/pdf/1812.01288.pdf,FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis,2018
-52,China,MsCeleb,msceleb,22.59805605,113.98533784,Shenzhen Institutes of Advanced Technology,edu,de7d36173f9ca0e89e7a1991d541aed7c65127ea,citation,https://arxiv.org/pdf/1812.01288.pdf,FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis,2018
-53,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,212608e00fc1e8912ff845ee7a4a67f88ba938fc,citation,https://arxiv.org/pdf/1704.02450.pdf,Coupled Deep Learning for Heterogeneous Face Recognition,2018
-54,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,1fd5d08394a3278ef0a89639e9bfec7cb482e0bf,citation,https://arxiv.org/pdf/1804.03487.pdf,Exploring Disentangled Feature Representation Beyond Face Identification,2018
-55,China,MsCeleb,msceleb,39.993008,116.329882,SenseTime,company,1fd5d08394a3278ef0a89639e9bfec7cb482e0bf,citation,https://arxiv.org/pdf/1804.03487.pdf,Exploring Disentangled Feature Representation Beyond Face Identification,2018
-56,United States,MsCeleb,msceleb,40.8722825,-73.89489171,City University of New York,edu,f74917fc0e55f4f5682909dcf6929abd19d33e2e,citation,https://pdfs.semanticscholar.org/f749/17fc0e55f4f5682909dcf6929abd19d33e2e.pdf,GAN Q UALITY I NDEX ( GQI ) BY GAN-INDUCED C LASSIFIER,2018
-57,United States,MsCeleb,msceleb,42.3383668,-71.08793524,Northeastern University,edu,f74917fc0e55f4f5682909dcf6929abd19d33e2e,citation,https://pdfs.semanticscholar.org/f749/17fc0e55f4f5682909dcf6929abd19d33e2e.pdf,GAN Q UALITY I NDEX ( GQI ) BY GAN-INDUCED C LASSIFIER,2018
-58,United States,MsCeleb,msceleb,47.6423318,-122.1369302,Microsoft,company,f74917fc0e55f4f5682909dcf6929abd19d33e2e,citation,https://pdfs.semanticscholar.org/f749/17fc0e55f4f5682909dcf6929abd19d33e2e.pdf,GAN Q UALITY I NDEX ( GQI ) BY GAN-INDUCED C LASSIFIER,2018
-59,China,MsCeleb,msceleb,32.0565957,118.77408833,Nanjing University,edu,8ff8c64288a2f7e4e8bf8fda865820b04ab3dbe8,citation,https://pdfs.semanticscholar.org/0056/92b9fa6728df3a7f14578c43410867bba425.pdf,Age Estimation Using Expectation of Label Distribution Learning,2018
-60,China,MsCeleb,msceleb,32.0575279,118.78682252,Southeast University,edu,8ff8c64288a2f7e4e8bf8fda865820b04ab3dbe8,citation,https://pdfs.semanticscholar.org/0056/92b9fa6728df3a7f14578c43410867bba425.pdf,Age Estimation Using Expectation of Label Distribution Learning,2018
-61,United States,MsCeleb,msceleb,42.4505507,-76.4783513,Cornell University,edu,dec0c26855da90876c405e9fd42830c3051c2f5f,citation,https://pdfs.semanticscholar.org/dec0/c26855da90876c405e9fd42830c3051c2f5f.pdf,Supplementary Material : Learning Compositional Visual Concepts with Mutual Consistency,2018
-62,France,MsCeleb,msceleb,48.8476037,2.2639934,"Université Paris-Saclay, France",edu,96e318f8ff91ba0b10348d4de4cb7c2142eb8ba9,citation,,State-of-the-art face recognition performance using publicly available software and datasets,2018
-63,United States,MsCeleb,msceleb,29.7207902,-95.34406271,University of Houston,edu,38d8ff137ff753f04689e6b76119a44588e143f3,citation,https://arxiv.org/pdf/1709.06532.pdf,When 3D-Aided 2D Face Recognition Meets Deep Learning: An extended UR2D for Pose-Invariant Face Recognition,2017
-64,United States,MsCeleb,msceleb,38.0333742,-84.5017758,University of Kentucky,edu,455a7e03a0c5ab618d0e86a06c9910ac179f0479,citation,https://arxiv.org/pdf/1807.08772.pdf,Identity Preserving Face Completion for Large Ocular Region Occlusion,2018
-65,United States,MsCeleb,msceleb,34.0224149,-118.28634407,University of Southern California,edu,455a7e03a0c5ab618d0e86a06c9910ac179f0479,citation,https://arxiv.org/pdf/1807.08772.pdf,Identity Preserving Face Completion for Large Ocular Region Occlusion,2018
-66,China,MsCeleb,msceleb,45.7413921,126.62552755,Harbin Institute of Technology,edu,455a7e03a0c5ab618d0e86a06c9910ac179f0479,citation,https://arxiv.org/pdf/1807.08772.pdf,Identity Preserving Face Completion for Large Ocular Region Occlusion,2018
-67,China,MsCeleb,msceleb,30.289532,120.009886,Hangzhou Normal University,edu,455a7e03a0c5ab618d0e86a06c9910ac179f0479,citation,https://arxiv.org/pdf/1807.08772.pdf,Identity Preserving Face Completion for Large Ocular Region Occlusion,2018
-68,United Kingdom,MsCeleb,msceleb,51.49887085,-0.17560797,Imperial College London,edu,51992fa881541ca3a4520c1ff9100b83e2f1ad87,citation,https://arxiv.org/pdf/1801.07698.pdf,ArcFace: Additive Angular Margin Loss for Deep Face Recognition,2018
-69,United States,MsCeleb,msceleb,30.40550035,-91.18620474,Louisiana State University,edu,5b9c6ca84268cb283941ae28b73989c0cf7e2ac2,citation,,A Pipeline to Improve Face Recognition Datasets and Applications,2018
-70,Italy,MsCeleb,msceleb,45.814548,8.827665,University of Insubria,edu,5b9c6ca84268cb283941ae28b73989c0cf7e2ac2,citation,,A Pipeline to Improve Face Recognition Datasets and Applications,2018
-71,United States,MsCeleb,msceleb,42.3383668,-71.08793524,Northeastern University,edu,c9efcd8e32dced6efa2bba64789df8d0a8e4996a,citation,,Deep Convolutional Neural Network with Independent Softmax for Large Scale Face Recognition,2016
-72,United Kingdom,MsCeleb,msceleb,51.49887085,-0.17560797,Imperial College London,edu,9b0489f2d5739213ef8c3e2e18739c4353c3a3b7,citation,https://arxiv.org/pdf/1801.06665.pdf,Visual Data Augmentation through Learning,2018
