HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task lea...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on pattern analysis and machine intelligence Vol. 41; no. 1; pp. 121 - 135
Main Authors Ranjan, Rajeev, Patel, Vishal M., Chellappa, Rama
Format Journal Article
LanguageEnglish
Published United States IEEE 01.01.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Online AccessGet full text
ISSN0162-8828
1939-3539
2160-9292
1939-3539
DOI10.1109/TPAMI.2017.2781233

Cover

Abstract We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance, and (2) Fast-HyperFace that uses a high recall fast face detector for generating region proposals to improve the speed of the algorithm. Extensive experiments show that the proposed models are able to capture both global and local information in faces and performs significantly better than many competitive algorithms for each of these four tasks.
AbstractList We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance, and (2) Fast-HyperFace that uses a high recall fast face detector for generating region proposals to improve the speed of the algorithm. Extensive experiments show that the proposed models are able to capture both global and local information in faces and performs significantly better than many competitive algorithms for each of these four tasks.
We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance, and (2) Fast-HyperFace that uses a high recall fast face detector for generating region proposals to improve the speed of the algorithm. Extensive experiments show that the proposed models are able to capture both global and local information in faces and performs significantly better than many competitive algorithms for each of these four tasks.
We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance, and (2) Fast-HyperFace that uses a high recall fast face detector for generating region proposals to improve the speed of the algorithm. Extensive experiments show that the proposed models are able to capture both global and local information in faces and performs significantly better than many competitive algorithms for each of these four tasks.We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance, and (2) Fast-HyperFace that uses a high recall fast face detector for generating region proposals to improve the speed of the algorithm. Extensive experiments show that the proposed models are able to capture both global and local information in faces and performs significantly better than many competitive algorithms for each of these four tasks.
Author Ranjan, Rajeev
Patel, Vishal M.
Chellappa, Rama
Author_xml – sequence: 1
  givenname: Rajeev
  orcidid: 0000-0003-2553-823X
  surname: Ranjan
  fullname: Ranjan, Rajeev
  email: rranjan1@umiacs.umd.edu
  organization: Department of Electrical and Computer Engineering, University of Maryland, College Park, MD
– sequence: 2
  givenname: Vishal M.
  surname: Patel
  fullname: Patel, Vishal M.
  email: pvishalm@gmail.com
  organization: Rutgers University, New Brunswick, NJ
– sequence: 3
  givenname: Rama
  surname: Chellappa
  fullname: Chellappa, Rama
  email: rama@umiacs.umd.edu
  organization: Department of Electrical and Computer Engineering, University of Maryland, College Park, MD
BackLink https://www.ncbi.nlm.nih.gov/pubmed/29990235$$D View this record in MEDLINE/PubMed
BookMark eNp9kc1u1DAUhS1URKeFFwAJWWLDggz2jZPY7Eal01ZKRYWGdeTYN5XbxB7sRKgseXIynaGLLlhd6dzv-OecE3Lkg0dC3nK25Jypz5ub1fXVEhivllBJDnn-giyAlyxToOCILBgvIZMS5DE5SemOMS4Klr8ix6CUYpAXC_Ln8mGLca0NfqEr-hVxS6-nfnTZRqd7WqOO3vlbuo56wF8h3tMuRLrDZ3ZEM7rgP9FaezvoeVkHo3v3W-_lm5CQnqfRDQdhxugFeouRfkcTbr3b6a_Jy073Cd8c5in5sT7fnF1m9beLq7NVnRnBqzFDYSG3XGDVihKKVglgVnPdGWQtWikkGGE7IQS33Fpote2sqozsjOgqZfNT8nF_7jaGnxOmsRlcMtj32mOYUgOslLkomSpm9MMz9C5M0c-va4AXXJQcAGbq_YGa2gFts43zT-ND8y_dGYA9YGJIKWL3hHDW7CpsHitsdhU2hwpnk3xmMm58DHCM2vX_t77bWx0iPt0lecVy4PlfQ8CpLQ
CODEN ITPIDJ
CitedBy_id crossref_primary_10_1109_TCYB_2018_2859482
crossref_primary_10_1007_s00779_023_01730_3
crossref_primary_10_1007_s00371_020_01814_8
crossref_primary_10_1007_s11760_024_03333_8
crossref_primary_10_3390_s20216235
crossref_primary_10_3724_SP_J_1224_2020_00538
crossref_primary_10_1109_ACCESS_2022_3176621
crossref_primary_10_1016_j_ins_2020_04_041
crossref_primary_10_1109_JAS_2021_1003871
crossref_primary_10_1109_TIP_2023_3331309
crossref_primary_10_3390_drones8100521
crossref_primary_10_1007_s42979_023_02233_x
crossref_primary_10_32604_cmc_2024_049911
crossref_primary_10_1007_s44196_023_00275_w
crossref_primary_10_1109_ACCESS_2019_2917451
crossref_primary_10_3390_app12126239
crossref_primary_10_1109_ACCESS_2020_2990958
crossref_primary_10_1155_2022_8709591
crossref_primary_10_1155_2021_9995074
crossref_primary_10_3389_fgene_2019_00397
crossref_primary_10_1007_s13753_020_00314_6
