A Survey of Multi-View Representation Learning

Recently, multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas. This paper introduces two categories for multi-view representation learning: multi-view representation alignment and multi-view representation fusion. Consequently, we first...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on knowledge and data engineering Vol. 31; no. 10; pp. 1863 - 1883
Main Authors: Li, Yingming, Yang, Ming, Zhang, Zhongfei
Format: Journal Article
Language:English
Published: New York IEEE 01.10.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
ISSN:1041-4347, 1558-2191
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Recently, multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas. This paper introduces two categories for multi-view representation learning: multi-view representation alignment and multi-view representation fusion. Consequently, we first review the representative methods and theories of multi-view representation learning based on the perspective of alignment, such as correlation-based alignment. Representative examples are canonical correlation analysis (CCA) and its several extensions. Then, from the perspective of representation fusion, we investigate the advancement of multi-view representation learning that ranges from generative methods including multi-modal topic learning, multi-view sparse coding, and multi-view latent space Markov networks, to neural network-based methods including multi-modal autoencoders, multi-view convolutional neural networks, and multi-modal recurrent neural networks. Further, we also investigate several important applications of multi-view representation learning. Overall, this survey aims to provide an insightful overview of theoretical foundation and state-of-the-art developments in the field of multi-view representation learning and to help researchers find the most appropriate tools for particular applications.
AbstractList Recently, multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas. This paper introduces two categories for multi-view representation learning: multi-view representation alignment and multi-view representation fusion. Consequently, we first review the representative methods and theories of multi-view representation learning based on the perspective of alignment, such as correlation-based alignment. Representative examples are canonical correlation analysis (CCA) and its several extensions. Then, from the perspective of representation fusion, we investigate the advancement of multi-view representation learning that ranges from generative methods including multi-modal topic learning, multi-view sparse coding, and multi-view latent space Markov networks, to neural network-based methods including multi-modal autoencoders, multi-view convolutional neural networks, and multi-modal recurrent neural networks. Further, we also investigate several important applications of multi-view representation learning. Overall, this survey aims to provide an insightful overview of theoretical foundation and state-of-the-art developments in the field of multi-view representation learning and to help researchers find the most appropriate tools for particular applications.
Author Yang, Ming
Li, Yingming
Zhang, Zhongfei
Author_xml – sequence: 1
  givenname: Yingming
  orcidid: 0000-0001-6859-9038
  surname: Li
  fullname: Li, Yingming
  email: yingming@zju.edu.cn
  organization: College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang, China
– sequence: 2
  givenname: Ming
  surname: Yang
  fullname: Yang, Ming
  email: cauchym@zju.edu.cn
  organization: College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang, China
– sequence: 3
  givenname: Zhongfei
  surname: Zhang
  fullname: Zhang, Zhongfei
  email: zhongfei@zju.edu.cn
  organization: College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang, China
BookMark eNp9kD1PwzAQhi1UJNrCD0AskZgTfLYTO2NVyocoQoLCatmJjVwVp9gJqP-eVKkYGJjuhvd57_RM0Mg33iB0DjgDwOXV6uF6kREMIiOCE1zQIzSGPBcpgRJG_Y4ZpIwyfoImMa4xxoILGKNslrx04cvsksYmj92mdembM9_Js9kGE41vVesanyyNCt7591N0bNUmmrPDnKLXm8Vqfpcun27v57NlWjFStqkAazmBSmthtahB17kFpiuOBclpkWNeG6qAU6HKSpWitnkNiqmyUFRboukUXQ6929B8dia2ct10wfcnJSGiJAUIAn2KD6kqNDEGY2XlhofboNxGApZ7OXIvR-7lyIOcnoQ_5Da4DxV2_zIXA-OMMb95wTgQKOgPm_JwnA
CODEN ITKEEH
CitedBy_id crossref_primary_10_1109_TNNLS_2021_3116784
crossref_primary_10_1109_ACCESS_2024_3513550
crossref_primary_10_1111_cgf_14290
crossref_primary_10_1109_TMI_2022_3161828
crossref_primary_10_1109_ACCESS_2019_2953318
crossref_primary_10_1016_j_engappai_2023_105959
crossref_primary_10_1007_s10845_025_02576_7
crossref_primary_10_1016_j_knosys_2023_110816
crossref_primary_10_1109_TVCG_2022_3209382
crossref_primary_10_1016_j_sigpro_2021_108182
crossref_primary_10_1007_s10044_023_01167_7
crossref_primary_10_1016_j_asoc_2024_112339
crossref_primary_10_1145_3404893
crossref_primary_10_1109_TGRS_2022_3213838
crossref_primary_10_1145_3737878
crossref_primary_10_1117_1_JEI_31_4_043024
crossref_primary_10_1109_ACCESS_2024_3524203
crossref_primary_10_1016_j_neucom_2025_129750
crossref_primary_10_1155_2021_5526479
crossref_primary_10_1007_s10462_024_10941_w
crossref_primary_10_1016_j_apnum_2023_11_009
crossref_primary_10_1016_j_knosys_2024_111871
crossref_primary_10_1109_TKDE_2021_3099125
crossref_primary_10_1016_j_inffus_2023_02_013
crossref_primary_10_1016_j_inffus_2024_102483
crossref_primary_10_1007_s11831_025_10260_5
crossref_primary_10_1016_j_engappai_2023_106138
crossref_primary_10_1016_j_inffus_2023_102068
crossref_primary_10_1016_j_ijar_2025_109547
crossref_primary_10_1109_ACCESS_2020_2980597
crossref_primary_10_1016_j_bspc_2023_104780
crossref_primary_10_1016_j_jag_2024_104104
crossref_primary_10_1109_TGRS_2022_3144192
crossref_primary_10_1109_TKDE_2023_3333522
crossref_primary_10_1109_TIP_2024_3504252
crossref_primary_10_1109_TSP_2021_3102751
crossref_primary_10_1016_j_knosys_2019_105172
crossref_primary_10_1109_TCYB_2021_3087114
crossref_primary_10_1038_s43588_021_00030_1
crossref_primary_10_1016_j_eswa_2022_117969
crossref_primary_10_1016_j_eswa_2025_126972