-73,United Kingdom,MsCeleb,msceleb,51.59029705,-0.22963221,Middlesex University,edu,9b0489f2d5739213ef8c3e2e18739c4353c3a3b7,citation,https://arxiv.org/pdf/1801.06665.pdf,Visual Data Augmentation through Learning,2018
-74,United States,MsCeleb,msceleb,42.718568,-84.47791571,Michigan State University,edu,ad2cb5c255e555d9767d526721a4c7053fa2ac58,citation,https://arxiv.org/pdf/1711.03990.pdf,Longitudinal Study of Child Face Recognition,2018
-75,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,9e182e0cd9d70f876f1be7652c69373bcdf37fb4,citation,https://arxiv.org/pdf/1807.07860.pdf,Talking Face Generation by Adversarially Disentangled Audio-Visual Representation,2018
-76,United States,MsCeleb,msceleb,38.99203005,-76.9461029,University of Maryland College Park,edu,06bd34951305d9f36eb29cf4532b25272da0e677,citation,https://arxiv.org/pdf/1809.07586.pdf,"A Fast and Accurate System for Face Detection, Identification, and Verification",2018
-77,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,94f74c6314ffd02db581e8e887b5fd81ce288dbf,citation,https://arxiv.org/pdf/1511.02683.pdf,A Light CNN for Deep Face Representation With Noisy Labels,2018
-78,Spain,MsCeleb,msceleb,40.4167754,-3.7037902,"Computer Vision Group (www.vision4uav.com), Centro de Automática y Robótica (CAR) UPM-CSIC, Universidad Politécnica de Madrid, José Gutiérrez Abascal 2, 28006, Spain",edu,726f76f11e904d7fcb12736c276a0b00eb5cde49,citation,https://arxiv.org/pdf/1901.05903.pdf,A Performance Comparison of Loss Functions for Deep Face Recognition,2019
-79,India,MsCeleb,msceleb,13.5568171,80.0261283,"Indian Institute of Information Technology, Sri City, India",edu,726f76f11e904d7fcb12736c276a0b00eb5cde49,citation,https://arxiv.org/pdf/1901.05903.pdf,A Performance Comparison of Loss Functions for Deep Face Recognition,2019
-80,United States,MsCeleb,msceleb,38.99203005,-76.9461029,University of Maryland College Park,edu,83447d47bb2837b831b982ebf9e63616742bfdec,citation,https://arxiv.org/pdf/1812.04058.pdf,An Automatic System for Unconstrained Video-Based Face Recognition,2018
-81,United States,MsCeleb,msceleb,38.99203005,-76.9461029,University of Maryland College Park,edu,7323b594d3a8508f809e276aa2d224c4e7ec5a80,citation,https://arxiv.org/pdf/1808.05508.pdf,An Experimental Evaluation of Covariates Effects on Unconstrained Face Verification,2018
-82,United States,MsCeleb,msceleb,43.7192587,10.4207947,"CNR ISTI-Institute of Information Science and Technologies, Pisa, Italy",edu,266766818dbc5a4ca1161ae2bc14c9e269ddc490,citation,https://pdfs.semanticscholar.org/2667/66818dbc5a4ca1161ae2bc14c9e269ddc490.pdf,Boosting a Low-Cost Smart Home Environment with Usage and Access Control Rules,2018
-83,United States,MsCeleb,msceleb,38.99203005,-76.9461029,University of Maryland College Park,edu,944ea33211d67663e04d0181843db634e42cb2ca,citation,https://arxiv.org/pdf/1804.01159.pdf,Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition.,2018
-84,Taiwan,MsCeleb,msceleb,25.01682835,121.53846924,National Taiwan University,edu,f15b7c317f106816bf444ac4ffb6c280cd6392c7,citation,http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w1/Zhang_Deep_Disguised_Faces_CVPR_2018_paper.pdf,Deep Disguised Faces Recognition,2018
-85,United States,MsCeleb,msceleb,38.99203005,-76.9461029,University of Maryland College Park,edu,a50fa5048c61209149de0711b5f1b1806b43da00,citation,http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w1/Bansal_Deep_Features_for_CVPR_2018_paper.pdf,Deep Features for Recognizing Disguised Faces in the Wild,2018
-86,China,MsCeleb,msceleb,40.00229045,116.32098908,Tsinghua University,edu,19d53bb35baf6ab02368756412800c218a2df71c,citation,https://arxiv.org/pdf/1711.09515.pdf,DeepDeblur: Fast one-step blurry face images restoration.,2017
-87,United States,MsCeleb,msceleb,42.718568,-84.47791571,Michigan State University,edu,12ba7c6f559a69fbfaacf61bfb2f8431505b09a0,citation,https://arxiv.org/pdf/1809.05620.pdf,DocFace+: ID Document to Selfie Matching,2018
-88,South Korea,MsCeleb,msceleb,37.5600406,126.9369248,Yonsei University,edu,d8526863f35b29cbf8ac2ae756eaae0d2930ffb1,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Choe_Face_Generation_for_ICCV_2017_paper.pdf,Face Generation for Low-Shot Learning Using Generative Adversarial Networks,2017
-89,China,MsCeleb,msceleb,38.880381,121.529021,Dailian University of Technology,edu,59fc69b3bc4759eef1347161e1248e886702f8f7,citation,https://pdfs.semanticscholar.org/59fc/69b3bc4759eef1347161e1248e886702f8f7.pdf,Final Report of Final Year Project HKU-Face : A Large Scale Dataset for Deep Face Recognition,2018
-90,Germany,MsCeleb,msceleb,52.381515,9.720171,"Leibniz Information Centre for Science and Technology, Hannover, Germany",edu,5209758096819efee15751c8875121bd27f2ee78,citation,https://arxiv.org/pdf/1806.08246.pdf,Finding Person Relations in Image Data of the Internet Archive,2018
-91,Germany,MsCeleb,msceleb,52.381515,9.720171,Leibniz Universität Hannover,edu,5209758096819efee15751c8875121bd27f2ee78,citation,https://arxiv.org/pdf/1806.08246.pdf,Finding Person Relations in Image Data of the Internet Archive,2018