crossref_primary_10_1016_j_infrared_2024_105223
crossref_primary_10_3390_inventions5020016
crossref_primary_10_1117_1_JEI_31_4_043012
crossref_primary_10_21869_2223_1560_2021_25_1_82_109
crossref_primary_10_1109_ACCESS_2024_3376441
crossref_primary_10_1109_TNNLS_2019_2933439
crossref_primary_10_1007_s11042_020_10291_z
crossref_primary_10_1007_s11128_025_04674_0
crossref_primary_10_1016_j_patcog_2022_108591
crossref_primary_10_1109_TMM_2019_2916455
crossref_primary_10_1109_TBIOM_2023_3349218
crossref_primary_10_1109_ACCESS_2019_2962010
crossref_primary_10_1109_JIOT_2020_3021763
crossref_primary_10_1016_j_neucom_2019_06_046
crossref_primary_10_1587_transinf_2021EDL8029
crossref_primary_10_3389_fpls_2020_00141
crossref_primary_10_1109_TII_2020_2998107
crossref_primary_10_1080_02533839_2020_1751724
crossref_primary_10_1016_j_eswa_2023_119614
crossref_primary_10_1109_TCBB_2024_3439541
crossref_primary_10_1109_ACCESS_2021_3120098
crossref_primary_10_1109_TCYB_2020_3036935
crossref_primary_10_1038_s41598_024_71856_8
crossref_primary_10_1007_s13369_019_04241_7
crossref_primary_10_1016_j_neucom_2021_03_012
crossref_primary_10_1016_j_patrec_2023_10_017
crossref_primary_10_1016_j_neucom_2020_01_123
crossref_primary_10_1109_TIP_2021_3113185
crossref_primary_10_1016_j_energy_2023_128344
crossref_primary_10_3390_jmse12081343
crossref_primary_10_3390_fi11050105
crossref_primary_10_1007_s12559_021_09894_x
crossref_primary_10_1016_j_neunet_2022_10_021
crossref_primary_10_1007_s10462_024_10936_7
crossref_primary_10_3389_fnbot_2019_00112
crossref_primary_10_1145_3533253
crossref_primary_10_1117_1_JEI_27_5_053023
crossref_primary_10_1109_ACCESS_2023_3301467
crossref_primary_10_1155_2022_1413597
crossref_primary_10_3390_s24165362
crossref_primary_10_1109_ACCESS_2020_2968837
crossref_primary_10_12720_jait_16_1_144_155
crossref_primary_10_1007_s11042_023_14750_1
crossref_primary_10_1007_s00530_022_01022_5
crossref_primary_10_1007_s11042_019_7424_8
crossref_primary_10_1088_1755_1315_783_1_012080
crossref_primary_10_3390_s20174787
crossref_primary_10_3390_s19163523
crossref_primary_10_1016_j_jksuci_2023_101869
crossref_primary_10_1109_JSEN_2022_3216057
crossref_primary_10_1177_0020294020941873
crossref_primary_10_1109_TBIOM_2019_2908436
crossref_primary_10_1016_j_neucom_2019_07_064
crossref_primary_10_1109_TNNLS_2020_3007790
crossref_primary_10_3390_electronics8050503
crossref_primary_10_1109_JSTSP_2023_3250956
crossref_primary_10_1007_s10044_020_00899_0
crossref_primary_10_1109_ACCESS_2020_3000902
crossref_primary_10_3233_IDT_190359
crossref_primary_10_4108_eetinis_v11i2_4318
crossref_primary_10_1016_j_neucom_2021_10_025
crossref_primary_10_3390_sym12122119
crossref_primary_10_1016_j_ifacol_2020_12_2431
crossref_primary_10_1007_s13748_019_00203_0
crossref_primary_10_1007_s43538_022_00069_2
crossref_primary_10_1109_ACCESS_2021_3130078
crossref_primary_10_1109_TNS_2024_3423695
crossref_primary_10_1016_j_neucom_2020_10_082
crossref_primary_10_1109_TPWRS_2023_3236330
crossref_primary_10_1038_s41598_020_58103_6
crossref_primary_10_1109_TITS_2019_2921325
crossref_primary_10_1109_THMS_2021_3123186
crossref_primary_10_1007_s11760_020_01680_w
crossref_primary_10_1109_ACCESS_2018_2869465
crossref_primary_10_1109_TITS_2022_3203800
crossref_primary_10_1007_s11063_023_11397_9
crossref_primary_10_1016_j_fsir_2021_100226
crossref_primary_10_1007_s11227_022_04402_w
crossref_primary_10_25046_aj060173
crossref_primary_10_1007_s10462_023_10654_6
crossref_primary_10_1109_TIP_2021_3059409
crossref_primary_10_3233_JIFS_211114
crossref_primary_10_1016_j_asoc_2021_107172
crossref_primary_10_3233_JIFS_210263
crossref_primary_10_1109_TNNLS_2022_3174031
crossref_primary_10_1016_j_apradiso_2023_110880
crossref_primary_10_1007_s00521_021_06690_4
crossref_primary_10_1145_3507902
crossref_primary_10_1016_j_neucom_2020_03_036
crossref_primary_10_1038_s41598_024_78746_z
crossref_primary_10_1109_TCYB_2019_2917049
crossref_primary_10_1587_transinf_2020EDP7059
crossref_primary_10_3390_e21070647
crossref_primary_10_1109_ACCESS_2020_3004359
crossref_primary_10_1109_TBIOM_2021_3060641
crossref_primary_10_1109_TIM_2022_3181940
crossref_primary_10_1016_j_neucom_2018_12_074
crossref_primary_10_1007_s00521_022_07454_4
crossref_primary_10_1007_s11042_020_10401_x
crossref_primary_10_1109_TSG_2020_3027491
crossref_primary_10_1587_transfun_2019EAP1134
crossref_primary_10_3390_s19092158
crossref_primary_10_1007_s10489_020_02074_8
crossref_primary_10_1109_TCSVT_2024_3409897
crossref_primary_10_1016_j_cmpb_2023_107428
crossref_primary_10_1177_0954407021999485
crossref_primary_10_1007_s10032_019_00337_w
crossref_primary_10_1016_j_image_2021_116479
crossref_primary_10_1109_ACCESS_2023_3328210
crossref_primary_10_1109_TNNLS_2021_3052756
crossref_primary_10_1109_ACCESS_2019_2937599