crossref_primary_10_1016_j_imavis_2025_105681
crossref_primary_10_1007_s11081_025_09993_w
crossref_primary_10_1016_j_imavis_2021_104111
crossref_primary_10_1016_j_patrec_2025_06_024
crossref_primary_10_1109_TETCI_2024_3412999
crossref_primary_10_1103_PhysRevApplied_23_044033
crossref_primary_10_1109_TBDATA_2023_3334674
crossref_primary_10_1145_3543848
crossref_primary_10_1016_j_inffus_2022_11_003
crossref_primary_10_1109_JBHI_2020_3025900
crossref_primary_10_1109_TIT_2025_3532280
crossref_primary_10_1007_s00034_020_01522_7
crossref_primary_10_1109_TASLP_2021_3133196
crossref_primary_10_3390_electronics14050886
crossref_primary_10_1007_s10489_022_03205_z
crossref_primary_10_1109_TBDATA_2022_3162150
crossref_primary_10_1016_j_knosys_2025_113314
crossref_primary_10_26599_BDMA_2023_9020004
crossref_primary_10_1016_j_neucom_2024_129253
crossref_primary_10_1109_TKDE_2022_3220874
crossref_primary_10_1145_3320277
crossref_primary_10_1093_bib_bbae418
crossref_primary_10_1049_cvi2_12152
crossref_primary_10_1016_j_knosys_2023_111330
crossref_primary_10_1109_ACCESS_2023_3242286
crossref_primary_10_1016_j_cogr_2025_05_001
crossref_primary_10_1007_s10489_020_02126_z
crossref_primary_10_1007_s10479_025_06727_0
crossref_primary_10_1080_10447318_2023_2254644
crossref_primary_10_1109_JSEN_2025_3598238
crossref_primary_10_26599_TST_2023_9010148
crossref_primary_10_1109_TNNLS_2023_3265699
crossref_primary_10_1109_TKDE_2021_3082470
crossref_primary_10_1016_j_knosys_2023_110590
crossref_primary_10_1016_j_neucom_2025_130827
crossref_primary_10_1016_j_knosys_2025_113303
crossref_primary_10_1109_JIOT_2020_3004077
crossref_primary_10_1007_s10796_023_10372_y
crossref_primary_10_1109_TMM_2023_3306489
crossref_primary_10_1145_3458282
crossref_primary_10_1016_j_engappai_2020_104140
crossref_primary_10_1016_j_jcmds_2022_100036
crossref_primary_10_1080_01621459_2025_2490302
crossref_primary_10_1016_j_tourman_2025_105209
crossref_primary_10_1109_TCSVT_2024_3376720
crossref_primary_10_1109_TCSVT_2023_3278285
crossref_primary_10_1109_TMM_2022_3219650
crossref_primary_10_3390_app14104144
crossref_primary_10_1007_s00530_024_01400_1
crossref_primary_10_1111_mice_13369
crossref_primary_10_1109_TGRS_2024_3366536
crossref_primary_10_1007_s11042_021_10736_z
crossref_primary_10_1109_ACCESS_2020_2980964
crossref_primary_10_1016_j_neucom_2022_06_047
crossref_primary_10_1109_TNNLS_2022_3184723
crossref_primary_10_1145_3664651
crossref_primary_10_1109_TKDE_2021_3072642
crossref_primary_10_1109_TMI_2024_3512175
crossref_primary_10_1016_j_patcog_2022_108817
crossref_primary_10_1109_TCYB_2021_3088519
crossref_primary_10_1007_s00530_025_01930_2
crossref_primary_10_1016_j_eswa_2025_126659
crossref_primary_10_1016_j_inffus_2025_103511
crossref_primary_10_1016_j_omega_2025_103280
crossref_primary_10_1016_j_knosys_2023_110601
crossref_primary_10_1007_s12559_021_09889_8
crossref_primary_10_1016_j_compbiomed_2024_107941
crossref_primary_10_1016_j_ins_2019_12_062
crossref_primary_10_1007_s10489_022_03246_4
crossref_primary_10_1016_j_neucom_2023_127119
crossref_primary_10_1016_j_knosys_2022_108364
crossref_primary_10_1016_j_neucom_2024_128627
crossref_primary_10_1016_j_engappai_2023_107306
crossref_primary_10_1007_s00211_022_01322_y
crossref_primary_10_1016_j_tree_2021_09_008
crossref_primary_10_3390_sym16091201
crossref_primary_10_1016_j_neunet_2024_106901
crossref_primary_10_1109_TIM_2025_3529543
crossref_primary_10_1109_TETCI_2023_3314551
crossref_primary_10_1109_TNNLS_2025_3545435
crossref_primary_10_1145_3645108
crossref_primary_10_1016_j_engappai_2025_110715
crossref_primary_10_1016_j_knosys_2023_111020
crossref_primary_10_1093_bioadv_vbae064
crossref_primary_10_1016_j_inffus_2024_102498
crossref_primary_10_1016_j_infsof_2022_106998
crossref_primary_10_1109_TPAMI_2024_3521478
crossref_primary_10_1016_j_im_2021_103484
crossref_primary_10_1109_TIP_2021_3083079
crossref_primary_10_1007_s10462_024_10990_1
crossref_primary_10_1007_s11042_022_12636_2
crossref_primary_10_1109_TNNLS_2022_3201498
crossref_primary_10_1080_01691864_2022_2035253
crossref_primary_10_1051_shsconf_202419703002
crossref_primary_10_1016_j_cviu_2023_103829
crossref_primary_10_1109_TGRS_2020_2996249
crossref_primary_10_1109_TPAMI_2023_3346869
crossref_primary_10_1016_j_knosys_2023_111132
crossref_primary_10_1016_j_knosys_2021_107632
crossref_primary_10_1109_TCSVT_2021_3055039
crossref_primary_10_1016_j_engappai_2022_104870
crossref_primary_10_1016_j_inffus_2024_102269
crossref_primary_10_1016_j_neucom_2023_126604
crossref_primary_10_1109_TIP_2022_3226408
crossref_primary_10_1109_LSENS_2024_3357941
crossref_primary_10_1016_j_knosys_2022_108463
crossref_primary_10_1109_TKDE_2023_3293498
crossref_primary_10_1016_j_engappai_2025_112115
crossref_primary_10_1016_j_neunet_2025_107837
crossref_primary_10_1109_TNNLS_2022_3214208
crossref_primary_10_1016_j_neucom_2023_126733
crossref_primary_10_1002_ajpa_24469
crossref_primary_10_1007_s10489_022_03735_6
crossref_primary_10_1109_TNNLS_2020_2980960
crossref_primary_10_1016_j_knosys_2024_111421
crossref_primary_10_1016_j_neucom_2024_129188
crossref_primary_10_1007_s12559_023_10123_w
crossref_primary_10_1016_j_eswa_2024_125165
crossref_primary_10_1109_TPAMI_2022_3225461
crossref_primary_10_1016_j_neucom_2025_131558
crossref_primary_10_1016_j_patcog_2024_110377
crossref_primary_10_1016_j_neunet_2025_107180
crossref_primary_10_1007_s11042_023_17815_3
crossref_primary_10_1002_dac_5338
crossref_primary_10_1109_TCSVT_2022_3159371
crossref_primary_10_3390_app13158791
crossref_primary_10_1007_s11432_023_3853_y
crossref_primary_10_1109_TKDE_2022_3230972
crossref_primary_10_1109_TNNLS_2022_3203412
crossref_primary_10_1016_j_knosys_2021_107244
crossref_primary_10_1093_bib_bbad394
crossref_primary_10_1134_S1064230722010129
crossref_primary_10_1109_TBDATA_2021_3128906
crossref_primary_10_1109_TMM_2020_3045259
crossref_primary_10_1145_3672078
crossref_primary_10_1109_ACCESS_2020_2992063
crossref_primary_10_1186_s12859_022_05110_1
crossref_primary_10_3390_bdcc6030096
crossref_primary_10_1016_j_knosys_2022_110145
crossref_primary_10_1145_3567430