-92,China,MsCeleb,msceleb,35.86166,104.195397,"Megvii Inc. (Face++), China",company,4874daed0f6a42d03011ed86e5ab46f231b02c13,citation,https://arxiv.org/pdf/1808.06210.pdf,GridFace: Face Rectification via Learning Local Homography Transformations,2018
-93,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,a89cbc90bbb4477a48aec185f2a112ea7ebe9b4d,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Xu_High_Performance_Large_ICCV_2017_paper.pdf,High Performance Large Scale Face Recognition with Multi-cognition Softmax and Feature Retrieval,2017
-94,Singapore,MsCeleb,msceleb,1.2962018,103.77689944,National University of Singapore,edu,a89cbc90bbb4477a48aec185f2a112ea7ebe9b4d,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Xu_High_Performance_Large_ICCV_2017_paper.pdf,High Performance Large Scale Face Recognition with Multi-cognition Softmax and Feature Retrieval,2017
-95,Singapore,MsCeleb,msceleb,1.3392609,103.8916077,Panasonic Singapore,company,a89cbc90bbb4477a48aec185f2a112ea7ebe9b4d,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Xu_High_Performance_Large_ICCV_2017_paper.pdf,High Performance Large Scale Face Recognition with Multi-cognition Softmax and Feature Retrieval,2017
-96,United States,MsCeleb,msceleb,40.8722825,-73.89489171,City University of New York,edu,32aeb90992f6cf8494b1b5c67f4b912feef05e9c,citation,https://arxiv.org/pdf/1802.00853.pdf,Incremental Classifier Learning with Generative Adversarial Networks,2018
-97,United States,MsCeleb,msceleb,47.6423318,-122.1369302,Microsoft,company,32aeb90992f6cf8494b1b5c67f4b912feef05e9c,citation,https://arxiv.org/pdf/1802.00853.pdf,Incremental Classifier Learning with Generative Adversarial Networks,2018
-98,United States,MsCeleb,msceleb,42.3383668,-71.08793524,Northeastern University,edu,32aeb90992f6cf8494b1b5c67f4b912feef05e9c,citation,https://arxiv.org/pdf/1802.00853.pdf,Incremental Classifier Learning with Generative Adversarial Networks,2018
-99,Singapore,MsCeleb,msceleb,1.2962018,103.77689944,National University of Singapore,edu,c808c784237f167c78a87cc5a9d48152579c27a4,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Cheng_Know_You_at_ICCV_2017_paper.pdf,Know You at One Glance: A Compact Vector Representation for Low-Shot Learning,2017
-100,Singapore,MsCeleb,msceleb,1.3392609,103.8916077,Panasonic Singapore,company,c808c784237f167c78a87cc5a9d48152579c27a4,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Cheng_Know_You_at_ICCV_2017_paper.pdf,Know You at One Glance: A Compact Vector Representation for Low-Shot Learning,2017
-101,United States,MsCeleb,msceleb,42.3383668,-71.08793524,Northeastern University,edu,332548fd2e52b27e062bd6dcc1db0953ced6ed48,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Wu_Low-Shot_Face_Recognition_ICCV_2017_paper.pdf,Low-Shot Face Recognition with Hybrid Classifiers,2017
-102,United States,MsCeleb,msceleb,40.4441619,-79.94272826,Carnegie Mellon University,edu,98b2f21db344b8b9f7747feaf86f92558595990c,citation,https://pdfs.semanticscholar.org/98b2/f21db344b8b9f7747feaf86f92558595990c.pdf,PACES OF G ENERATIVE A DVERSARIAL N ETWORKS,2018
-103,United States,MsCeleb,msceleb,37.43131385,-122.16936535,Stanford University,edu,98b2f21db344b8b9f7747feaf86f92558595990c,citation,https://pdfs.semanticscholar.org/98b2/f21db344b8b9f7747feaf86f92558595990c.pdf,PACES OF G ENERATIVE A DVERSARIAL N ETWORKS,2018
-104,United States,MsCeleb,msceleb,32.87935255,-117.23110049,"University of California, San Diego",edu,98b2f21db344b8b9f7747feaf86f92558595990c,citation,https://pdfs.semanticscholar.org/98b2/f21db344b8b9f7747feaf86f92558595990c.pdf,PACES OF G ENERATIVE A DVERSARIAL N ETWORKS,2018
-105,China,MsCeleb,msceleb,22.5283157,113.94481,Shenzhen Institute of Wuhan University,edu,e13360cda1ebd6fa5c3f3386c0862f292e4dbee4,citation,https://arxiv.org/pdf/1611.08976.pdf,Range Loss for Deep Face Recognition with Long-Tailed Training Data,2016
-106,Australia,MsCeleb,msceleb,-33.8832376,151.2004942,Southern University of Science and Technology,edu,e13360cda1ebd6fa5c3f3386c0862f292e4dbee4,citation,https://arxiv.org/pdf/1611.08976.pdf,Range Loss for Deep Face Recognition with Long-Tailed Training Data,2016
-107,China,MsCeleb,msceleb,36.20304395,117.05842113,Tianjin University,edu,e13360cda1ebd6fa5c3f3386c0862f292e4dbee4,citation,https://arxiv.org/pdf/1611.08976.pdf,Range Loss for Deep Face Recognition with Long-Tailed Training Data,2016
-108,United Kingdom,MsCeleb,msceleb,51.49887085,-0.17560797,Imperial College London,edu,b26d5d929cc3c0d14da058961ddd024f4c9690f5,citation,https://arxiv.org/pdf/1805.08657.pdf,Robust Conditional Generative Adversarial Networks,2018
-109,France,MsCeleb,msceleb,46.1464423,-1.1570872,La Rochelle University,edu,5c54e0f46330787c4fac48aecced9a8f8e37658a,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w23/Ming_Simple_Triplet_Loss_ICCV_2017_paper.pdf,Simple Triplet Loss Based on Intra/Inter-Class Metric Learning for Face Verification,2017
-110,China,MsCeleb,msceleb,39.9922379,116.30393816,Peking University,edu,4f0b641860d90dfa4c185670bf636149a2b2b717,citation,,Improve Cross-Domain Face Recognition with IBN-block,2018