crossref_primary_10_1109_TNSRE_2023_3342068
crossref_primary_10_3390_s20144021
crossref_primary_10_1109_JBHI_2020_2986376
crossref_primary_10_3390_app14051836
crossref_primary_10_1007_s11042_023_17612_y
crossref_primary_10_1007_s10489_023_05235_7
crossref_primary_10_1016_j_cmpb_2020_105513
crossref_primary_10_1049_ipr2_12222
crossref_primary_10_1016_j_patcog_2024_110263
crossref_primary_10_1016_j_neucom_2019_07_039
crossref_primary_10_3390_app122312457
crossref_primary_10_1016_j_imavis_2019_11_005
crossref_primary_10_1109_JSEN_2023_3325201
crossref_primary_10_1007_s00521_019_04330_6
crossref_primary_10_2139_ssrn_3995175
crossref_primary_10_1017_S0269964819000147
crossref_primary_10_1007_s10462_019_09742_3
crossref_primary_10_1007_s11042_023_17731_6
crossref_primary_10_3390_bdcc3030043
crossref_primary_10_1049_2024_7886911
crossref_primary_10_1109_TAI_2021_3133816
crossref_primary_10_7717_peerj_cs_894
crossref_primary_10_1016_j_dsp_2022_103696
crossref_primary_10_1109_TCYB_2019_2955178
crossref_primary_10_1016_j_patcog_2020_107504
crossref_primary_10_1007_s00376_024_3222_y
crossref_primary_10_1016_j_jvcir_2018_03_013
crossref_primary_10_1007_s12652_020_02463_4
crossref_primary_10_1016_j_asoc_2019_105890
crossref_primary_10_1016_j_measurement_2020_108158
crossref_primary_10_1109_ACCESS_2020_3011639
crossref_primary_10_1007_s12652_019_01470_4
crossref_primary_10_1016_j_ins_2021_03_027
crossref_primary_10_31590_ejosat_araconf67
crossref_primary_10_1080_07373937_2021_1885432
crossref_primary_10_3390_app10041531
crossref_primary_10_1016_j_neunet_2022_12_021
crossref_primary_10_1109_TGRS_2018_2837142
crossref_primary_10_1109_TCSVT_2023_3304724
crossref_primary_10_1007_s11042_019_08208_6
crossref_primary_10_1049_ipr2_12480
crossref_primary_10_1007_s11390_021_1325_9
crossref_primary_10_1016_j_asoc_2024_111854
crossref_primary_10_1109_TPAMI_2019_2910522
crossref_primary_10_1016_j_neucom_2019_01_046
crossref_primary_10_1109_TCYB_2019_2959403
crossref_primary_10_1145_3474595
crossref_primary_10_1007_s11042_022_13538_z
crossref_primary_10_1007_s00607_019_00722_7
crossref_primary_10_1007_s11042_023_15710_5
crossref_primary_10_1109_TII_2022_3143605
crossref_primary_10_1007_s12652_021_03218_5
crossref_primary_10_1109_TCSVT_2022_3233191
crossref_primary_10_1109_ACCESS_2019_2954845
crossref_primary_10_3390_app10072253
crossref_primary_10_1007_s10489_022_03707_w
crossref_primary_10_1016_j_ins_2022_10_074
crossref_primary_10_1109_TMM_2020_2993943
crossref_primary_10_1007_s12652_020_02750_0
crossref_primary_10_1109_ACCESS_2022_3141791
crossref_primary_10_3389_fict_2019_00018
crossref_primary_10_1016_j_image_2019_01_005
crossref_primary_10_1007_s00500_022_07074_z
crossref_primary_10_1016_j_jag_2021_102341
crossref_primary_10_1109_TAFFC_2022_3178524
crossref_primary_10_1080_1463922X_2019_1697389
crossref_primary_10_1109_ACCESS_2020_3021508
crossref_primary_10_1016_j_measurement_2024_114256
crossref_primary_10_1016_j_aej_2023_01_017
crossref_primary_10_1117_1_JEI_29_2_023005
crossref_primary_10_1038_s41598_023_49739_1
crossref_primary_10_1109_ACCESS_2024_3485804
crossref_primary_10_3390_ai1040029
crossref_primary_10_1186_s13550_023_00955_w
crossref_primary_10_1016_j_inffus_2020_06_014
crossref_primary_10_1007_s11063_021_10703_7
crossref_primary_10_1109_TGRS_2023_3264736
crossref_primary_10_1007_s00371_020_01974_7
crossref_primary_10_1109_ACCESS_2024_3351283
crossref_primary_10_1109_ACCESS_2022_3149380
crossref_primary_10_3390_electronics11030440
crossref_primary_10_1016_j_patcog_2021_107837
crossref_primary_10_1088_1361_6579_ab4102
crossref_primary_10_12720_jait_15_11_1252_1263
crossref_primary_10_1007_s11042_023_17295_5
crossref_primary_10_1145_3338842
crossref_primary_10_1186_s13643_021_01879_z
crossref_primary_10_1109_TPAMI_2020_3035969
crossref_primary_10_1109_TIM_2018_2884364
crossref_primary_10_3389_fenrg_2022_998797
crossref_primary_10_1109_TCYB_2019_2931042
crossref_primary_10_1109_TPAMI_2020_2997456
crossref_primary_10_1002_eng2_12267
crossref_primary_10_3390_s20164491
crossref_primary_10_1109_TMI_2018_2878669
crossref_primary_10_1038_s41598_019_41034_2
crossref_primary_10_1117_1_JEI_29_1_013006
crossref_primary_10_1007_s11263_020_01308_z
crossref_primary_10_1109_ACCESS_2020_3019318
crossref_primary_10_1016_j_neucom_2020_01_048
crossref_primary_10_1109_ACCESS_2020_3008793
crossref_primary_10_1109_ACCESS_2019_2939201
crossref_primary_10_1016_j_image_2021_116587
crossref_primary_10_1007_s10044_021_01026_3
crossref_primary_10_1088_1757_899X_806_1_012054
crossref_primary_10_1007_s13042_023_01933_3
crossref_primary_10_1109_TIA_2022_3186662
crossref_primary_10_1016_j_jmir_2023_03_033
crossref_primary_10_1038_s41598_020_76670_6
crossref_primary_10_3390_computers14010029
crossref_primary_10_2478_jaiscr_2022_0005
crossref_primary_10_1049_iet_cds_2019_0246