crossref_primary_10_1109_TFUZZ_2023_3288479
crossref_primary_10_1109_TCYB_2021_3053057
crossref_primary_10_1051_shsconf_20197002004
crossref_primary_10_1109_LSP_2024_3356419
crossref_primary_10_1109_TPAMI_2025_3582689
crossref_primary_10_1109_TPAMI_2020_2973634
crossref_primary_10_1007_s00521_021_06597_0
crossref_primary_10_1109_TCSVT_2025_3546973
crossref_primary_10_1016_j_iot_2023_100882
crossref_primary_10_1109_TPAMI_2021_3127870
crossref_primary_10_1016_j_imavis_2025_105722
crossref_primary_10_1109_TKDE_2020_3015098
crossref_primary_10_1109_TKDE_2022_3185399
crossref_primary_10_1109_TNNLS_2020_2984625
crossref_primary_10_1016_j_inffus_2023_102217
crossref_primary_10_1109_ACCESS_2021_3123078
crossref_primary_10_1016_j_ins_2020_10_021
crossref_primary_10_1007_s10489_021_02417_z
crossref_primary_10_1109_ACCESS_2023_3304912
crossref_primary_10_1109_TKDE_2022_3185151
crossref_primary_10_1007_s11280_024_01298_9
crossref_primary_10_1109_TIP_2024_3442610
crossref_primary_10_1109_ACCESS_2022_3231617
crossref_primary_10_1016_j_compmedimag_2024_102410
crossref_primary_10_1016_j_ijmedinf_2022_104785
crossref_primary_10_1016_j_bspc_2021_102550
crossref_primary_10_1007_s10489_022_03918_1
crossref_primary_10_1109_TNNLS_2022_3211149
crossref_primary_10_1109_TPAMI_2023_3343717
crossref_primary_10_1080_07421222_2024_2376384
crossref_primary_10_1109_TBDATA_2021_3063048
crossref_primary_10_1016_j_eswa_2022_118408
crossref_primary_10_1016_j_neucom_2021_02_043
crossref_primary_10_1016_j_neucom_2024_128687
crossref_primary_10_1109_TMM_2020_3003747
crossref_primary_10_3390_robotics12040100
crossref_primary_10_1109_TPAMI_2022_3218605
crossref_primary_10_1016_j_knosys_2024_112302
crossref_primary_10_1016_j_inffus_2024_102727
crossref_primary_10_1038_s41467_023_38125_0
crossref_primary_10_1109_TFUZZ_2021_3058572
crossref_primary_10_1016_j_eswa_2024_124683
crossref_primary_10_1109_TKDE_2023_3248221
crossref_primary_10_1016_j_asoc_2021_107899
crossref_primary_10_1016_j_neunet_2025_107193
crossref_primary_10_1016_j_iswa_2024_200474
crossref_primary_10_1109_TKDE_2021_3068461
crossref_primary_10_1109_TIP_2024_3354106
crossref_primary_10_1016_j_compbiomed_2024_108058
crossref_primary_10_1109_TNNLS_2024_3456593
crossref_primary_10_3390_e26030252
crossref_primary_10_1007_s11704_024_40004_w
crossref_primary_10_1109_TKDE_2023_3295874
crossref_primary_10_1080_12460125_2023_2207268
crossref_primary_10_1109_TCSVT_2025_3546951
crossref_primary_10_1109_TNNLS_2024_3390776
crossref_primary_10_1007_s10462_024_10955_4
crossref_primary_10_3390_rs15071762
crossref_primary_10_1007_s00521_021_06599_y
crossref_primary_10_1162_neco_a_01273
crossref_primary_10_1007_s13042_020_01130_6
crossref_primary_10_1016_j_neucom_2021_03_090
crossref_primary_10_1109_JSTARS_2024_3361556
crossref_primary_10_1109_TPAMI_2022_3222569
crossref_primary_10_1016_j_compag_2023_107957
crossref_primary_10_1016_j_molmed_2021_01_007
crossref_primary_10_1109_TNNLS_2020_3008496
crossref_primary_10_1002_edn3_70058
crossref_primary_10_1016_j_measurement_2022_111159
crossref_primary_10_1016_j_neunet_2021_11_002
crossref_primary_10_1016_j_bspc_2022_104076
crossref_primary_10_1016_j_patcog_2025_111704
crossref_primary_10_3390_ijgi14040169
crossref_primary_10_1109_TNNLS_2022_3153310
crossref_primary_10_1016_j_inffus_2023_101974
crossref_primary_10_1016_j_jksuci_2023_101904
crossref_primary_10_1109_TNNLS_2020_2984810
crossref_primary_10_1109_TNNLS_2024_3482408
crossref_primary_10_1016_j_inffus_2022_08_014
crossref_primary_10_1186_s12864_019_6285_x
crossref_primary_10_1109_TPAMI_2023_3332967
crossref_primary_10_1177_14604582241290474
crossref_primary_10_1016_j_eswa_2025_129406
crossref_primary_10_1016_j_knosys_2022_109736
crossref_primary_10_1109_TNNLS_2023_3304626
crossref_primary_10_1016_j_neunet_2024_106503
crossref_primary_10_1002_widm_1563
crossref_primary_10_1145_3568675
crossref_primary_10_1016_j_jvcir_2019_05_016
crossref_primary_10_1109_TPAMI_2022_3155499
crossref_primary_10_1145_3545572
crossref_primary_10_1109_TPAMI_2021_3135841
crossref_primary_10_1016_j_engappai_2023_107151
crossref_primary_10_1016_j_eswa_2024_126198
crossref_primary_10_1016_j_eswa_2023_120272
crossref_primary_10_1016_j_engappai_2025_111767
crossref_primary_10_1007_s10845_024_02360_z
crossref_primary_10_1109_TKDE_2020_3022072
crossref_primary_10_1007_s10846_022_01626_z
crossref_primary_10_1016_j_eswa_2024_125454
crossref_primary_10_1109_TNNLS_2025_3543219
crossref_primary_10_1016_j_compbiomed_2024_108087
crossref_primary_10_1016_j_ins_2022_03_022
crossref_primary_10_1109_TAI_2022_3207112
crossref_primary_10_1109_TCSVT_2023_3300319
crossref_primary_10_1109_TPAMI_2021_3086895
crossref_primary_10_1109_TCBB_2022_3229678
crossref_primary_10_1109_TKDE_2025_3551292
crossref_primary_10_1016_j_patrec_2023_11_015
crossref_primary_10_1109_TIT_2025_3560674
crossref_primary_10_1109_TCSVT_2022_3206865
crossref_primary_10_1016_j_knosys_2022_110244
crossref_primary_10_1016_j_media_2021_102278
crossref_primary_10_1007_s11749_024_00923_z
crossref_primary_10_1016_j_inffus_2023_101959
crossref_primary_10_1007_s00371_024_03679_7
crossref_primary_10_1016_j_inffus_2025_103012
crossref_primary_10_1016_j_inffus_2024_102661
crossref_primary_10_1016_j_cose_2024_103736
crossref_primary_10_1016_j_neunet_2025_107791
crossref_primary_10_1109_ACCESS_2023_3243854
crossref_primary_10_1016_j_powtec_2024_119448
crossref_primary_10_1016_j_dsp_2022_103888
crossref_primary_10_1109_JBHI_2024_3434439
crossref_primary_10_1007_s10489_022_04161_4
crossref_primary_10_1007_s10489_023_04666_6
crossref_primary_10_1007_s44336_024_00004_7
crossref_primary_10_1016_j_neunet_2024_106844
crossref_primary_10_1109_TNNLS_2024_3387577
crossref_primary_10_1002_alz_14421
crossref_primary_10_1016_j_ins_2024_121760
crossref_primary_10_1016_j_sigpro_2023_109341
crossref_primary_10_1016_j_ipm_2021_102534
crossref_primary_10_1016_j_patcog_2023_109836
crossref_primary_10_1016_j_neunet_2022_03_039
crossref_primary_10_1109_TMM_2023_3330093
crossref_primary_10_1007_s10115_023_01886_7
Cites_doi 10.1145/1390156.1390294
10.1109/ICCV.2009.5459205
10.1109/TCSVT.2012.2202075
10.7551/mitpress/4175.001.0001