-111,China,MsCeleb,msceleb,31.83907195,117.26420748,University of Science and Technology of China,edu,c5b324f7f9abdffc1be83f640674beda81b74315,citation,,Towards Open-Set Identity Preserving Face Synthesis,2018
-112,Italy,MsCeleb,msceleb,44.6451046,10.9279268,University of Modena and Reggio Emilia,edu,ff44d8938c52cfdca48c80f8e1618bbcbf91cb2a,citation,https://pdfs.semanticscholar.org/ff44/d8938c52cfdca48c80f8e1618bbcbf91cb2a.pdf,Towards Video Captioning with Naming: A Novel Dataset and a Multi-modal Approach,2017
-113,France,MsCeleb,msceleb,45.7833631,4.76877036,Ecole Centrale de Lyon,edu,727d03100d4a8e12620acd7b1d1972bbee54f0e6,citation,https://arxiv.org/pdf/1706.04264.pdf,von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification,2017
-114,France,MsCeleb,msceleb,48.832493,2.267474,Safran Identity and Security,company,727d03100d4a8e12620acd7b1d1972bbee54f0e6,citation,https://arxiv.org/pdf/1706.04264.pdf,von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification,2017
-115,China,MsCeleb,msceleb,39.980196,116.333305,"CASIA, Center for Research on Intelligent Perception and Computing, Beijing, 100190, China",edu,3ac09c2589178dac0b6a2ea2edf04b7629672d81,citation,https://arxiv.org/pdf/1708.02412.pdf,Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition,2018
-116,China,MsCeleb,msceleb,39.979203,116.33287,"CASIA, National Laboratory of Pattern Recognition",edu,3ac09c2589178dac0b6a2ea2edf04b7629672d81,citation,https://arxiv.org/pdf/1708.02412.pdf,Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition,2018
-117,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,3ac09c2589178dac0b6a2ea2edf04b7629672d81,citation,https://arxiv.org/pdf/1708.02412.pdf,Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition,2018
-118,United States,MsCeleb,msceleb,38.99203005,-76.9461029,University of Maryland College Park,edu,b35ff9985aaee9371588330bcef0dfc88d1401d7,citation,,Deep Density Clustering of Unconstrained Faces,2018
-119,United States,MsCeleb,msceleb,30.6108365,-96.352128,Texas A&M University,edu,e36fdb50844132fc7925550398e68e7ae95467de,citation,,Face Verification with Disguise Variations via Deep Disguise Recognizer,2018
-120,United States,MsCeleb,msceleb,39.65404635,-79.96475355,West Virginia University,edu,e36fdb50844132fc7925550398e68e7ae95467de,citation,,Face Verification with Disguise Variations via Deep Disguise Recognizer,2018
-121,United States,MsCeleb,msceleb,42.4505507,-76.4783513,Cornell University,edu,9ccf528ef8df99372ce6286ffbb0bf6f9a505cca,citation,,Learning Compositional Visual Concepts with Mutual Consistency,2018
-122,United States,MsCeleb,msceleb,40.3442079,-74.5924599,"Siemens Corporate Research, Princeton, NJ",edu,9ccf528ef8df99372ce6286ffbb0bf6f9a505cca,citation,,Learning Compositional Visual Concepts with Mutual Consistency,2018
-123,United States,MsCeleb,msceleb,42.3383668,-71.08793524,Northeastern University,edu,3827f1cab643a57e3cd22fbffbf19dd5e8a298a8,citation,,One-Shot Face Recognition via Generative Learning,2018
-124,China,MsCeleb,msceleb,39.9106327,116.3356321,Chinese Academy of Science,edu,20f87ed94a423b5d8599d85d1f2f80bab8902107,citation,,Pose-Guided Photorealistic Face Rotation,2018
-125,United States,MsCeleb,msceleb,40.4441619,-79.94272826,Carnegie Mellon University,edu,67a9659de0bf671fafccd7f39b7587f85fb6dfbd,citation,,Ring Loss: Convex Feature Normalization for Face Recognition,2018
+4,France,MsCeleb,msceleb,46.1476461,-1.1549415,University of La Rochelle,edu,153fbae25efd061f9046970071d0cfe739a35a0e,citation,,FaceLiveNet: End-to-End Networks Combining Face Verification with Interactive Facial Expression-Based Liveness Detection,2018
+5,China,MsCeleb,msceleb,26.89887,112.590435,University of South China,edu,98518fc368d7e1478cef40f5f8fd4468763645ad,citation,http://downloads.hindawi.com/journals/cin/2018/4512473.pdf,A Community Detection Approach to Cleaning Extremely Large Face Database,2018
+6,China,MsCeleb,msceleb,28.2290209,112.99483204,"National University of Defense Technology, China",mil,98518fc368d7e1478cef40f5f8fd4468763645ad,citation,http://downloads.hindawi.com/journals/cin/2018/4512473.pdf,A Community Detection Approach to Cleaning Extremely Large Face Database,2018
+7,China,MsCeleb,msceleb,39.9601488,116.35193921,Beijing University of Posts and Telecommunications,edu,6cdbbced12bff53bcbdde3cdb6d20b4bd02a9d6c,citation,https://arxiv.org/pdf/1811.12026.pdf,Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network,2018
+8,China,MsCeleb,msceleb,39.98177,116.330086,National Laboratory of Pattern Recognition,edu,e47f4a127f41c055fb7893ddc295932ead783c63,citation,https://arxiv.org/pdf/1709.03675.pdf,Adversarial Discriminative Heterogeneous Face Recognition,2018
+9,China,MsCeleb,msceleb,39.9082804,116.2458527,University of Chinese Academy of Sciences,edu,e47f4a127f41c055fb7893ddc295932ead783c63,citation,https://arxiv.org/pdf/1709.03675.pdf,Adversarial Discriminative Heterogeneous Face Recognition,2018
+10,United States,MsCeleb,msceleb,42.718568,-84.47791571,Michigan State University,edu,b446bcd7fb78adfe346cf7a01a38e4f43760f363,citation,https://pdfs.semanticscholar.org/b446/bcd7fb78adfe346cf7a01a38e4f43760f363.pdf,To appear in ICB 2018 Longitudinal Study of Child Face Recognition,2017
+11,United Kingdom,MsCeleb,msceleb,51.3791442,-2.3252332,University of Bath,edu,26567da544239cc6628c5696b0b10539144cbd57,citation,https://arxiv.org/pdf/1811.12784.pdf,The GAN that Warped: Semantic Attribute Editing with Unpaired Data,2018
+12,United States,MsCeleb,msceleb,39.2899685,-76.62196103,University of Maryland,edu,872dfdeccf99bbbed7c8f1ea08afb2d713ebe085,citation,https://arxiv.org/pdf/1703.09507.pdf,L2-constrained Softmax Loss for Discriminative Face Verification,2017
+13,United States,MsCeleb,msceleb,42.718568,-84.47791571,Michigan State University,edu,3011b5fce49112228711a9e5f92d6f191687c1ea,citation,https://arxiv.org/pdf/1803.09014.pdf,Feature Transfer Learning for Deep Face Recognition with Long-Tail Data,2018
+14,United Kingdom,MsCeleb,msceleb,51.49887085,-0.17560797,Imperial College London,edu,1929863fff917ee7f6dc428fc1ce732777668eca,citation,https://arxiv.org/pdf/1712.04695.pdf,UV-GAN: Adversarial Facial UV Map Completion for Pose-Invariant Face Recognition,2018
+15,United States,MsCeleb,msceleb,39.2899685,-76.62196103,University of Maryland,edu,b6f758be954d34817d4ebaa22b30c63a4b8ddb35,citation,https://arxiv.org/pdf/1703.04835.pdf,A Proximity-Aware Hierarchical Clustering of Faces,2017
+16,United States,MsCeleb,msceleb,42.718568,-84.47791571,Michigan State University,edu,19fa871626df604639550c6445d2f76cd369dd13,citation,https://arxiv.org/pdf/1805.02283.pdf,DocFace: Matching ID Document Photos to Selfies,2018
+17,United States,MsCeleb,msceleb,32.87935255,-117.23110049,"University of California, San Diego",edu,d35534f3f59631951011539da2fe83f2844ca245,citation,https://arxiv.org/pdf/1705.07904.pdf,Semantically Decomposing the Latent Spaces of Generative Adversarial Networks,2017
+18,United States,MsCeleb,msceleb,37.43131385,-122.16936535,Stanford University,edu,d35534f3f59631951011539da2fe83f2844ca245,citation,https://arxiv.org/pdf/1705.07904.pdf,Semantically Decomposing the Latent Spaces of Generative Adversarial Networks,2017
+19,United States,MsCeleb,msceleb,40.4441619,-79.94272826,Carnegie Mellon University,edu,d35534f3f59631951011539da2fe83f2844ca245,citation,https://arxiv.org/pdf/1705.07904.pdf,Semantically Decomposing the Latent Spaces of Generative Adversarial Networks,2017
+20,Canada,MsCeleb,msceleb,49.2767454,-122.91777375,Simon Fraser University,edu,b301fd2fc33f24d6f75224e7c0991f4f04b64a65,citation,https://arxiv.org/pdf/1803.06340.pdf,Faces as Lighting Probes via Unsupervised Deep Highlight Extraction,2018
+21,China,MsCeleb,msceleb,28.2290209,112.99483204,"National University of Defense Technology, China",mil,b301fd2fc33f24d6f75224e7c0991f4f04b64a65,citation,https://arxiv.org/pdf/1803.06340.pdf,Faces as Lighting Probes via Unsupervised Deep Highlight Extraction,2018
+22,United States,MsCeleb,msceleb,42.3614256,-71.0812092,Microsoft Research Asia,company,b301fd2fc33f24d6f75224e7c0991f4f04b64a65,citation,https://arxiv.org/pdf/1803.06340.pdf,Faces as Lighting Probes via Unsupervised Deep Highlight Extraction,2018
+23,China,MsCeleb,msceleb,39.9041999,116.4073963,"Beijing, China",edu,7fa4e972da46735971aad52413d17c4014c49e6e,citation,https://arxiv.org/pdf/1709.02940.pdf,How to Train Triplet Networks with 100K Identities?,2017
+24,Singapore,MsCeleb,msceleb,1.2962018,103.77689944,National University of Singapore,edu,fca9ebaa30d69ccec8bb577c31693c936c869e72,citation,https://arxiv.org/pdf/1809.00338.pdf,Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition,2018
+25,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,fca9ebaa30d69ccec8bb577c31693c936c869e72,citation,https://arxiv.org/pdf/1809.00338.pdf,Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition,2018
+26,Japan,MsCeleb,msceleb,35.6992503,139.7721568,"Hitachi, Ltd., Tokyo, Japan",company,3b4da93fbdf7ae520fa00d39ffa694e850b85162,citation,,Face-Voice Matching using Cross-modal Embeddings,2018
+27,China,MsCeleb,msceleb,30.19331415,120.11930822,Zhejiang University,edu,85860d38c66a5cf2e6ffd6475a3a2ba096ea2920,citation,,Celeb-500K: A Large Training Dataset for Face Recognition,2018
+28,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,6f5309d8cc76d3d300b72745887addd2a2480ba8,citation,,KinNet: Fine-to-Coarse Deep Metric Learning for Kinship Verification,2017
+29,China,MsCeleb,msceleb,40.00229045,116.32098908,Tsinghua University,edu,09ad80c4e80e1e02afb8fa4cb6dab260fb66df53,citation,,Feature Learning for One-Shot Face Recognition,2018
+30,United States,MsCeleb,msceleb,40.4441619,-79.94272826,Carnegie Mellon University,edu,c71217b2b111a51a31cf1107c71d250348d1ff68,citation,https://arxiv.org/pdf/1703.09912.pdf,One Network to Solve Them All — Solving Linear Inverse Problems Using Deep Projection Models,2017
+31,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,de7d36173f9ca0e89e7a1991d541aed7c65127ea,citation,https://arxiv.org/pdf/1812.01288.pdf,FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis,2018
+32,China,MsCeleb,msceleb,22.59805605,113.98533784,Shenzhen Institutes of Advanced Technology,edu,de7d36173f9ca0e89e7a1991d541aed7c65127ea,citation,https://arxiv.org/pdf/1812.01288.pdf,FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis,2018
+33,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,212608e00fc1e8912ff845ee7a4a67f88ba938fc,citation,https://arxiv.org/pdf/1704.02450.pdf,Coupled Deep Learning for Heterogeneous Face Recognition,2018
+34,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,1fd5d08394a3278ef0a89639e9bfec7cb482e0bf,citation,https://arxiv.org/pdf/1804.03487.pdf,Exploring Disentangled Feature Representation Beyond Face Identification,2018
+35,China,MsCeleb,msceleb,39.993008,116.329882,SenseTime,company,1fd5d08394a3278ef0a89639e9bfec7cb482e0bf,citation,https://arxiv.org/pdf/1804.03487.pdf,Exploring Disentangled Feature Representation Beyond Face Identification,2018
+36,United States,MsCeleb,msceleb,40.8722825,-73.89489171,City University of New York,edu,f74917fc0e55f4f5682909dcf6929abd19d33e2e,citation,https://pdfs.semanticscholar.org/f749/17fc0e55f4f5682909dcf6929abd19d33e2e.pdf,GAN Q UALITY I NDEX ( GQI ) BY GAN-INDUCED C LASSIFIER,2018
+37,United States,MsCeleb,msceleb,42.3383668,-71.08793524,Northeastern University,edu,f74917fc0e55f4f5682909dcf6929abd19d33e2e,citation,https://pdfs.semanticscholar.org/f749/17fc0e55f4f5682909dcf6929abd19d33e2e.pdf,GAN Q UALITY I NDEX ( GQI ) BY GAN-INDUCED C LASSIFIER,2018
+38,United States,MsCeleb,msceleb,47.6423318,-122.1369302,Microsoft,company,f74917fc0e55f4f5682909dcf6929abd19d33e2e,citation,https://pdfs.semanticscholar.org/f749/17fc0e55f4f5682909dcf6929abd19d33e2e.pdf,GAN Q UALITY I NDEX ( GQI ) BY GAN-INDUCED C LASSIFIER,2018
+39,China,MsCeleb,msceleb,32.0565957,118.77408833,Nanjing University,edu,8ff8c64288a2f7e4e8bf8fda865820b04ab3dbe8,citation,https://pdfs.semanticscholar.org/0056/92b9fa6728df3a7f14578c43410867bba425.pdf,Age Estimation Using Expectation of Label Distribution Learning,2018
+40,China,MsCeleb,msceleb,32.0575279,118.78682252,Southeast University,edu,8ff8c64288a2f7e4e8bf8fda865820b04ab3dbe8,citation,https://pdfs.semanticscholar.org/0056/92b9fa6728df3a7f14578c43410867bba425.pdf,Age Estimation Using Expectation of Label Distribution Learning,2018
+41,United States,MsCeleb,msceleb,42.4505507,-76.4783513,Cornell University,edu,dec0c26855da90876c405e9fd42830c3051c2f5f,citation,https://pdfs.semanticscholar.org/dec0/c26855da90876c405e9fd42830c3051c2f5f.pdf,Supplementary Material : Learning Compositional Visual Concepts with Mutual Consistency,2018
+42,France,MsCeleb,msceleb,48.8476037,2.2639934,"Université Paris-Saclay, France",edu,96e318f8ff91ba0b10348d4de4cb7c2142eb8ba9,citation,,State-of-the-art face recognition performance using publicly available software and datasets,2018
+43,United States,MsCeleb,msceleb,29.7207902,-95.34406271,University of Houston,edu,38d8ff137ff753f04689e6b76119a44588e143f3,citation,https://arxiv.org/pdf/1709.06532.pdf,When 3D-Aided 2D Face Recognition Meets Deep Learning: An extended UR2D for Pose-Invariant Face Recognition,2017
+44,United States,MsCeleb,msceleb,38.0333742,-84.5017758,University of Kentucky,edu,455a7e03a0c5ab618d0e86a06c9910ac179f0479,citation,https://arxiv.org/pdf/1807.08772.pdf,Identity Preserving Face Completion for Large Ocular Region Occlusion,2018
+45,United States,MsCeleb,msceleb,34.0224149,-118.28634407,University of Southern California,edu,455a7e03a0c5ab618d0e86a06c9910ac179f0479,citation,https://arxiv.org/pdf/1807.08772.pdf,Identity Preserving Face Completion for Large Ocular Region Occlusion,2018
+46,China,MsCeleb,msceleb,45.7413921,126.62552755,Harbin Institute of Technology,edu,455a7e03a0c5ab618d0e86a06c9910ac179f0479,citation,https://arxiv.org/pdf/1807.08772.pdf,Identity Preserving Face Completion for Large Ocular Region Occlusion,2018
+47,China,MsCeleb,msceleb,30.289532,120.009886,Hangzhou Normal University,edu,455a7e03a0c5ab618d0e86a06c9910ac179f0479,citation,https://arxiv.org/pdf/1807.08772.pdf,Identity Preserving Face Completion for Large Ocular Region Occlusion,2018
+48,United States,MsCeleb,msceleb,42.3383668,-71.08793524,Northeastern University,edu,c9efcd8e32dced6efa2bba64789df8d0a8e4996a,citation,,Deep Convolutional Neural Network with Independent Softmax for Large Scale Face Recognition,2016
+49,United Kingdom,MsCeleb,msceleb,51.49887085,-0.17560797,Imperial College London,edu,9b0489f2d5739213ef8c3e2e18739c4353c3a3b7,citation,https://arxiv.org/pdf/1801.06665.pdf,Visual Data Augmentation through Learning,2018
+50,United Kingdom,MsCeleb,msceleb,51.59029705,-0.22963221,Middlesex University,edu,9b0489f2d5739213ef8c3e2e18739c4353c3a3b7,citation,https://arxiv.org/pdf/1801.06665.pdf,Visual Data Augmentation through Learning,2018
+51,United States,MsCeleb,msceleb,42.718568,-84.47791571,Michigan State University,edu,ad2cb5c255e555d9767d526721a4c7053fa2ac58,citation,https://arxiv.org/pdf/1711.03990.pdf,Longitudinal Study of Child Face Recognition,2018
+52,China,MsCeleb,msceleb,22.4162632,114.2109318,Chinese University of Hong Kong,edu,9e182e0cd9d70f876f1be7652c69373bcdf37fb4,citation,https://arxiv.org/pdf/1807.07860.pdf,Talking Face Generation by Adversarially Disentangled Audio-Visual Representation,2018
+53,United States,MsCeleb,msceleb,38.99203005,-76.9461029,University of Maryland College Park,edu,83447d47bb2837b831b982ebf9e63616742bfdec,citation,https://arxiv.org/pdf/1812.04058.pdf,An Automatic System for Unconstrained Video-Based Face Recognition,2018
+54,United States,MsCeleb,msceleb,43.7192587,10.4207947,"CNR ISTI-Institute of Information Science and Technologies, Pisa, Italy",edu,266766818dbc5a4ca1161ae2bc14c9e269ddc490,citation,https://pdfs.semanticscholar.org/2667/66818dbc5a4ca1161ae2bc14c9e269ddc490.pdf,Boosting a Low-Cost Smart Home Environment with Usage and Access Control Rules,2018
+55,United States,MsCeleb,msceleb,38.99203005,-76.9461029,University of Maryland College Park,edu,944ea33211d67663e04d0181843db634e42cb2ca,citation,https://arxiv.org/pdf/1804.01159.pdf,Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition.,2018
+56,Taiwan,MsCeleb,msceleb,25.01682835,121.53846924,National Taiwan University,edu,f15b7c317f106816bf444ac4ffb6c280cd6392c7,citation,http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w1/Zhang_Deep_Disguised_Faces_CVPR_2018_paper.pdf,Deep Disguised Faces Recognition,2018
+57,China,MsCeleb,msceleb,40.00229045,116.32098908,Tsinghua University,edu,19d53bb35baf6ab02368756412800c218a2df71c,citation,https://arxiv.org/pdf/1711.09515.pdf,DeepDeblur: Fast one-step blurry face images restoration.,2017
+58,United States,MsCeleb,msceleb,42.718568,-84.47791571,Michigan State University,edu,12ba7c6f559a69fbfaacf61bfb2f8431505b09a0,citation,https://arxiv.org/pdf/1809.05620.pdf,DocFace+: ID Document to Selfie Matching,2018
+59,South Korea,MsCeleb,msceleb,37.5600406,126.9369248,Yonsei University,edu,d8526863f35b29cbf8ac2ae756eaae0d2930ffb1,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Choe_Face_Generation_for_ICCV_2017_paper.pdf,Face Generation for Low-Shot Learning Using Generative Adversarial Networks,2017
+60,Germany,MsCeleb,msceleb,52.381515,9.720171,"Leibniz Information Centre for Science and Technology, Hannover, Germany",edu,5209758096819efee15751c8875121bd27f2ee78,citation,https://arxiv.org/pdf/1806.08246.pdf,Finding Person Relations in Image Data of the Internet Archive,2018
+61,Germany,MsCeleb,msceleb,52.381515,9.720171,Leibniz Universität Hannover,edu,5209758096819efee15751c8875121bd27f2ee78,citation,https://arxiv.org/pdf/1806.08246.pdf,Finding Person Relations in Image Data of the Internet Archive,2018
+62,China,MsCeleb,msceleb,35.86166,104.195397,"Megvii Inc. (Face++), China",company,4874daed0f6a42d03011ed86e5ab46f231b02c13,citation,https://arxiv.org/pdf/1808.06210.pdf,GridFace: Face Rectification via Learning Local Homography Transformations,2018
+63,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,a89cbc90bbb4477a48aec185f2a112ea7ebe9b4d,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Xu_High_Performance_Large_ICCV_2017_paper.pdf,High Performance Large Scale Face Recognition with Multi-cognition Softmax and Feature Retrieval,2017
+64,Singapore,MsCeleb,msceleb,1.2962018,103.77689944,National University of Singapore,edu,a89cbc90bbb4477a48aec185f2a112ea7ebe9b4d,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Xu_High_Performance_Large_ICCV_2017_paper.pdf,High Performance Large Scale Face Recognition with Multi-cognition Softmax and Feature Retrieval,2017
+65,Singapore,MsCeleb,msceleb,1.3392609,103.8916077,Panasonic Singapore,company,a89cbc90bbb4477a48aec185f2a112ea7ebe9b4d,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Xu_High_Performance_Large_ICCV_2017_paper.pdf,High Performance Large Scale Face Recognition with Multi-cognition Softmax and Feature Retrieval,2017
+66,United States,MsCeleb,msceleb,40.8722825,-73.89489171,City University of New York,edu,32aeb90992f6cf8494b1b5c67f4b912feef05e9c,citation,https://arxiv.org/pdf/1802.00853.pdf,Incremental Classifier Learning with Generative Adversarial Networks,2018
+67,United States,MsCeleb,msceleb,47.6423318,-122.1369302,Microsoft,company,32aeb90992f6cf8494b1b5c67f4b912feef05e9c,citation,https://arxiv.org/pdf/1802.00853.pdf,Incremental Classifier Learning with Generative Adversarial Networks,2018
+68,United States,MsCeleb,msceleb,42.3383668,-71.08793524,Northeastern University,edu,32aeb90992f6cf8494b1b5c67f4b912feef05e9c,citation,https://arxiv.org/pdf/1802.00853.pdf,Incremental Classifier Learning with Generative Adversarial Networks,2018
+69,Singapore,MsCeleb,msceleb,1.2962018,103.77689944,National University of Singapore,edu,c808c784237f167c78a87cc5a9d48152579c27a4,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Cheng_Know_You_at_ICCV_2017_paper.pdf,Know You at One Glance: A Compact Vector Representation for Low-Shot Learning,2017
+70,Singapore,MsCeleb,msceleb,1.3392609,103.8916077,Panasonic Singapore,company,c808c784237f167c78a87cc5a9d48152579c27a4,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Cheng_Know_You_at_ICCV_2017_paper.pdf,Know You at One Glance: A Compact Vector Representation for Low-Shot Learning,2017
+71,United States,MsCeleb,msceleb,42.3383668,-71.08793524,Northeastern University,edu,332548fd2e52b27e062bd6dcc1db0953ced6ed48,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Wu_Low-Shot_Face_Recognition_ICCV_2017_paper.pdf,Low-Shot Face Recognition with Hybrid Classifiers,2017
+72,United States,MsCeleb,msceleb,40.4441619,-79.94272826,Carnegie Mellon University,edu,98b2f21db344b8b9f7747feaf86f92558595990c,citation,https://pdfs.semanticscholar.org/98b2/f21db344b8b9f7747feaf86f92558595990c.pdf,PACES OF G ENERATIVE A DVERSARIAL N ETWORKS,2018