crossref_primary_10_1109_TIP_2020_2984373
crossref_primary_10_3390_app9204344
crossref_primary_10_1007_s11760_020_01753_w
crossref_primary_10_1109_TCSVT_2020_3006236
crossref_primary_10_1109_TNNLS_2021_3054407
crossref_primary_10_1016_j_compeleceng_2024_109234
crossref_primary_10_1109_TAFFC_2021_3114158
crossref_primary_10_1007_s00521_019_04577_z
crossref_primary_10_1109_ACCESS_2023_3262247
crossref_primary_10_1109_ACCESS_2023_3285246
crossref_primary_10_2139_ssrn_4073651
crossref_primary_10_1007_s00521_022_07823_z
crossref_primary_10_1109_TIFS_2020_3036803
crossref_primary_10_1007_s11263_021_01513_4
crossref_primary_10_1016_j_isci_2023_108501
crossref_primary_10_1109_ACCESS_2020_2968489
crossref_primary_10_1109_TPAMI_2021_3069250
crossref_primary_10_3390_sci2040091
crossref_primary_10_1016_j_optlastec_2024_110997
crossref_primary_10_3390_s21175918
crossref_primary_10_1007_s11042_020_08800_1
crossref_primary_10_1088_1742_6596_2224_1_012062
crossref_primary_10_3390_jmse11040867
crossref_primary_10_3390_sci2030065
crossref_primary_10_1186_s42400_023_00137_0
crossref_primary_10_3389_fnins_2023_1213176
crossref_primary_10_1007_s00371_023_02809_x
crossref_primary_10_1145_3458023
crossref_primary_10_1016_j_compmedimag_2020_101812
crossref_primary_10_1080_00140139_2019_1651904
crossref_primary_10_1016_j_scs_2020_102692
crossref_primary_10_1109_ACCESS_2020_3011112
crossref_primary_10_1016_j_chemolab_2021_104233
crossref_primary_10_1109_LGRS_2020_3013026
crossref_primary_10_1007_s12008_021_00814_9
crossref_primary_10_1016_j_patcog_2020_107342
crossref_primary_10_1109_TCSVT_2020_3045978
crossref_primary_10_1109_TIP_2020_2976765
crossref_primary_10_2478_cait_2024_0018
crossref_primary_10_3390_rs11212584
crossref_primary_10_3390_app11010089
crossref_primary_10_1109_TIM_2022_3162615
crossref_primary_10_3390_rs14020397
crossref_primary_10_1109_TCSS_2019_2910599
crossref_primary_10_1142_S0218001424560019
crossref_primary_10_1016_j_cviu_2023_103622
crossref_primary_10_1007_s11042_023_15336_7
crossref_primary_10_1109_TNNLS_2020_3015996
crossref_primary_10_3390_electronics11081210
crossref_primary_10_1007_s11633_022_1349_9
crossref_primary_10_1142_S0218488523400044
crossref_primary_10_1007_s11042_021_10918_9
crossref_primary_10_3390_s19153361
crossref_primary_10_1007_s11042_021_11783_2
crossref_primary_10_3390_s21041098
crossref_primary_10_3390_sci2020047
crossref_primary_10_1109_TPAMI_2021_3086914
crossref_primary_10_1109_TMM_2019_2919469
crossref_primary_10_1109_ACCESS_2023_3253968
crossref_primary_10_1007_s10489_020_01946_3
crossref_primary_10_1109_TIM_2018_2879706
crossref_primary_10_1117_1_JEI_28_1_013012
crossref_primary_10_3390_jlpea10010001
crossref_primary_10_3390_sci2010015
crossref_primary_10_1007_s10032_021_00364_6
crossref_primary_10_3233_JIFS_231423
crossref_primary_10_1007_s11548_024_03315_8
crossref_primary_10_1109_ACCESS_2019_2914319
crossref_primary_10_1016_j_neucom_2023_126284
crossref_primary_10_1007_s11042_022_13070_0
crossref_primary_10_1007_s11263_023_01935_2
crossref_primary_10_1007_s00530_023_01134_6
crossref_primary_10_1007_s00521_020_05167_0
crossref_primary_10_1117_1_JEI_28_1_013029
crossref_primary_10_1109_ACCESS_2021_3119615
crossref_primary_10_1016_j_jobe_2023_108126
crossref_primary_10_1155_2021_5552206
crossref_primary_10_1155_2021_2891303
crossref_primary_10_1016_j_buildenv_2019_106424
crossref_primary_10_1007_s11263_020_01378_z
crossref_primary_10_1007_s11760_024_02999_4
crossref_primary_10_1109_TIM_2020_3026514
crossref_primary_10_1109_ACCESS_2020_2995764
crossref_primary_10_1109_ACCESS_2019_2960325
crossref_primary_10_3390_s19061346
crossref_primary_10_1080_17517575_2019_1668964
crossref_primary_10_1049_cit2_12090
crossref_primary_10_1109_TEVC_2023_3272663
crossref_primary_10_1016_j_matpr_2022_07_342
crossref_primary_10_3390_app12157473
crossref_primary_10_1109_TBIOM_2021_3100926
crossref_primary_10_1109_ACCESS_2023_3241606
crossref_primary_10_1186_s40494_022_00732_3
crossref_primary_10_1016_j_eswa_2021_116105
crossref_primary_10_1016_j_measurement_2022_110807
crossref_primary_10_1109_TCSVT_2019_2897243
crossref_primary_10_1007_s11704_020_8272_4
crossref_primary_10_1016_j_dsp_2020_102809
crossref_primary_10_1049_bme2_12061
crossref_primary_10_3390_rs15040953
crossref_primary_10_1007_s11036_021_01874_7
crossref_primary_10_1109_ACCESS_2019_2962974
crossref_primary_10_1109_TAFFC_2022_3215918
crossref_primary_10_1016_j_neucom_2019_10_094
crossref_primary_10_1016_j_chemolab_2019_04_007
crossref_primary_10_1109_TBIOM_2020_2973504
crossref_primary_10_1109_TNNLS_2020_2994325
crossref_primary_10_1109_TMI_2020_2974159
crossref_primary_10_3390_app15052473
crossref_primary_10_1109_JIOT_2019_2916777
crossref_primary_10_1109_TMM_2024_3391888
crossref_primary_10_1109_TPAMI_2020_3046323