10.1145/1553374.1553391
10.1137/1.9781611972757.39
10.1007/978-3-642-40811-3_33
10.1162/0899766042321814
10.1145/1390156.1390285
10.1145/2502081.2502107
10.1007/s10791-009-9117-9
10.1007/978-3-540-72927-3_8
10.1145/2671188.2749400
10.1002/cem.785
10.1613/jair.3994
10.1145/2647868.2654902
10.2202/1544-6115.1329
10.1109/CVPR.2010.5540112
10.1145/860458.860460
10.1093/bioinformatics/btg1045
10.1109/TIP.2011.2169972
10.1111/j.2517-6161.1996.tb02080.x
10.1145/2463676.2465274
10.1016/j.patrec.2011.02.011
10.1145/2487575.2487612
10.1080/0954898X.1996.11978653
10.1016/S0893-6080(00)00067-8
10.1109/ICCV.2015.515
10.1007/s10994-008-5085-3
10.3115/v1/N15-1028
10.7551/mitpress/1113.003.0010
10.2307/2333955
10.18653/v1/D15-1044
10.3115/v1/N15-1016
10.1109/TCYB.2016.2519449
10.1109/TPAMI.2007.1037
10.1109/TMM.2015.2480340
10.3115/v1/D14-1005
10.1142/S012906570000034X
10.1109/TASLP.2014.2339736
10.1109/ICASSP.2015.7178840
10.1109/Allerton.2012.6483308
10.1016/S0169-7439(01)00155-1
10.7551/mitpress/5236.001.0001
10.1016/S0893-6080(99)00075-1
10.1109/CVPR.2011.5995432
10.1109/TIP.2015.2507401
10.1109/ICCV.2015.114
10.1109/JPROC.2015.2460697
10.1137/130919222
10.1109/CVPR.2016.144
10.1109/ICASSP.2013.6639047
10.1214/009053604000000067
10.1109/CVPR.2010.5539928
10.1109/TMM.2013.2291214
10.1109/CVPR.2016.337
10.1145/279943.279962
10.1109/CVPR.2015.7299016
10.1145/2733373.2806240
10.18653/v1/P16-1154
10.1007/s11425-011-4245-2
10.1109/CVPR.2016.148
10.1145/957142.957143
10.1109/CVPR.2016.213
10.1016/j.cviu.2013.03.007
10.1007/s11263-011-0494-3
10.1145/2736277.2741667
10.1162/neco.1997.9.8.1735
10.1137/050645506
10.2307/2334380
10.1109/ICCV.2007.4408965
10.1109/ICCV.2015.279
10.3115/v1/D14-1179
10.1007/s11263-013-0658-4
10.1145/1873951.1873987
10.1145/2783258.2783273
10.1145/1401890.1401969
10.1145/1873951.1874183
10.1109/TCYB.2015.2392052
10.1145/1456650.1456651
10.1109/TPAMI.2013.142
10.1093/biostatistics/kxp008
10.1109/CVPR.2018.00526
10.1109/ICCV.2015.510
10.1109/CVPR.2016.293
10.1109/72.279181
10.1109/CVPR.2008.4587353
10.15607/RSS.2016.XII.041
10.1109/CVPR.2005.274
10.1145/1273496.1273519
10.1007/s10994-010-5198-3
10.1109/CVPR.2016.285
10.1145/2020408.2020480
10.1145/1102351.1102363
10.1006/jcss.1997.1504
10.1162/089976602760128018
10.1109/TIP.2014.2311377
10.1145/1281192.1281244
10.3115/v1/D14-1181
10.1109/ALLERTON.2015.7447071
10.1613/jair.4135
10.1007/s00530-010-0182-0
10.1145/1871985.1871989
10.1145/1015330.1015415
10.1145/1835804.1835846
10.1109/FG.2013.6553737
10.1109/CVPR.2015.7298754
10.1109/CVPR.2015.7298966
10.1038/355161a0
10.3115/v1/P14-1068
10.1109/TASLP.2016.2520371
10.1109/TPAMI.2007.70791
10.1109/TPAMI.2013.50
10.1145/2964284.2984066
10.1007/s00521-013-1362-6
10.1109/CVPR.2015.7298878
10.1109/CVPR.2015.7299101
10.1109/ICASSP.2013.6639140
10.1145/2600428.2609563
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
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TKDE.2018.2872063
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
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
DatabaseTitle CrossRef
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
DatabaseTitleList
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1558-2191
EndPage 1883
ExternalDocumentID 10_1109_TKDE_2018_2872063
8471216
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 61702448; 61672456
  funderid: 10.13039/501100001809
– fundername: Zhejiang University
  funderid: 10.13039/501100004835
– fundername: Fundamental Research Funds for the Central Universities
  grantid: 2017QNA5008; 2017FZA5007
GroupedDBID -~X
.DC
0R~
29I
4.4
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
IEDLZ
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
UHB
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
RIG
ID FETCH-LOGICAL-c429t-81ff721cbb8fb8d1bd5f14bc7082536507de3a1738a9ca98df5d1a4a96a3bf2b3
IEDL.DBID RIE
ISICitedReferencesCount 441
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000485736500003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1041-4347
IngestDate Sun Jun 29 15:38:53 EDT 2025
Sat Nov 29 04:46:47 EST 2025
Tue Nov 18 22:17:19 EST 2025
Wed Aug 27 02:45:12 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 10
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-c429t-81ff721cbb8fb8d1bd5f14bc7082536507de3a1738a9ca98df5d1a4a96a3bf2b3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-6859-9038
PQID 2289261821
PQPubID 85438
PageCount 21
ParticipantIDs crossref_citationtrail_10_1109_TKDE_2018_2872063
proquest_journals_2289261821
ieee_primary_8471216
crossref_primary_10_1109_TKDE_2018_2872063
PublicationCentury 2000
PublicationDate 2019-10-01
PublicationDateYYYYMMDD 2019-10-01
PublicationDate_xml – month: 10
  year: 2019
  text: 2019-10-01
  day: 01
PublicationDecade 2010
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on knowledge and data engineering
PublicationTitleAbbrev TKDE
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
ref59
ref203
ref55
ref201
mnih (ref180) 2014; abs 1406 6247
ref54
arora (ref81) 2012
graves (ref198) 2014
williams (ref90) 2000
ref50
ref45
sutskever (ref170) 2014
ref48
ref47
ref42
ref41
serban (ref194) 2016; 16
ref43
torres (ref69) 2007
ref49
ref7
ref4
ref3
dhillon (ref53) 2012
huang (ref132) 2013
ref5
ref100
wang (ref113) 2015; abs 1502 5134
ref101
ref40
collins (ref119) 2002
ref37
ref36
ref31
ref33
ref32
dong (ref134) 2016
ref39
mcwilliams (ref51) 2013
ref38
xing (ref153) 2002
xu (ref141) 2015
chen (ref177) 2014
ref23
ref25
rosipal (ref105) 2006
ref28
ref27
ref29
barnard (ref10) 2003; 3
krizhevsky (ref35) 2012
ref200
ref128
venugopalan (ref173) 2014
ref96
dong (ref204) 2017
ref127
ref99
ref124
ngiam (ref18) 2011
ref98
ref125
purushotham (ref202) 2012
ref133
ref131
ref130
dhillon (ref52) 2011
karpathy (ref21) 2014; abs 1412 2306
ref88
ref87
ref136
yang (ref91) 2012
wang (ref111) 2012; 14
mao (ref22) 2014
akaho (ref75) 2001
pang (ref159) 2015
lai (ref97) 1998
han (ref146) 2012; 22
kumar (ref122) 2011
hu (ref157) 2013
lu (ref62) 2014
ref82
ref144
ref140
ref80
ref79
ref108
ref78
ref109
ref106
ref107
ref74
ref77
ref102
ref76
kuss (ref85) 2003