+73,United States,MsCeleb,msceleb,37.43131385,-122.16936535,Stanford University,edu,98b2f21db344b8b9f7747feaf86f92558595990c,citation,https://pdfs.semanticscholar.org/98b2/f21db344b8b9f7747feaf86f92558595990c.pdf,PACES OF G ENERATIVE A DVERSARIAL N ETWORKS,2018
+74,United States,MsCeleb,msceleb,32.87935255,-117.23110049,"University of California, San Diego",edu,98b2f21db344b8b9f7747feaf86f92558595990c,citation,https://pdfs.semanticscholar.org/98b2/f21db344b8b9f7747feaf86f92558595990c.pdf,PACES OF G ENERATIVE A DVERSARIAL N ETWORKS,2018
+75,China,MsCeleb,msceleb,22.5283157,113.94481,Shenzhen Institute of Wuhan University,edu,e13360cda1ebd6fa5c3f3386c0862f292e4dbee4,citation,https://arxiv.org/pdf/1611.08976.pdf,Range Loss for Deep Face Recognition with Long-Tailed Training Data,2016
+76,Australia,MsCeleb,msceleb,-33.8832376,151.2004942,Southern University of Science and Technology,edu,e13360cda1ebd6fa5c3f3386c0862f292e4dbee4,citation,https://arxiv.org/pdf/1611.08976.pdf,Range Loss for Deep Face Recognition with Long-Tailed Training Data,2016
+77,China,MsCeleb,msceleb,36.20304395,117.05842113,Tianjin University,edu,e13360cda1ebd6fa5c3f3386c0862f292e4dbee4,citation,https://arxiv.org/pdf/1611.08976.pdf,Range Loss for Deep Face Recognition with Long-Tailed Training Data,2016
+78,United Kingdom,MsCeleb,msceleb,51.49887085,-0.17560797,Imperial College London,edu,b26d5d929cc3c0d14da058961ddd024f4c9690f5,citation,https://arxiv.org/pdf/1805.08657.pdf,Robust Conditional Generative Adversarial Networks,2018
+79,France,MsCeleb,msceleb,46.1464423,-1.1570872,La Rochelle University,edu,5c54e0f46330787c4fac48aecced9a8f8e37658a,citation,http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w23/Ming_Simple_Triplet_Loss_ICCV_2017_paper.pdf,Simple Triplet Loss Based on Intra/Inter-Class Metric Learning for Face Verification,2017
+80,China,MsCeleb,msceleb,31.83907195,117.26420748,University of Science and Technology of China,edu,c5b324f7f9abdffc1be83f640674beda81b74315,citation,,Towards Open-Set Identity Preserving Face Synthesis,2018
+81,Italy,MsCeleb,msceleb,44.6451046,10.9279268,University of Modena and Reggio Emilia,edu,ff44d8938c52cfdca48c80f8e1618bbcbf91cb2a,citation,https://pdfs.semanticscholar.org/ff44/d8938c52cfdca48c80f8e1618bbcbf91cb2a.pdf,Towards Video Captioning with Naming: A Novel Dataset and a Multi-modal Approach,2017
+82,France,MsCeleb,msceleb,45.7833631,4.76877036,Ecole Centrale de Lyon,edu,727d03100d4a8e12620acd7b1d1972bbee54f0e6,citation,https://arxiv.org/pdf/1706.04264.pdf,von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification,2017
+83,France,MsCeleb,msceleb,48.832493,2.267474,Safran Identity and Security,company,727d03100d4a8e12620acd7b1d1972bbee54f0e6,citation,https://arxiv.org/pdf/1706.04264.pdf,von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification,2017
+84,China,MsCeleb,msceleb,39.980196,116.333305,"CASIA, Center for Research on Intelligent Perception and Computing, Beijing, 100190, China",edu,3ac09c2589178dac0b6a2ea2edf04b7629672d81,citation,https://arxiv.org/pdf/1708.02412.pdf,Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition,2018
+85,China,MsCeleb,msceleb,39.979203,116.33287,"CASIA, National Laboratory of Pattern Recognition",edu,3ac09c2589178dac0b6a2ea2edf04b7629672d81,citation,https://arxiv.org/pdf/1708.02412.pdf,Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition,2018
+86,China,MsCeleb,msceleb,40.0044795,116.370238,Chinese Academy of Sciences,edu,3ac09c2589178dac0b6a2ea2edf04b7629672d81,citation,https://arxiv.org/pdf/1708.02412.pdf,Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition,2018
+87,United States,MsCeleb,msceleb,38.99203005,-76.9461029,University of Maryland College Park,edu,b35ff9985aaee9371588330bcef0dfc88d1401d7,citation,,Deep Density Clustering of Unconstrained Faces,2018
+88,United States,MsCeleb,msceleb,30.6108365,-96.352128,Texas A&M University,edu,e36fdb50844132fc7925550398e68e7ae95467de,citation,,Face Verification with Disguise Variations via Deep Disguise Recognizer,2018
+89,United States,MsCeleb,msceleb,39.65404635,-79.96475355,West Virginia University,edu,e36fdb50844132fc7925550398e68e7ae95467de,citation,,Face Verification with Disguise Variations via Deep Disguise Recognizer,2018
+90,China,MsCeleb,msceleb,39.9106327,116.3356321,Chinese Academy of Science,edu,20f87ed94a423b5d8599d85d1f2f80bab8902107,citation,,Pose-Guided Photorealistic Face Rotation,2018
+91,China,MsCeleb,msceleb,39.98177,116.330086,National Laboratory of Pattern Recognition,edu,c7c8d150ece08b12e3abdb6224000c07a6ce7d47,citation,https://arxiv.org/pdf/1611.05271.pdf,DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification,2018
+92,South Korea,MsCeleb,msceleb,36.0138857,129.3231836,POSTECH,edu,e6b45d5a86092bbfdcd6c3c54cda3d6c3ac6b227,citation,https://arxiv.org/pdf/1808.04976.pdf,Pairwise Relational Networks for Face Recognition,2018
+93,China,MsCeleb,msceleb,30.318764,120.363977,China Jiliang University,edu,406c5aeca71011fd8f8bd233744a81b53ccf635a,citation,,Scalable softmax loss for face verification,2017