crossref_primary_10_1109_ACCESS_2020_3023782
crossref_primary_10_3390_sym11060770
crossref_primary_10_1016_j_patcog_2021_108425
crossref_primary_10_1109_ACCESS_2024_3354373
crossref_primary_10_1007_s00371_022_02732_7
crossref_primary_10_1007_s11042_022_13653_x
crossref_primary_10_3390_s23083825
crossref_primary_10_1017_S2633903X24000035
crossref_primary_10_1016_j_cviu_2021_103218
crossref_primary_10_1049_ipr2_12556
crossref_primary_10_1007_s10489_025_06231_9
crossref_primary_10_1109_ACCESS_2023_3288569
crossref_primary_10_3390_e24070974
crossref_primary_10_1109_ACCESS_2022_3165203
crossref_primary_10_1145_3527662
crossref_primary_10_1109_ACCESS_2022_3190404
crossref_primary_10_1109_TAFFC_2020_2983669
crossref_primary_10_2139_ssrn_5088950
crossref_primary_10_1016_j_eswa_2024_124425
crossref_primary_10_1007_s00371_023_02781_6
crossref_primary_10_1007_s13042_021_01413_6
crossref_primary_10_1016_j_neucom_2020_03_023
crossref_primary_10_1109_JIOT_2020_3039359
crossref_primary_10_1109_TPAMI_2021_3088859
crossref_primary_10_1016_j_isci_2020_101656
crossref_primary_10_1007_s11042_022_11958_5
crossref_primary_10_1109_ACCESS_2023_3297500
crossref_primary_10_1016_j_neucom_2021_09_055
crossref_primary_10_1007_s13198_022_01688_0
crossref_primary_10_1007_s11760_019_01538_w
crossref_primary_10_1109_TBIOM_2021_3122307
crossref_primary_10_1109_ACCESS_2020_3026421
crossref_primary_10_31590_ejosat_1113302
crossref_primary_10_1142_S0218001421550016
crossref_primary_10_1007_s10489_022_03766_z
crossref_primary_10_1109_JSTSP_2019_2955024
crossref_primary_10_1109_ACCESS_2020_2977346
crossref_primary_10_1007_s10489_022_03173_4
crossref_primary_10_1109_JSTSP_2023_3270621
crossref_primary_10_4218_etrij_2018_0621
crossref_primary_10_1016_j_imavis_2020_103912
crossref_primary_10_3390_s22218449
crossref_primary_10_1109_TIP_2024_3372457
crossref_primary_10_1016_j_displa_2021_102020
crossref_primary_10_1007_s11042_019_07848_y
crossref_primary_10_1016_j_jclepro_2021_126242
crossref_primary_10_1109_ACCESS_2021_3077070
crossref_primary_10_3390_s20020328
crossref_primary_10_1016_j_patcog_2021_108449
crossref_primary_10_1109_TPAMI_2021_3073593
crossref_primary_10_1541_ieejeiss_143_871
crossref_primary_10_1016_j_cviu_2024_103999
crossref_primary_10_1007_s10044_022_01098_9
crossref_primary_10_1080_19479832_2024_2382737
crossref_primary_10_1016_j_media_2020_101824
crossref_primary_10_3233_JIFS_189508
crossref_primary_10_1016_j_patcog_2022_108753
crossref_primary_10_3390_s23104731
crossref_primary_10_1016_j_asoc_2023_110176
crossref_primary_10_1016_j_patrec_2020_03_002
crossref_primary_10_3390_jmse10050639
crossref_primary_10_3390_s23218676
crossref_primary_10_3390_s22218303
crossref_primary_10_1109_TIFS_2018_2800901
crossref_primary_10_1155_2022_3017149
crossref_primary_10_1007_s00500_019_04174_1
crossref_primary_10_1007_s11390_024_2264_z
crossref_primary_10_1093_iwcomp_iwaa011
crossref_primary_10_1109_TNNLS_2021_3117685
crossref_primary_10_1016_j_jclepro_2020_122722
crossref_primary_10_1109_TCI_2018_2889933
crossref_primary_10_1109_TMM_2021_3081873
crossref_primary_10_1155_2021_5196000
crossref_primary_10_1016_j_compag_2020_105629
crossref_primary_10_1016_j_neucom_2020_12_090
crossref_primary_10_1109_ACCESS_2022_3157857
crossref_primary_10_3390_app12105252
crossref_primary_10_1109_TPAMI_2021_3103980
crossref_primary_10_1007_s41365_024_01606_y
crossref_primary_10_1016_j_imavis_2022_104555
crossref_primary_10_1109_JIOT_2022_3201310
crossref_primary_10_1016_j_patcog_2021_108256
crossref_primary_10_1177_0263276419867752
crossref_primary_10_1016_j_cag_2019_08_013
crossref_primary_10_1109_TIP_2020_2991549
crossref_primary_10_1016_j_neucom_2021_07_006
crossref_primary_10_1109_ACCESS_2022_3214227
crossref_primary_10_1002_jnm_3020
crossref_primary_10_1109_ACCESS_2021_3071581
crossref_primary_10_1109_ACCESS_2019_2947519
crossref_primary_10_1016_j_sysarc_2024_103085
crossref_primary_10_1109_TIP_2024_3378180
crossref_primary_10_1109_TII_2018_2884211
crossref_primary_10_1109_TCSVT_2024_3366522
crossref_primary_10_3390_electronics11070993
crossref_primary_10_1109_JSEN_2021_3064060
crossref_primary_10_3390_math12132089
crossref_primary_10_1109_ACCESS_2020_2982970
crossref_primary_10_1016_j_eswa_2022_117368
crossref_primary_10_1109_ACCESS_2018_2882227
crossref_primary_10_1177_16878140211013138
crossref_primary_10_1007_s11042_023_17343_0
crossref_primary_10_1007_s11831_021_09639_x
crossref_primary_10_3233_JIFS_189789
crossref_primary_10_1007_s00371_019_01707_5
crossref_primary_10_1016_j_diin_2019_07_008
crossref_primary_10_1016_j_neucom_2020_05_010
crossref_primary_10_1016_j_patrec_2020_10_003
crossref_primary_10_1109_TBIOM_2019_2961926
crossref_primary_10_1007_s42979_022_01359_8
crossref_primary_10_1109_JPROC_2023_3275192
crossref_primary_10_1007_s42979_023_01796_z