ref103
roller (ref190) 2013
fukumizu (ref86) 2007; 8
chen (ref16) 2010
chen (ref73) 2012
ref71
hardoon (ref64) 2007
ref112
ref72
ref110
blei (ref142) 2003; 3
ref68
ref118
hinton (ref155) 2009
ref115
ref63
ref116
ref66
herbrich (ref117) 2000
ref65
ref114
ref60
ref120
ref121
zhen (ref123) 2012
ref168
ref169
bahdanau (ref178) 2014; abs 1409 473
zhuang (ref148) 2013
wang (ref143) 2009
jia (ref12) 2010
ref175
ref176
xing (ref15) 2005
ref174
ref171
cohn (ref9) 2000
norouzi (ref139) 2013
ref189
ref186
ref187
ref184
ref185
ref182
ref183
golub (ref58) 1992
ref149
ref147
andrew (ref8) 2013
ref156
ref151
weiss (ref129) 2008
kiros (ref172) 2014
wold (ref104) 1982; 2
rumelhart (ref154) 1986
ref158
bach (ref2) 2002; 3
wang (ref20) 2015
becker (ref95) 1992; 355
dean (ref138) 2012
ref166
ref164
ref165
ref162
ref163
ref160
ref161
ref13
ref14
frome (ref30) 2013
ref11
welling (ref150) 2004
ref19
shakhnarovich (ref126) 2005
gunasekar (ref34) 2015
xu (ref26) 2013
bishop (ref145) 2006
belkin (ref67) 2006; 7
kiros (ref135) 2014; 14
le (ref92) 2013
xie (ref152) 2013
avron (ref46) 2013; 28
brand (ref89) 2002
collell (ref188) 2017
ref1
tropp (ref61) 2010; abs 1011 1595
salakhutdinov (ref6) 2009; 1
ref191
ref192
srivastava (ref17) 2012
ref199
ref197
foster (ref44) 2008
ref195
schölkopf (ref84) 2001
ref196
mikolov (ref167) 2010; 2
lopez-paz (ref93) 2014
xu (ref181) 2015; abs 1502 3044
gretton (ref83) 2005; 6
wang (ref94) 2015; abs 1511 4773
wiesel (ref70) 2008
ba (ref179) 2014; abs 1412 7755
vinyals (ref193) 2015
mikolov (ref137) 2013
bleiholder (ref24) 2009; 41
zhang (ref56) 2011
References_xml – ident: ref5
  doi: 10.1145/1390156.1390294
– ident: ref106
  doi: 10.1109/ICCV.2009.5459205
– volume: 7
  start-page: 2399
  year: 2006
  ident: ref67
  article-title: Manifold regularization: A geometric framework for learning from labeled and unlabeled examples
  publication-title: J Mach Learn Res
– volume: 22
  start-page: 1485
  year: 2012
  ident: ref146
  article-title: Sparse unsupervised dimensionality reduction for multiple view data
  publication-title: IEEE Trans Circuits Syst Video Technol
  doi: 10.1109/TCSVT.2012.2202075
– start-page: 1903
  year: 2009
  ident: ref143
  article-title: Simultaneous image classification and annotation
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– start-page: 707
  year: 2002
  ident: ref89
  article-title: Incremental singular value decomposition of uncertain data with missing values
  publication-title: Proc Eur Conf Comput Vis
– year: 2013
  ident: ref139
  article-title: Zero-shot learning by convex combination of semantic embeddings
– year: 2001
  ident: ref84
  publication-title: Learning With Kernels Support Vector Machines Regularization Optimization and Beyond
  doi: 10.7551/mitpress/4175.001.0001
– year: 2015
  ident: ref193
  article-title: A neural conversational model
– start-page: 2121
  year: 2013
  ident: ref30
  article-title: Devise: A deep visual-semantic embedding model
  publication-title: Proc Advances Neural Inf Process Syst
– ident: ref49
  doi: 10.1145/1553374.1553391
– volume: 14
  start-page: 3
  year: 2012
  ident: ref111
  article-title: Kernel cross-modal factor analysis for information fusion with application to bimodal emotion recognition
  publication-title: IEEE Trans Multimedia
– volume: abs 1409 473
  year: 2014
  ident: ref178
  article-title: Neural machine translation by jointly learning to align and translate
– start-page: 440
  year: 2013
  ident: ref51
  article-title: Correlated random features for fast semi-supervised learning
  publication-title: Proc 20th Int Conf Neural Inf Process Syst
– ident: ref47
  doi: 10.1137/1.9781611972757.39
– ident: ref13
  doi: 10.1007/978-3-642-40811-3_33
– start-page: 1247
  year: 2013
  ident: ref8
  article-title: Deep canonical correlation analysis
  publication-title: Mach Learn Res
– ident: ref3
  doi: 10.1162/0899766042321814
– start-page: 4378
  year: 2017
  ident: ref188
  article-title: Imagined visual representations as multimodal embeddings
  publication-title: Proc 31st AAAI Conf Artif Intell
– ident: ref43
  doi: 10.1145/1390156.1390285
– ident: ref124
  doi: 10.1145/2502081.2502107
– ident: ref114
  doi: 10.1007/s10791-009-9117-9
– ident: ref50
  doi: 10.1007/978-3-540-72927-3_8
– start-page: 619
  year: 2015
  ident: ref159
  article-title: Mutlimodal learning with deep boltzmann machine for emotion prediction in user generated videos
  publication-title: Proc 5th ACM Int Conf Multimedia Retrieval
  doi: 10.1145/2671188.2749400
– ident: ref108
  doi: 10.1002/cem.785
– ident: ref182
  doi: 10.1613/jair.3994
– start-page: 505
  year: 2002
  ident: ref153
  article-title: Distance metric learning with application to clustering with side-information
  publication-title: Proc Advances Neural Inf Process Syst
– year: 2007
  ident: ref69
  article-title: Finding musically meaningful words by sparse CCA
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref19
  doi: 10.1145/2647868.2654902
– start-page: 633
  year: 2005
  ident: ref15
  article-title: Mining associated text and images with dual-wing harmoniums
  publication-title: Proc 21st Conf Uncertainty Artif Intell
– ident: ref65
  doi: 10.2202/1544-6115.1329
– ident: ref76
  doi: 10.1109/CVPR.2010.5540112
– ident: ref11
  doi: 10.1145/860458.860460
– volume: abs 1502 5134
  year: 2015
  ident: ref113
  article-title: Supervised cross-modal factor analysis
– ident: ref78
  doi: 10.1093/bioinformatics/btg1045
– ident: ref57
  doi: 10.1109/TIP.2011.2169972
– ident: ref63
  doi: 10.1111/j.2517-6161.1996.tb02080.x
– ident: ref131
  doi: 10.1145/2463676.2465274
– start-page: 199
  year: 2012
  ident: ref73
  article-title: Structured sparse canonical correlation analysis
  publication-title: Proc Conf Artif Intell Statist
– ident: ref79
  doi: 10.1016/j.patrec.2011.02.011
– ident: ref158
  doi: 10.1145/2487575.2487612
– ident: ref96
  doi: 10.1080/0954898X.1996.11978653
– ident: ref99
  doi: 10.1016/S0893-6080(00)00067-8
– year: 2016
  ident: ref134
  article-title: Word2visualvec: Cross-media retrieval by visual feature prediction
– start-page: 689