crossref_primary_10_1016_j_asoc_2024_111274
crossref_primary_10_1016_j_patcog_2022_108672
crossref_primary_10_1109_TAES_2023_3293074
crossref_primary_10_1109_TITS_2020_3019390
crossref_primary_10_1109_TIP_2019_2911114
crossref_primary_10_1049_iet_ipr_2020_0199
crossref_primary_10_1109_TPAMI_2021_3076733
crossref_primary_10_1016_j_softx_2023_101516
crossref_primary_10_32604_cmc_2020_013590
crossref_primary_10_3390_app11104366
crossref_primary_10_1109_TAFFC_2020_3031841
crossref_primary_10_1016_j_engappai_2023_106391
crossref_primary_10_1155_2022_2103975
crossref_primary_10_3390_bioengineering11010101
crossref_primary_10_1142_S0218001421600028
crossref_primary_10_1109_TPAMI_2019_2902556
crossref_primary_10_1007_s00138_021_01234_1
crossref_primary_10_1016_j_iswa_2024_200391
crossref_primary_10_1186_s13634_022_00868_1
crossref_primary_10_2139_ssrn_4157631
crossref_primary_10_1109_TIP_2019_2948728
crossref_primary_10_4018_IJEHMC_309930
crossref_primary_10_1109_ACCESS_2019_2932146
crossref_primary_10_1109_ACCESS_2019_2934563
crossref_primary_10_1007_s10846_022_01652_x
crossref_primary_10_1109_ACCESS_2023_3324403
crossref_primary_10_1109_TIM_2023_3238750
crossref_primary_10_1016_j_patcog_2025_111393
crossref_primary_10_1109_TCSS_2021_3059318
crossref_primary_10_4018_IJMDEM_2019040103
crossref_primary_10_1109_TCSI_2019_2921714
Cites_doi 10.5244/C.20.92
10.1109/ICCV.2015.425
10.1109/ICCV.2015.144
10.1109/CVPR.2014.212
10.1109/CVPR.2015.7298594
10.1007/s11263-007-0072-x
10.1109/ICCV.2013.103
10.1109/ICCV.2015.419
10.1109/CVPR.2016.371
10.1109/CVPR.2015.7299170
10.1109/ICCV.2015.18
10.1145/2647868.2654889
10.1109/CVPR.2013.75
10.1109/CVPR.2017.579
10.1109/CVPR.2016.90
10.1109/CVPR.2014.241
10.1109/CVPR.2015.7298642
10.1109/ICCV.2015.421
10.1109/ICCVW.2011.6130513
10.1109/CVPR.2016.92
10.1109/ICPR.2002.1047456
10.1109/CVPR.2014.218
10.1109/CVPR.2009.5206848
10.1007/s11263-013-0667-3
10.1109/CVPR.2013.446
10.1109/TPAMI.2009.167
10.1109/ICCV.2013.191
10.1006/cviu.1995.1004
10.1109/CVPR.2013.445
10.1109/CVPR.2014.81
10.1109/ICCV.2015.304
10.1145/2671188.2749408
10.1016/j.imavis.2013.12.004
10.1007/s11263-010-0380-4
10.1109/CVPR.2016.23
10.1007/s11263-009-0275-4
10.1109/ICCVW.2013.126
10.1007/978-1-4615-5529-2_5
10.1109/CVPR.2017.166
10.1109/TPAMI.2015.2469286
10.1109/ICCV.2013.244
10.1109/CVPR.2015.7298882
10.1023/B:VISI.0000029666.37597.d3
10.1109/ICCV.2011.6126456
10.1109/TPAMI.2008.106
10.1109/ICCVW.2013.59
10.1109/BTAS.2015.7358755
10.1109/CVPR.2014.239
10.1109/CVPR.2013.465
10.1109/CVPR.2007.383280
10.1023/B:VISI.0000013087.49260.fb
10.1109/TPAMI.2015.2448075
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID 97E
RIA
RIE
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TPAMI.2017.2781233
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList MEDLINE

Technology Research Database
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 3
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 2160-9292
1939-3539
EndPage 135
ExternalDocumentID 29990235
10_1109_TPAMI_2017_2781233
8170321
Genre orig-research
Research Support, U.S. Gov't, Non-P.H.S
Journal Article
GrantInformation_xml – fundername: Intelligence Advanced Research Projects Activity (IARPA)
– fundername: U.S. Government
– fundername: IARPA R&D Contract
  grantid: 2014-14071600012
– fundername: Office of the Director of National Intelligence (ODNI)
– fundername: IARPA
– fundername: ODNI
GroupedDBID ---
-DZ
-~X
.DC
0R~
29I
4.4
53G
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
HZ~
IEDLZ
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
UHB
~02
AAYXX
CITATION
5VS
9M8
AAYOK
ABFSI
ADRHT
AETIX
AGSQL
AI.
AIBXA
ALLEH
CGR
CUY
CVF
ECM
EIF
FA8
H~9
IBMZZ
ICLAB
IFJZH
NPM
PKN
RIC
RIG
RNI
RZB
VH1
XJT
Z5M
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c417t-e4d23d14e7b4625b9420da1afce0bed8482c4df4441d1dd2badfd97c8fc4f79d3
IEDL.DBID RIE
ISSN 0162-8828
1939-3539
IngestDate Sat Sep 27 22:18:48 EDT 2025
Mon Jun 30 03:28:02 EDT 2025
Wed Feb 19 02:31:36 EST 2025
Thu Apr 24 23:05:32 EDT 2025
Wed Oct 01 03:57:32 EDT 2025
Wed Aug 27 02:50:17 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c417t-e4d23d14e7b4625b9420da1afce0bed8482c4df4441d1dd2badfd97c8fc4f79d3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0003-2553-823X
PMID 29990235
PQID 2151461222
PQPubID 85458
PageCount 15
ParticipantIDs proquest_journals_2151461222
crossref_primary_10_1109_TPAMI_2017_2781233
pubmed_primary_29990235
crossref_citationtrail_10_1109_TPAMI_2017_2781233
ieee_primary_8170321
proquest_miscellaneous_2068346095
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2019-Jan.-1
2019-1-1
2019-01-00
20190101
PublicationDateYYYYMMDD 2019-01-01
PublicationDate_xml – month: 01
  year: 2019
  text: 2019-Jan.-1
  day: 01
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev TPAMI
PublicationTitleAlternate IEEE Trans Pattern Anal Mach Intell
PublicationYear 2019
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref13
ref56
ref12
ref59
ref15
ref58
ref14
ref53
ref52
kumar (ref31) 2008
ref55
ref11
ref54
ref10
ref17
liang (ref35) 2008; 5303
ref18
liu (ref37) 2016
zeiler (ref63) 2014
zhang (ref65) 2014
simonyan (ref47) 2014
ref51
ref50
huang (ref21) 2007
caruana (ref5) 1998
ref46
ref45
ref48
jain (ref23) 2010
ref42
ref41
ref44
ref43
gkioxari (ref16) 2014
mathias (ref39) 2014; 8692
ref8
ref9
ref4
ref3
ref40
ref34
ref36
cootes (ref7) 1995; 61
ref33
krizhevsky (ref29) 2012
ref32
ref2
zhu (ref71) 2012
ref1
ref38
sun (ref49) 2014
zhu (ref67) 2015
ref68
ref24
ref26
ref69
ref25
ref64
ref20
ref66
ioffe (ref22) 2015
zhu (ref70) 2012
ref28
hu (ref19) 2005; 2
ref27
kumar (ref30) 0
chen (ref6) 2014; 8694
ref60
ref62
ref61
References_xml – ident: ref11
  doi: 10.5244/C.20.92
– ident: ref38
  doi: 10.1109/ICCV.2015.425
– start-page: 21
  year: 2016
  ident: ref37
  article-title: SSD: Single shot multibox detector
  publication-title: Proc Eur Conf Comput Vis
– ident: ref61
  doi: 10.1109/ICCV.2015.144
– ident: ref64
  doi: 10.1109/CVPR.2014.212
– start-page: 448
  year: 2015
  ident: ref22
  article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
  publication-title: Proc Int Conf Mach Learn
– start-page: 1097
  year: 2012
  ident: ref29
  article-title: ImageNet classification with deep convolutional neural networks
  publication-title: Proc Int Conf Adv Neural Inform Process Syst
– start-page: 2879
  year: 2012
  ident: ref70
  article-title: Face detection, pose estimation, and landmark localization in the wild
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– ident: ref51
  doi: 10.1109/CVPR.2015.7298594
– ident: ref1
  doi: 10.1007/s11263-007-0072-x
– ident: ref32
  doi: 10.1109/ICCV.2013.103
– ident: ref60
  doi: 10.1109/ICCV.2015.419
– ident: ref68
  doi: 10.1109/CVPR.2016.371
– ident: ref33
  doi: 10.1109/CVPR.2015.7299170
– ident: ref59
  doi: 10.1109/ICCV.2015.18
– ident: ref24
  doi: 10.1145/2647868.2654889
– start-page: 2879
  year: 2012
  ident: ref71
  article-title: FaceDPL: Face detection, pose estimation, and landmark localization in the wild
  publication-title: IEEE Conf Comput Vis Pattern Recognit
– ident: ref56
  doi: 10.1109/CVPR.2013.75
– year: 2014
  ident: ref16
  article-title: R-CNNS for pose estimation and action detection
– start-page: 340
  year: 2008
  ident: ref31
  article-title: FaceTracer: A search engine for large collections of images with faces
  publication-title: Proc Eur Conf Comput Vis
– start-page: 4998
  year: 2015
  ident: ref67
  article-title: Face alignment by coarse-to-fine shape searching
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– ident: ref27
  doi: 10.1109/CVPR.2017.579
– ident: ref18
  doi: 10.1109/CVPR.2016.90
– ident: ref26
  doi: 10.1109/CVPR.2014.241
– ident: ref17
  doi: 10.1109/CVPR.2015.7298642
– ident: ref25
  doi: 10.1109/ICCV.2015.421
– ident: ref28
  doi: 10.1109/ICCVW.2011.6130513
– volume: 5303
  start-page: 72
  year: 2008
  ident: ref35
  article-title: Face alignment via component-based discriminative search
  publication-title: Proc Eur Conf Comput Vis
– ident: ref14
  doi: 10.1109/CVPR.2016.92
– ident: ref48
  doi: 10.1109/ICPR.2002.1047456
– start-page: 1988
  year: 2014
  ident: ref49
  article-title: Deep learning face representation by joint identification-verification
  publication-title: Proc Int Conf Adv Neural Inform Process Syst
– ident: ref43
  doi: 10.1109/CVPR.2014.218
– year: 2007
  ident: ref21
  article-title: Labeled faces in the wild: A database for studying face recognition in unconstrained environments
– ident: ref8
  doi: 10.1109/CVPR.2009.5206848
– ident: ref4
  doi: 10.1007/s11263-013-0667-3
– ident: ref50
  doi: 10.1109/CVPR.2013.446
– ident: ref13
  doi: 10.1109/TPAMI.2009.167
– ident: ref3
  doi: 10.1109/ICCV.2013.191
– volume: 61
  start-page: 38
  year: 1995
  ident: ref7
  article-title: Active shape models-their training and application
  publication-title: Comput Vis Image Underst
  doi: 10.1006/cviu.1995.1004
– start-page: 818
  year: 2014
  ident: ref63
  article-title: Visualizing and understanding convolutional networks
  publication-title: European Conf Comput Vis
– ident: ref34
  doi: 10.1109/CVPR.2013.445
– ident: ref15
  doi: 10.1109/CVPR.2014.81
– ident: ref9
  doi: 10.1109/ICCV.2015.304
– volume: 2
  start-page: ii?342
  year: 2005
  ident: ref19
  article-title: Head pose estimation by non-linear embedding and mapping
  publication-title: Proc IEEE Int Conf Image Process
– ident: ref12
  doi: 10.1145/2671188.2749408
– ident: ref58
  doi: 10.1016/j.imavis.2013.12.004
– year: 2014
  ident: ref47
  article-title: Very deep convolutional networks for large-scale image recognition