  year: 2011
  ident: ref18
  article-title: Multimodal deep learning
  publication-title: Proc Int Conf Mach Learn
– ident: ref174
  doi: 10.1109/ICCV.2015.515
– year: 2012
  ident: ref202
  article-title: Collaborative topic regression with social matrix factorization for recommendation systems
– ident: ref87
  doi: 10.1007/s10994-008-5085-3
– ident: ref101
  doi: 10.3115/v1/N15-1028
– year: 2003
  ident: ref85
  article-title: The geometry of kernel canonical correlation analysis
– year: 2000
  ident: ref117
  article-title: Large margin rank boundaries for ordinal regression
  publication-title: Advances in Large Margin Classifiers
  doi: 10.7551/mitpress/1113.003.0010
– ident: ref1
  doi: 10.2307/2333955
– start-page: 2333
  year: 2013
  ident: ref132
  article-title: Learning deep structured semantic models for web search using clickthrough data
  publication-title: Proc ACM Int Conf Inf Knowl Manag
– year: 2007
  ident: ref64
  article-title: Sparse canonical correlation analysis
– ident: ref191
  doi: 10.18653/v1/D15-1044
– ident: ref136
  doi: 10.3115/v1/N15-1016
– ident: ref185
  doi: 10.1109/TCYB.2016.2519449
– volume: 1
  year: 2009
  ident: ref6
  article-title: Deep boltzmann machines
  publication-title: Proc Int Conf Artif Intell Statist
– ident: ref55
  doi: 10.1109/TPAMI.2007.1037
– ident: ref183
  doi: 10.1109/TMM.2015.2480340
– start-page: 199
  year: 2011
  ident: ref52
  article-title: Multi-view learning of word embeddings via CCA
  publication-title: Proc Advances Neural Inf Process Syst
– start-page: 3104
  year: 2014
  ident: ref170
  article-title: Sequence to sequence learning with neural networks
  publication-title: Proc Conf Neural Inf Process Syst
– start-page: 1806
  year: 2013
  ident: ref152
  article-title: Multi-modal distance metric learning
  publication-title: Proc 23rd Int Joint Conf Artif Intell
– ident: ref39
  doi: 10.3115/v1/D14-1005
– ident: ref74
  doi: 10.1142/S012906570000034X
– ident: ref37
  doi: 10.1109/TASLP.2014.2339736
– start-page: 982
  year: 2010
  ident: ref12
  article-title: Factorized latent spaces with structured sparsity
  publication-title: Proc Advances in Neural Inf Process Syst
– volume: 3
  start-page: 1
  year: 2002
  ident: ref2
  article-title: Kernel independent component analysis
  publication-title: J Mach Learn Res
– start-page: 1607
  year: 2009
  ident: ref155
  article-title: Replicated softmax: An undirected topic model
  publication-title: Proc Advances Neural Inf Process Syst
– year: 2008
  ident: ref70
  article-title: A greedy approach to sparse canonical correlation analysis
– ident: ref100
  doi: 10.1109/ICASSP.2015.7178840
– year: 2001
  ident: ref75
  article-title: A kernel method for canonical correlation analysis
  publication-title: Proc Int Meeting Psychometric Soc
– start-page: 1481
  year: 2004
  ident: ref150
  article-title: Exponential family harmoniums with an application to information retrieval
  publication-title: Proc 17th Int Conf Neural Inf Process Syst
– start-page: 2346
  year: 2015
  ident: ref141
  article-title: Jointly modeling deep video and compositional text to bridge vision and language in a unified framework
  publication-title: Proc AAAI Conf Artif Intell
– start-page: 244
  year: 2013
  ident: ref92
  article-title: Fastfood - computing hilbert space expansions in loglinear time
  publication-title: Proc Int Conf Mach Learn
– year: 1992
  ident: ref58
  article-title: The canonical correlations of matrix pairs and their numerical computation
– ident: ref109
  doi: 10.1109/Allerton.2012.6483308
– ident: ref107
  doi: 10.1016/S0169-7439(01)00155-1
– year: 1986
  ident: ref154
  publication-title: Parallel Distributed Processing Explorations in the Microstructure of Cognition Vol 1 Foundations
  doi: 10.7551/mitpress/5236.001.0001
– ident: ref98
  doi: 10.1016/S0893-6080(99)00075-1
– ident: ref130
  doi: 10.1109/CVPR.2011.5995432
– ident: ref186
  doi: 10.1109/TIP.2015.2507401
– start-page: 1753
  year: 2008
  ident: ref129
  article-title: Spectral hashing
  publication-title: Proc Advances Neural Inf Process Syst
– ident: ref163
  doi: 10.1109/ICCV.2015.114
– volume: 16
  start-page: 3776
  year: 2016
  ident: ref194
  article-title: Building end-to-end dialogue systems using generative hierarchical neural network models
  publication-title: Proc 13th AAAI Conf Artif Intell
– start-page: 1359
  year: 2014
  ident: ref93
  article-title: Randomized nonlinear component analysis
  publication-title: Proc Int Conf Mach Learn
– ident: ref27
  doi: 10.1109/JPROC.2015.2460697
– ident: ref60
  doi: 10.1137/130919222
– ident: ref166
  doi: 10.1109/CVPR.2016.144
– ident: ref82
  doi: 10.1109/ICASSP.2013.6639047
– year: 2014
  ident: ref172
  article-title: Unifying visual-semantic embeddings with multimodal neural language models
– ident: ref66
  doi: 10.1214/009053604000000067
– ident: ref121
  doi: 10.1109/CVPR.2010.5539928
– ident: ref149
  doi: 10.1109/TMM.2013.2291214
– ident: ref197
  doi: 10.1109/CVPR.2016.337
– volume: 28
  start-page: 347
  year: 2013
  ident: ref46
  article-title: Efficient dimensionality reduction for canonical correlation analysis
  publication-title: Proc 30th Int Conf Mach Learn
– ident: ref28
  doi: 10.1145/279943.279962
– ident: ref164
  doi: 10.1109/CVPR.2015.7299016
– ident: ref184
  doi: 10.1145/2733373.2806240
– year: 2006
  ident: ref145
  publication-title: Pattern Recognition and Machine Learning
– ident: ref192
  doi: 10.18653/v1/P16-1154
– year: 2008
  ident: ref44
  article-title: Multi-view dimensionality reduction via canonical correlation analysis
– start-page: 363
  year: 1998
  ident: ref97
  article-title: Canonical correlation analysis using artificial neural networks
  publication-title: Proc Eur Symp Artif Neural Netw
– ident: ref88
  doi: 10.1007/s11425-011-4245-2
– start-page: 1764
  year: 2014
  ident: ref198
  article-title: Towards end-to-end speech recognition with recurrent neural networks
  publication-title: Proc 31st Int Conf Int Conf Mach Learn
– ident: ref40
  doi: 10.1109/CVPR.2016.148
– ident: ref29
  doi: 10.1145/957142.957143
– start-page: 1223
  year: 2012
  ident: ref138
  article-title: Large scale distributed deep networks
  publication-title: Proc Advances Neural Inf Process Syst
– ident: ref38
  doi: 10.1109/CVPR.2016.213
– ident: ref14
  doi: 10.1016/j.cviu.2013.03.007
– volume: 2
  start-page: 589
  year: 1982
  ident: ref104
  article-title: Soft modeling: the basic design and some extensions
  publication-title: Systems under Indirect Observation
– volume: abs 1502 3044
  year: 2015
  ident: ref181
  article-title: Show, attend and tell: Neural image caption generation with visual attention
– ident: ref77
  doi: 10.1007/s11263-011-0494-3
– ident: ref133
  doi: 10.1145/2736277.2741667
– start-page: 1309
  year: 2017
  ident: ref204
  article-title: A hybrid collaborative filtering model with deep structure for recommender systems
  publication-title: Proc 31st AAAI Conf Artif Intell
– ident: ref168
  doi: 10.1162/neco.1997.9.8.1735
– start-page: 1097
  year: 2012
  ident: ref35
  article-title: Imagenet classification with deep convolutional neural networks
  publication-title: Proc 25th Int Conf Neural Inf Process Syst
– ident: ref68
  doi: 10.1137/050645506
– ident: ref59
  doi: 10.2307/2334380
– start-page: 1360
  year: 2011
  ident: ref122
  article-title: Learning hash functions for cross-view similarity search
  publication-title: Proc 20nd Int Joint Conf Artif Intell
– start-page: 485
  year: 2012
  ident: ref91
  article-title: Nyström method versus random fourier features: A theoretical and empirical comparison
  publication-title: Proc Advances Neural Inf Process Syst
– year: 2014
  ident: ref177
  article-title: Learning a recurrent visual representation for image caption generation
– ident: ref189
  doi: 10.3115/v1/D14-1005
– ident: ref144
  doi: 10.1109/ICCV.2007.4408965
– start-page: 361
  year: 2010
  ident: ref16
  article-title: Predictive subspace learning for multi-view data: A large margin approach
  publication-title: Proc 23rd Int Conf Neural Inf Process Syst
– ident: ref175
  doi: 10.1109/ICCV.2015.279
– start-page: 1385
  year: 2012
  ident: ref123
  article-title: Co-regularized hashing for multimodal data
  publication-title: Proc Advances Neural Inf Process Syst
– ident: ref169
  doi: 10.3115/v1/D14-1179
– ident: ref54
  doi: 10.1007/s11263-013-0658-4
– ident: ref41
  doi: 10.1145/1873951.1873987
– year: 2014
  ident: ref22
  article-title: Deep captioning with multimodal recurrent neural networks (m-RNN)
– ident: ref203
  doi: 10.1145/2783258.2783273
– ident: ref31
  doi: 10.1145/1401890.1401969
– ident: ref33
  doi: 10.1145/1873951.1874183
– volume: 6
  start-page: 2075
  year: 2005
  ident: ref83
  article-title: Kernel methods for measuring independence
  publication-title: J Mach Learn Res
– ident: ref125
  doi: 10.1109/TCYB.2015.2392052
– volume: 41
  year: 2009
  ident: ref24
  article-title: Data fusion
  publication-title: ACM Comput Surv
  doi: 10.1145/1456650.1456651
– ident: ref112
  doi: 10.1109/TPAMI.2013.142
– ident: ref72
  doi: 10.1093/biostatistics/kxp008
– ident: ref165
  doi: 10.1109/CVPR.2018.00526
– start-page: 306
  year: 2015
  ident: ref34
  article-title: Consistent collective matrix completion under joint low rank structure
  publication-title: Proc Conf Artif Intell Statist
– volume: abs 1511 4773
  year: 2015
  ident: ref94
  article-title: Large-scale approximate kernel canonical correlation analysis
  publication-title: CoRR
– ident: ref199
  doi: 10.1109/ICCV.2015.510
– volume: 3
  start-page: 1107
  year: 2003
  ident: ref10
  article-title: Matching words and pictures
  publication-title: J Mach Learn Res
– ident: ref196
  doi: 10.1109/CVPR.2016.293
– ident: ref171
  doi: 10.1109/72.279181
– ident: ref48
  doi: 10.1109/CVPR.2008.4587353
– ident: ref160
  doi: 10.15607/RSS.2016.XII.041
– ident: ref42
  doi: 10.1109/CVPR.2005.274
– start-page: 682
  year: 2000
  ident: ref90
  article-title: Using the nyström method to speed up kernel machines
  publication-title: Proc 13th Int Conf Neural Inf Process Syst
– ident: ref71
  doi: 10.1145/1273496.1273519
– year: 2014
  ident: ref173
  article-title: Translating videos to natural language using deep recurrent neural networks
– year: 2012
  ident: ref53
  article-title: Two Step CCA: A new spectral method for estimating vector models of words
  publication-title: Proc 29th Int Conf Mach Learn
– start-page: 873
  year: 2011
  ident: ref56
  article-title: Multi-label output codes using canonical correlation analysis
  publication-title: Proc 14th Int Conf Artificial Intell
– year: 2013
  ident: ref137
  article-title: Efficient estimation of word representations in vector space
– ident: ref115
  doi: 10.1007/s10994-010-5198-3
– ident: ref162
  doi: 10.1109/CVPR.2016.285
– start-page: 34
  year: 2012
  ident: ref81
  article-title: Kernel CCA for multi-view learning of acoustic features using articulatory measurements
  publication-title: Proc Symp Mach Learning Speech Lang Process
– ident: ref201
  doi: 10.1145/2020408.2020480
– ident: ref118
  doi: 10.1145/1102351.1102363
– start-page: 2231
  year: 2012
  ident: ref17
  article-title: Multimodal learning with deep boltzmann machines
  publication-title: Proc Int Conf Neural Inf Process
– volume: 3
  start-page: 993
  year: 2003
  ident: ref142
  article-title: Latent dirichlet allocation
  publication-title: J Mach Learn Res
– ident: ref127
  doi: 10.1006/jcss.1997.1504
– volume: abs 1406 6247
  year: 2014
  ident: ref180
  article-title: Recurrent models of visual attention
– ident: ref151
  doi: 10.1162/089976602760128018
– ident: ref147
  doi: 10.1109/TIP.2014.2311377
– ident: ref32
  doi: 10.1145/1281192.1281244
– ident: ref36
  doi: 10.3115/v1/D14-1181
– ident: ref102
  doi: 10.1109/ALLERTON.2015.7447071
– ident: ref187
  doi: 10.1613/jair.4135
– ident: ref25
  doi: 10.1007/s00530-010-0182-0
– ident: ref80
  doi: 10.1145/1871985.1871989
– ident: ref120
  doi: 10.1145/1015330.1015415
– ident: ref45
  doi: 10.1145/1835804.1835846
– ident: ref110
  doi: 10.1109/FG.2013.6553737
– ident: ref140
  doi: 10.1109/CVPR.2015.7298754
– ident: ref103
  doi: 10.1109/CVPR.2015.7298966
– volume: abs 1412 7755
  year: 2014
  ident: ref179
  article-title: Multiple object recognition with visual attention
– volume: 355
  start-page: 161
  year: 1992
  ident: ref95
  article-title: Self-organizing neural network that discovers surfaces in random-dot stereograms
  publication-title: Nature
  doi: 10.1038/355161a0
– volume: 2
  year: 2010
  ident: ref167
  article-title: Recurrent neural network based language model
  publication-title: Proc Annu Conf Int Speech Commun Assoc
– ident: ref161
  doi: 10.3115/v1/P14-1068
– ident: ref176
  doi: 10.1109/TASLP.2016.2520371
– ident: ref116
  doi: 10.1109/TPAMI.2007.70791
– ident: ref7
  doi: 10.1109/TPAMI.2013.50
– start-page: 1083
  year: 2015
  ident: ref20
  article-title: On deep multi-view representation learning
  publication-title: Proc Int Conf Int Conf Mach Learn
– volume: 8
  start-page: 361
  year: 2007
  ident: ref86
  article-title: Statistical consistency of kernel canonical correlation analysis
  publication-title: J Mach Learn Res
– start-page: 91
  year: 2014
  ident: ref62
  article-title: large scale canonical correlation analysis with iterative least squares
  publication-title: Proc 27th Int Conf Neural Inf Process Syst
– ident: ref200
  doi: 10.1145/2964284.2984066
– start-page: 1146
  year: 2013
  ident: ref190
  article-title: A multimodal lda model integrating textual, cognitive and visual modalities
  publication-title: Proc Conf Empirical Methods Natural Language Process
– volume: abs 1011 1595
  year: 2010
  ident: ref61
  article-title: Improved analysis of the subsampled randomized hadamard transform
– start-page: 34
  year: 2006
  ident: ref105
  publication-title: Overview and recent advances in partial least squares
– start-page: 430
  year: 2000
  ident: ref9
  article-title: The missing link - A probabilistic model of document content and hypertext connectivity
  publication-title: Proc Advances Neural Inf Process Syst
– volume: 14
  start-page: 595
  year: 2014
  ident: ref135
  article-title: Multimodal neural language models
  publication-title: Proc 31st Int Conf Mach Learn
– volume: abs 1412 2306
  year: 2014
  ident: ref21
  article-title: Deep visual-semantic alignments for generating image descriptions
– ident: ref4
  doi: 10.1007/s00521-013-1362-6
– start-page: 263
  year: 2002
  ident: ref119
  article-title: New ranking algorithms for parsing and tagging: Kernels over discrete structures, and the voted perceptron
  publication-title: Proc Annual Meeting of the Assoc Computational Linguistics
– ident: ref23
  doi: 10.1109/CVPR.2015.7298878
– year: 2013
  ident: ref26
  article-title: A survey on multi-view learning
– start-page: 1070
  year: 2013
  ident: ref148
  article-title: Supervised coupled dictionary learning with group structures for multi-modal retrieval
  publication-title: Proc AAAI Conf Artif Intell
– ident: ref195
  doi: 10.1109/CVPR.2015.7299101
– ident: ref156
  doi: 10.1109/ICASSP.2013.6639140
– start-page: 843
  year: 2013
  ident: ref157
  article-title: Multimodal DBN for predicting high-quality answers in CQA portals
  publication-title: Proc Annual Meeting of the Assoc Computational Linguistics
– year: 2005
  ident: ref126
  article-title: Learning task-specific similarity
– ident: ref128
  doi: 10.1145/2600428.2609563
SSID ssj0008781
Score 2.703258
Snippet Recently, multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas. This paper introduces two...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1863
SubjectTerms Alignment
Artificial neural networks
canonical correlation analysis
Correlation
Correlation analysis
Data mining
Data models
Kernel
Learning systems
Machine learning
Markov processes
Markov random fields
multi-view deep learning
Multi-view representation learning
Neural networks
Recurrent neural networks
Representations
Title A Survey of Multi-View Representation Learning
URI https://ieeexplore.ieee.org/document/8471216
https://www.proquest.com/docview/2289261821
Volume 31
WOSCitedRecordID wos000485736500003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-2191
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0008781
  issn: 1041-4347
  databaseCode: RIE
  dateStart: 19890101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFH7M4UEPTjfF6ZQePInd2qZrkuPQDUEZonPsVpLmVQbSyX6J_71Jlg1FEbz1kJTypXnvfcl77wO4iFQsY4LczzERfhxF2g6SQPiog3VC2wmiPXAb3tN-n41G_KEEV5taGES0yWfYNI_2Ll9NsoU5KmsZSxqFyRZsUZqsarU2VpdRK0iq2YXmRCSm7gYzDHhrcHfTNUlcrKnpQRQk5JsPsqIqPyyxdS-9yv8-bB_2XBjpdVbrfgAlLKpQWUs0eG7HVmH3S7_BGjQ73tNiusQPb5J7tvTWH47x3Xu06bCuCqnwXM_Vl0N47nUH17e-E0zwM-1W5j4L81wzukxKlkumQqnaeRjLjBoeSHQsRhUSEVLCBM8EZypvq1DEgieCyDyS5AjKxaTAY_ASEqiMSW0P4kT7OcEDzXRYm0mFQjAM6hCsIUwz103ciFq8ppZVBDw1qKcG9dShXofLzZS3VSuNvwbXDMybgQ7hOjTW65S6zTZLI00aNRFkUXjy-6xT2NHv5qscvAaU59MFnsF2tpyPZ9Nz-x99As7Qwvg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB58gXrwLdbnHjyJ22aT7G5yFB8o1iJaxduSbGZFkFZqq_jvTdK0KIrgbQ8Ju3zZzMyXzMwHsE8N15yhjCvMVMwptXaQERWjDdZZnmaI_sDtvpm3WuLhQV5PwOG4FgYRffIZ1t2jv8s33XLgjsoazpLSJJuE6ZRzSobVWmO7K3IvSWr5hWVFjOfhDjMhstG-PDl1aVyibgkCJRn75oW8rMoPW-wdzNni_z5tCRZCIBkdDVd-GSawswKLI5GGKOzZFZj_0nFwFepH0e2g94YfUbeKfPFtfP-E79GNT4gNdUidKHRdfVyDu7PT9vF5HCQT4tI6ln4skqqynK7UWlRamESbtEq4LnPHBJmNxnKDTCU5E0qWSgpTpSZRXMlMMV1RzdZhqtPt4AZEGSOmFNpaBJ5ZT6cksVxHpEIbVEogqQEZQViUoZ-4k7V4LjyvILJwqBcO9SKgXoOD8ZSXYTONvwavOpjHAwPCNdgerVMRtttrQS1ttFRQ0GTz91l7MHvevmoWzYvW5RbM2ffIYUbeNkz1ewPcgZnyrf_02tv1_9QnIMXGPw
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=A+Survey+of+Multi-View+Representation+Learning&rft.jtitle=IEEE+transactions+on+knowledge+and+data+engineering&rft.au=Li%2C+Yingming&rft.au=Yang%2C+Ming&rft.au=Zhang%2C+Zhongfei&rft.date=2019-10-01&rft.issn=1041-4347&rft.eissn=1558-2191&rft.volume=31&rft.issue=10&rft.spage=1863&rft.epage=1883&rft_id=info:doi/10.1109%2FTKDE.2018.2872063&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TKDE_2018_2872063
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1041-4347&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1041-4347&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1041-4347&client=summon