– ident: ref45
  doi: 10.1007/s11263-010-0380-4
– ident: ref69
  doi: 10.1109/CVPR.2016.23
– ident: ref10
  doi: 10.1007/s11263-009-0275-4
– year: 0
  ident: ref30
  article-title: Face alignment by local deep descriptor regression
– start-page: 94
  year: 2014
  ident: ref65
  article-title: Facial landmark detection by deep multi-task learning
  publication-title: Proc Eur Conf Comput Vis
– ident: ref57
  doi: 10.1109/ICCVW.2013.126
– start-page: 95
  year: 1998
  ident: ref5
  article-title: Multitask learning
  publication-title: Learning to Learn
  doi: 10.1007/978-1-4615-5529-2_5
– ident: ref20
  doi: 10.1109/CVPR.2017.166
– ident: ref66
  doi: 10.1109/TPAMI.2015.2469286
– ident: ref62
  doi: 10.1109/ICCV.2013.244
– ident: ref55
  doi: 10.1109/CVPR.2015.7298882
– ident: ref40
  doi: 10.1023/B:VISI.0000029666.37597.d3
– year: 2010
  ident: ref23
  article-title: FDDB: A benchmark for face detection in unconstrained settings
– ident: ref53
  doi: 10.1109/ICCV.2011.6126456
– ident: ref41
  doi: 10.1109/TPAMI.2008.106
– ident: ref44
  doi: 10.1109/ICCVW.2013.59
– ident: ref42
  doi: 10.1109/BTAS.2015.7358755
– ident: ref52
  doi: 10.1109/CVPR.2014.239
– volume: 8692
  start-page: 720
  year: 2014
  ident: ref39
  article-title: Face detection without bells and whistles
  publication-title: Proc Eur Conf Comput Vis
– volume: 8694
  start-page: 109
  year: 2014
  ident: ref6
  article-title: Joint cascade face detection and alignment
  publication-title: Proc Eur Conf Comput Vis
– ident: ref46
  doi: 10.1109/CVPR.2013.465
– ident: ref2
  doi: 10.1109/CVPR.2007.383280
– ident: ref54
  doi: 10.1023/B:VISI.0000013087.49260.fb
– ident: ref36
  doi: 10.1109/TPAMI.2015.2448075
SSID ssj0014503
Score 2.7153723
Snippet We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 121
SubjectTerms Algorithms
Artificial neural networks
deep convolutional neural networks
Deep Learning
Face
Face - diagnostic imaging
Face detection
Face recognition
Feature extraction
Female
Fuses
Gender Identity
gender recognition
head pose estimation
Humans
Image Processing, Computer-Assisted - methods
Landmarks
landmarks localization
Localization
Machine learning
Male
multi-task learning
Pattern Recognition, Automated - methods
Pose estimation
Posture - physiology
Title HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition
URI https://ieeexplore.ieee.org/document/8170321
https://www.ncbi.nlm.nih.gov/pubmed/29990235
https://www.proquest.com/docview/2151461222
https://www.proquest.com/docview/2068346095
Volume 41
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2160-9292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014503
  issn: 0162-8828
  databaseCode: RIE
  dateStart: 19790101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB6VnuiBQltoSkGuxI3NNna8m4TbCrpaqi6q0FbqLfJjwqE0qbrZS4_95YwdJwIEiFuUjBNHM-P5xp4HwDshFNl1buO8mthYCs1jrVyyOwqjc00YFt0-5PLLdHElz68n11swGnJhENEHn-HYXfqzfNuYjdsqO3XF5FKXNf4ky6ddrtZwYiAnvgsyIRjScHIj-gSZpDhdXc6Wn10UVzYWGRm01DXPoWW4cLVefrFHvsHK37GmtznzXVj2s-1CTW7Gm1aPzcNvhRz_93eew7MAPtmsk5YXsIX1Huz2jR1Y0PM92PmpSuE-PC7IV72fK4Mf2Ix9QrxjPm03Xqn1DQsFWr-xeR_mxQgHM0dOtK2P9KpH7ELV9lbRwwtnPEPy54hdNmtkZ7TM3IYbRMa69nbsax_b1NQHcDU_W31cxKF1Q2wkz9oYpRWp5RIzLcnD0oUUiVVcVQYTjTaXuTDSVpLAmOXWCq1sZYvM5JWRVVbY9CVs102Nh8C4SSznKpvo3Eqk4SkShqkUebbIkZsIeM_A0oS65q69xvfS-zdJUXr-l47_ZeB_BO-HMXddVY9_Uu875g2UgW8RHPdyUgbFX5cOQUlCjUJEcDI8JpV15zCqxmZDNMk0T6Wr9BfBq06-hnf3Ynn052--hqc0s6LbAzqG7fZ-g28IFbX6rVeHH7fxBoo
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB5V5QAcWmihDRQwEjc229hxmoTbCrrawm5Voa3UW-THhENpUnV3Lxz55YwdJwIEiFuUjBNHM-P5xp4HwBshFNl1buOizmwsheaxVi7ZHYXRhSYMi24fcnF-MruUH6-yqy0YDbkwiOiDz3DsLv1Zvm3Nxm2VHbticqnLGr-XSSmzLltrODOQme-DTBiGdJwciT5FJimPlxeTxZmL48rHIieTlrr2ObQQl67ayy8WybdY-Tva9FZnuguLfr5dsMn1eLPWY_Ptt1KO__tDj2AnwE826eTlMWxhswe7fWsHFjR9Dx7-VKdwH77PyFu9myqD79iEfUC8ZT5xN16q1TULJVq_sGkf6MUICTNHTrRrH-vVjNhcNfZG0cO5M58h_XPELtoVslNaaG7CDSJjXYM79rmPbmqbJ3A5PV2-n8WheUNsJM_XMUorUssl5lqSj6VLKRKruKoNJhptIQthpK2Jj9xya4VWtrZlborayDovbfoUtpu2wUNg3CSWc5VnurASaXiKhGJqRb4tcuQmAt4zsDKhsrlrsPG18h5OUlae_5XjfxX4H8HbYcxtV9fjn9T7jnkDZeBbBEe9nFRB9VeVw1CScKMQEbweHpPSupMY1WC7IZrkpEilq_UXwUEnX8O7e7F89udvvoL7s-ViXs3Pzj89hwc0y7LbETqC7fXdBl8QRlrrl141fgCW4wnX
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=HyperFace%3A+A+Deep+Multi-Task+Learning+Framework+for+Face+Detection%2C+Landmark+Localization%2C+Pose+Estimation%2C+and+Gender+Recognition&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Ranjan%2C+Rajeev&rft.au=Patel%2C+Vishal+M.&rft.au=Chellappa%2C+Rama&rft.date=2019-01-01&rft.issn=0162-8828&rft.eissn=2160-9292&rft.volume=41&rft.issue=1&rft.spage=121&rft.epage=135&rft_id=info:doi/10.1109%2FTPAMI.2017.2781233&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TPAMI_2017_2781233
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon