Deep neural network concepts for background subtraction:A systematic review and comparative evaluation

Conventional neural networks have been demonstrated to be a powerful framework for background subtraction in video acquired by static cameras. Indeed, the well-known Self-Organizing Background Subtraction (SOBS) method and its variants based on neural networks have long been the leading methods on t...

Full description

Saved in:
Bibliographic Details
Published inNeural networks Vol. 117; pp. 8 - 66
Main Authors Bouwmans, Thierry, Javed, Sajid, Sultana, Maryam, Jung, Soon Ki
Format Journal Article
LanguageEnglish
Published United States Elsevier Ltd 01.09.2019
Elsevier
Subjects
Auto-encoders networks
Background subtraction
Computer Science
Convolutional neural networks
Generative adversarial networks
Image Processing
Restricted Boltzmann machines
Generative adversarial networks
Restricted Boltzmann machines
Convolutional neural networks
Background subtraction
Auto-encoders networks
Online AccessGet full text
ISSN0893-6080
1879-2782
1879-2782
DOI10.1016/j.neunet.2019.04.024

Cover

Abstract Conventional neural networks have been demonstrated to be a powerful framework for background subtraction in video acquired by static cameras. Indeed, the well-known Self-Organizing Background Subtraction (SOBS) method and its variants based on neural networks have long been the leading methods on the large-scale CDnet 2012 dataset during a long time. Convolutional neural networks, which are used in deep learning, have been recently and excessively employed for background initialization, foreground detection, and deep learned features. The top background subtraction methods currently used in CDnet 2014 are based on deep neural networks, and have demonstrated a large performance improvement in comparison to conventional unsupervised approaches based on multi-feature or multi-cue strategies. Furthermore, since the seminal work of Braham and Van Droogenbroeck in 2016, a large number of studies on convolutional neural networks applied to background subtraction have been published, and a continual gain of performance has been achieved. In this context, we provide the first review of deep neural network concepts in background subtraction for novices and experts in order to analyze this success and to provide further directions. To do so, we first surveyed the background initialization and background subtraction methods based on deep neural networks concepts, and also deep learned features. We then discuss the adequacy of deep neural networks for the task of background subtraction. Finally, experimental results are presented for the CDnet 2014 dataset.
AbstractList Conventional neural networks have been demonstrated to be a powerful framework for background subtraction in video acquired by static cameras. Indeed, the well-known Self-Organizing Background Subtraction (SOBS) method and its variants based on neural networks have long been the leading methods on the large-scale CDnet 2012 dataset during a long time. Convolutional neural networks, which are used in deep learning, have been recently and excessively employed for background initialization, foreground detection, and deep learned features. The top background subtraction methods currently used in CDnet 2014 are based on deep neural networks, and have demonstrated a large performance improvement in comparison to conventional unsupervised approaches based on multi-feature or multi-cue strategies. Furthermore, since the seminal work of Braham and Van Droogenbroeck in 2016, a large number of studies on convolutional neural networks applied to background subtraction have been published, and a continual gain of performance has been achieved. In this context, we provide the first review of deep neural network concepts in background subtraction for novices and experts in order to analyze this success and to provide further directions. To do so, we first surveyed the background initialization and background subtraction methods based on deep neural networks concepts, and also deep learned features. We then discuss the adequacy of deep neural networks for the task of background subtraction. Finally, experimental results are presented for the CDnet 2014 dataset.
Conventional neural networks have been demonstrated to be a powerful framework for background subtraction in video acquired by static cameras. Indeed, the well-known Self-Organizing Background Subtraction (SOBS) method and its variants based on neural networks have long been the leading methods on the large-scale CDnet 2012 dataset during a long time. Convolutional neural networks, which are used in deep learning, have been recently and excessively employed for background initialization, foreground detection, and deep learned features. The top background subtraction methods currently used in CDnet 2014 are based on deep neural networks, and have demonstrated a large performance improvement in comparison to conventional unsupervised approaches based on multi-feature or multi-cue strategies. Furthermore, since the seminal work of Braham and Van Droogenbroeck in 2016, a large number of studies on convolutional neural networks applied to background subtraction have been published, and a continual gain of performance has been achieved. In this context, we provide the first review of deep neural network concepts in background subtraction for novices and experts in order to analyze this success and to provide further directions. To do so, we first surveyed the background initialization and background subtraction methods based on deep neural networks concepts, and also deep learned features. We then discuss the adequacy of deep neural networks for the task of background subtraction. Finally, experimental results are presented for the CDnet 2014 dataset.Conventional neural networks have been demonstrated to be a powerful framework for background subtraction in video acquired by static cameras. Indeed, the well-known Self-Organizing Background Subtraction (SOBS) method and its variants based on neural networks have long been the leading methods on the large-scale CDnet 2012 dataset during a long time. Convolutional neural networks, which are used in deep learning, have been recently and excessively employed for background initialization, foreground detection, and deep learned features. The top background subtraction methods currently used in CDnet 2014 are based on deep neural networks, and have demonstrated a large performance improvement in comparison to conventional unsupervised approaches based on multi-feature or multi-cue strategies. Furthermore, since the seminal work of Braham and Van Droogenbroeck in 2016, a large number of studies on convolutional neural networks applied to background subtraction have been published, and a continual gain of performance has been achieved. In this context, we provide the first review of deep neural network concepts in background subtraction for novices and experts in order to analyze this success and to provide further directions. To do so, we first surveyed the background initialization and background subtraction methods based on deep neural networks concepts, and also deep learned features. We then discuss the adequacy of deep neural networks for the task of background subtraction. Finally, experimental results are presented for the CDnet 2014 dataset.
Author Javed, Sajid
Sultana, Maryam
Jung, Soon Ki
Bouwmans, Thierry
Author_xml – sequence: 1
  givenname: Thierry
  surname: Bouwmans
  fullname: Bouwmans, Thierry
  email: tbouwman@univ-lr.fr
  organization: Lab. MIA, University La Rochelle, France
– sequence: 2
  givenname: Sajid
  surname: Javed
  fullname: Javed, Sajid
  organization: Department of Computer Science, University of Warwick, UK
– sequence: 3
  givenname: Maryam
  surname: Sultana
  fullname: Sultana, Maryam
  organization: Department of Computer Science and Engineering, Kyungpook National University, Republic of Korea
– sequence: 4
  givenname: Soon Ki
  surname: Jung
  fullname: Jung, Soon Ki
  organization: Department of Computer Science and Engineering, Kyungpook National University, Republic of Korea
BackLink https://www.ncbi.nlm.nih.gov/pubmed/31129491$$D View this record in MEDLINE/PubMed
https://hal.science/hal-02118618$$DView record in HAL
BookMark eNqFkU9v1DAQxS1URLeFb4BQjnBIsGPHcXpAWpU_RVqJC5ytiTMBb5M42M5W_fY4pPTAAS4z0uj3nkbvXZCzyU1IyEtGC0aZfHssJlwmjEVJWVNQUdBSPCE7puomL2tVnpEdVQ3PJVX0nFyEcKSUSiX4M3LOGSsb0bAd6d8jzlly8jCkFe-cv82MmwzOMWS981kL5va7d8vUZWFpowcTrZuu9lm4DxFHiNZkHk8W7zJIjHHjDD5dT5jhCYYFVvw5edrDEPDFw74k3z5--Hp9kx--fPp8vT_kpqIq5qA6wSXDvjaVEooJowzr2r6WbRpCAWDPZV0DbaBWpu8aQ3kFHa8kr2re80vyZvP9AYOevR3B32sHVt_sD3q90ZIxJZk6scS-3tjZu58LhqhHGwwOA0zolqDLkjMlGilFQl89oEs7Yvfo_CfHBIgNMN6F4LF_RBjVa136qLe69FqXpiJ9svpe_SUzNv4OLOVsh_-J321iTIGm_L0OxmJqrrMeTdSds_82-AVpo7Rp
CitedBy_id crossref_primary_10_3390_agronomy14081800
crossref_primary_10_1109_TIP_2021_3122102
crossref_primary_10_3390_electronics12153234
crossref_primary_10_1016_j_ijleo_2020_164563
crossref_primary_10_1186_s10033_024_01068_8
crossref_primary_10_1073_pnas_1915252117
crossref_primary_10_1109_ACCESS_2024_3452633
crossref_primary_10_3390_electronics11030408
crossref_primary_10_1016_j_cviu_2020_103101
crossref_primary_10_3390_electronics12153346
crossref_primary_10_1016_j_ecoenv_2023_115894
crossref_primary_10_1109_TII_2020_3009111
crossref_primary_10_3390_coatings11070845
crossref_primary_10_2478_ttj_2020_0010
crossref_primary_10_1016_j_cviu_2022_103584
crossref_primary_10_1109_TII_2021_3064845
crossref_primary_10_1016_j_imavis_2019_08_007
crossref_primary_10_1117_1_JEI_32_2_023021
crossref_primary_10_3390_s22093171
crossref_primary_10_1007_s11042_023_16344_3
crossref_primary_10_3390_app11041807
crossref_primary_10_1007_s11063_022_11055_6
crossref_primary_10_1016_j_knosys_2024_111765
crossref_primary_10_1109_TCSVT_2020_2991191
crossref_primary_10_1016_j_imavis_2024_105021
crossref_primary_10_1016_j_engappai_2020_104000
crossref_primary_10_1002_stc_2910
crossref_primary_10_1007_s00366_020_01272_9
crossref_primary_10_1016_j_scitotenv_2024_170698
crossref_primary_10_1142_S219688882350015X
crossref_primary_10_3390_app13137671
crossref_primary_10_4218_etrij_2023_0115
crossref_primary_10_3389_fenrg_2023_1175102
crossref_primary_10_3390_sym13071158
crossref_primary_10_1016_j_cviu_2025_104290
crossref_primary_10_1007_s00138_024_01570_y
crossref_primary_10_1016_j_autcon_2021_103862
crossref_primary_10_1109_JSEN_2021_3054940
crossref_primary_10_1007_s10462_020_09811_y
crossref_primary_10_1007_s10661_019_7980_4
crossref_primary_10_1109_ACCESS_2021_3071163
crossref_primary_10_1109_JQE_2022_3177793
crossref_primary_10_1007_s00371_022_02417_1
crossref_primary_10_1016_j_future_2022_03_039
crossref_primary_10_3169_mta_9_247
crossref_primary_10_3390_electronics10101187
crossref_primary_10_25092_baunfbed_878224
crossref_primary_10_1007_s13735_022_00232_x
crossref_primary_10_1098_rsif_2022_0676
crossref_primary_10_1002_aelm_202200876
crossref_primary_10_1007_s11071_024_10423_2
crossref_primary_10_1109_ACCESS_2020_3022818
crossref_primary_10_1016_j_cviu_2022_103560
crossref_primary_10_1093_chemle_upae181
crossref_primary_10_2200_S01127ED1V01Y202109COV019
crossref_primary_10_3390_make1030044
crossref_primary_10_1016_j_infrared_2025_105740
crossref_primary_10_1038_s41433_024_03184_0
crossref_primary_10_1016_j_neunet_2022_10_023
crossref_primary_10_1109_TSUSC_2022_3177688
crossref_primary_10_1016_j_jjimei_2022_100066
crossref_primary_10_1016_j_eswa_2022_117947
crossref_primary_10_1109_TIFS_2024_3447237
crossref_primary_10_1007_s11831_025_10250_7
crossref_primary_10_3390_app13063812
crossref_primary_10_1016_j_neucom_2022_07_081
crossref_primary_10_1145_3721136
crossref_primary_10_1039_D1MD00074H
crossref_primary_10_1109_TCSVT_2020_3023175
crossref_primary_10_3390_jimaging8010009
crossref_primary_10_1007_s11042_020_09838_x
crossref_primary_10_1007_s10851_020_00967_4
crossref_primary_10_1109_ACCESS_2022_3195053
crossref_primary_10_1109_JSEN_2024_3358181
crossref_primary_10_1007_s10278_024_01256_x
crossref_primary_10_1109_TIP_2021_3055063
crossref_primary_10_1016_j_fmre_2024_08_009
crossref_primary_10_1109_ACCESS_2019_2927745
crossref_primary_10_3390_robotics13080114
crossref_primary_10_3390_electronics12132975
crossref_primary_10_3390_electronics11101590
crossref_primary_10_1016_j_cviu_2020_103022
crossref_primary_10_1109_TIP_2024_3378473
crossref_primary_10_1515_jisys_2023_0041
crossref_primary_10_3390_rs13040653
crossref_primary_10_1007_s00521_022_07141_4
crossref_primary_10_1109_TITS_2021_3077883
crossref_primary_10_4236_ojs_2021_115040
crossref_primary_10_1109_ACCESS_2020_2992494
crossref_primary_10_1016_j_cviu_2021_103355
crossref_primary_10_1007_s10044_024_01227_6
crossref_primary_10_1142_S0218001420500238
crossref_primary_10_1186_s13321_023_00781_1
crossref_primary_10_3390_s19061352
crossref_primary_10_3390_sym12050840
crossref_primary_10_1109_TIP_2022_3162961
crossref_primary_10_1109_MMUL_2021_3083701
crossref_primary_10_1049_iet_ipr_2019_0769
crossref_primary_10_1016_j_cviu_2020_103032
crossref_primary_10_1109_TNNLS_2021_3131406
crossref_primary_10_1109_TPAMI_2020_3042093
crossref_primary_10_3390_s20236973
crossref_primary_10_1109_TMM_2020_3006419
crossref_primary_10_1007_s11042_020_10249_1
crossref_primary_10_1016_j_asoc_2022_109799
crossref_primary_10_1109_ACCESS_2024_3381612
crossref_primary_10_1016_j_neunet_2021_03_024
crossref_primary_10_1016_j_patcog_2022_108719
crossref_primary_10_1007_s11633_022_1378_4
crossref_primary_10_1007_s11042_022_12832_0
crossref_primary_10_1016_j_energy_2023_127212
crossref_primary_10_1080_23311975_2025_2460627
crossref_primary_10_1016_j_imu_2023_101428
crossref_primary_10_1016_j_neucom_2019_08_087
crossref_primary_10_3233_ICA_200621
crossref_primary_10_3390_electronics11071122
crossref_primary_10_1021_acs_chemrev_3c00708
crossref_primary_10_1109_TIE_2020_3013747
crossref_primary_10_3390_math12162529
crossref_primary_10_1007_s00371_021_02286_0
crossref_primary_10_1016_j_egyr_2023_05_260
crossref_primary_10_1109_JSEN_2023_3263539
crossref_primary_10_1016_j_cviu_2022_103501
crossref_primary_10_1007_s00500_023_08208_7
crossref_primary_10_1109_TIP_2023_3336176
crossref_primary_10_1016_j_cosrev_2021_100379
crossref_primary_10_1109_LSP_2023_3236585
crossref_primary_10_1063_5_0151244
crossref_primary_10_5498_wjp_v12_i2_204
crossref_primary_10_3390_app13148073
crossref_primary_10_32604_cmc_2022_021850
crossref_primary_10_3390_su16188214
crossref_primary_10_1109_MITS_2021_3122926
crossref_primary_10_1007_s11227_022_05019_9
crossref_primary_10_1145_3524497
crossref_primary_10_1007_s11042_024_19180_1
crossref_primary_10_1016_j_neunet_2023_06_036
crossref_primary_10_1007_s00202_023_01952_x
crossref_primary_10_1109_TNNLS_2022_3170789
crossref_primary_10_1109_ACCESS_2020_3021795
crossref_primary_10_1109_TCSS_2021_3137306
crossref_primary_10_2139_ssrn_3988170
crossref_primary_10_3389_fpsyg_2020_515531
crossref_primary_10_1016_j_patcog_2021_108350
crossref_primary_10_1111_liv_70038
crossref_primary_10_1109_TITS_2022_3184978
crossref_primary_10_1007_s11042_025_20753_x
crossref_primary_10_3390_su141710994
crossref_primary_10_1016_j_neucom_2021_01_030
crossref_primary_10_1016_j_trc_2023_104205
crossref_primary_10_1016_j_mlwa_2021_100058
crossref_primary_10_1016_j_neucom_2022_06_104
crossref_primary_10_1109_TETCI_2021_3100641
crossref_primary_10_1007_s13735_023_00270_z
crossref_primary_10_1007_s00362_022_01323_x
crossref_primary_10_1109_TIP_2022_3172851
crossref_primary_10_1155_2022_5485284
crossref_primary_10_1007_s11760_022_02337_6
crossref_primary_10_1016_j_imavis_2022_104425
crossref_primary_10_1021_acsabm_3c00054
crossref_primary_10_1007_s12204_023_2603_1
crossref_primary_10_1016_j_eswa_2022_118873
crossref_primary_10_1364_OE_468648
crossref_primary_10_1109_OJITS_2022_3170075
crossref_primary_10_1371_journal_pcbi_1012327
crossref_primary_10_3390_s20123420
crossref_primary_10_1016_j_eswa_2022_118995
crossref_primary_10_1109_TCSVT_2021_3088130
crossref_primary_10_57062_ijpem_st_2023_00136
crossref_primary_10_1007_s00034_024_02808_w
crossref_primary_10_1007_s11042_019_08506_z
crossref_primary_10_1109_TII_2020_3017078
crossref_primary_10_1007_s10851_022_01068_0
crossref_primary_10_1016_j_engappai_2024_108873
crossref_primary_10_1016_j_mlwa_2021_100037
crossref_primary_10_1109_JPROC_2021_3117472
crossref_primary_10_1109_JSEN_2021_3121582
crossref_primary_10_1002_tal_70002
crossref_primary_10_1016_j_patrec_2020_10_011
crossref_primary_10_1109_TCSVT_2019_2951778
crossref_primary_10_1007_s00530_022_01014_5
crossref_primary_10_1016_j_knosys_2020_105650
crossref_primary_10_1109_TAI_2023_3299903
crossref_primary_10_1007_s11042_020_09386_4
crossref_primary_10_1109_TIP_2020_2983598
crossref_primary_10_3390_app12031289
crossref_primary_10_1007_s11356_023_26782_z
crossref_primary_10_1016_j_cosrev_2019_100204
crossref_primary_10_3390_a12070128
crossref_primary_10_1007_s00024_022_03208_4
crossref_primary_10_1016_j_jvcir_2020_102907
crossref_primary_10_1016_j_resourpol_2020_101604
crossref_primary_10_1007_s12652_023_04686_7
crossref_primary_10_1007_s11042_023_15849_1
crossref_primary_10_1088_2632_2153_abd614
crossref_primary_10_1142_S2251171723400056
crossref_primary_10_1109_TVT_2020_3043575
crossref_primary_10_1016_j_jvcir_2021_103278
crossref_primary_10_1155_2022_7651539
crossref_primary_10_1016_j_imu_2023_101284
crossref_primary_10_1155_2020_7397169
crossref_primary_10_1007_s00530_023_01139_1
crossref_primary_10_1016_j_iswa_2022_200112
crossref_primary_10_1109_ACCESS_2021_3123975
crossref_primary_10_3390_app10082749
crossref_primary_10_1088_1361_6501_aca497
crossref_primary_10_1155_2022_7432615
crossref_primary_10_1088_1755_1315_539_1_012102
crossref_primary_10_3390_app14031045
crossref_primary_10_1016_j_ijar_2021_04_007
crossref_primary_10_1016_j_mlwa_2021_100124
crossref_primary_10_1155_2022_4331351
crossref_primary_10_3390_s23146492
Cites_doi 10.1109/CVPR.2017.467
10.1109/ISCAS.2018.8351344
10.1007/978-3-319-70742-6_22
10.1016/j.imavis.2012.08.017
10.1109/IJCNN.2018.8489230
10.1007/978-3-642-33179-4_41
10.1109/IJCNN.2009.5178632
10.1016/j.neunet.2014.09.003
10.1109/TCSVT.2015.2424052
10.1109/ICPR.2016.7899623
10.1145/3019612.3019687
10.1016/j.patcog.2017.10.013
10.1109/FCV.2015.7103745
10.1109/CVPR.2017.790
10.1109/AVSS.2017.8078550
10.1109/CVPRW.2014.65
10.1109/ICASSP.2019.8682914
10.1109/TPAMI.2006.68
10.1109/ICME.2018.8486556
10.1016/0893-6080(91)90009-T
10.1109/TASLP.2018.2876171
10.1007/3-540-45053-X_48
10.1109/TITS.2017.2749964
10.1016/0893-6080(89)90020-8
10.1109/ICMLA.2013.43
10.1016/j.neucom.2016.12.038
10.1016/j.neucom.2015.05.082
10.1109/CVPR.1999.784637
10.1016/j.neunet.2018.08.019
10.1109/LGRS.2018.2841502
10.1109/JSTSP.2018.2869111
10.1145/2647868.2654889
10.1109/TNNLS.2018.2852738
10.1109/ICIP.2017.8297144
10.1007/978-3-030-00563-4_8
10.1109/TFUZZ.2016.2574915
10.1109/AVSS.2017.8078483
10.1504/IJSTDS.2019.097607
10.1007/978-3-540-76856-2_31
10.5772/38267
10.1109/CVPR.2016.90
10.1109/TFUZZ.2016.2639064
10.1109/ICCVW.2015.123
10.1109/ITSC.2004.1399038
10.1109/CVPRW.2016.109
10.1109/TITS.2011.2159266
10.1007/978-3-319-23234-8_32
10.1109/IWSSIP.2016.7502717
10.1016/j.cviu.2013.12.003
10.1109/TPAMI.2008.87
10.1007/978-3-642-35286-7_23
10.1007/978-3-319-23222-5_62
10.1109/TCSI.2017.2729787
10.1109/TIP.2008.924285
10.1109/CVPRW.2014.68
10.1109/TIP.2017.2728181
10.1109/ICPR.2016.7899619
10.1109/MWSCAS.2018.8623825
10.1109/ICIP.2018.8451816
10.1007/978-3-030-00776-8_48
10.1109/TASLP.2018.2842159
10.1109/TASLP.2018.2881912
10.1109/TPAMI.2012.230
10.1016/j.patrec.2018.05.018
10.1007/11553595_20
10.1109/ICCV.2017.548
10.1109/CVPR.2017.452
10.1109/WACV.2019.00193
10.3390/jimaging4070090
10.1109/TIP.2017.2746268
10.1007/978-3-319-24574-4_28
10.1109/CIS.2009.178
10.1109/CVPR.2015.7298965
10.1109/AVSS.2013.6636617
10.1145/1015706.1015718
10.1145/3194554
10.1007/978-3-319-70742-6_23
10.1109/IJCNN.2013.6706737
10.1109/CVPRW.2014.126
10.1007/978-3-642-33765-9_8
10.1109/34.598236
10.1016/j.patrec.2016.12.024
10.1145/2647868.2654914
10.1109/AVSS.2013.6636673
10.3390/s18124269
10.1145/3097983.3098052
10.1007/11919476_5
10.1016/j.neunet.2017.09.007
10.1016/j.patrec.2016.11.022
10.1109/TIP.2015.2427519
10.1016/j.patrec.2005.11.005
10.1109/ICPR.2016.7899965
10.1016/j.aeue.2009.05.004
10.3390/jimaging4060079
10.1016/j.patcog.2014.09.009
10.1109/ICAIPR.2016.7585207
10.1007/978-3-540-87536-9_67
10.1162/neco_a_00984
10.1109/ACCESS.2016.2551458
10.1109/TGRS.2018.2849692
10.1109/ICIP.2018.8451540
10.1109/CVPR.2014.81
10.1109/ICIP.2010.5653489
10.1162/neco.1997.9.8.1735
10.1109/SIU.2018.8404636
10.1016/j.neunet.2017.12.012
10.1109/ICCV.2009.5459202
10.1109/CVPRW.2012.6238925
10.1007/978-3-030-00374-6_32
10.1109/ISIE.2017.8001492
10.1109/ICASSP.2013.6638947
10.1109/IJCNN.2013.6706734
10.1109/ICCV.2015.169
10.1038/s41928-018-0023-2
10.1109/ICPR.2016.7899617
10.1007/978-3-540-89639-5_74
10.1016/j.neunet.2017.10.001
10.1145/3061639.3062326
10.1109/5.58323
10.1049/iet-ipr.2017.1055
10.1109/LGRS.2018.2859024
10.1109/TIP.2010.2101613
10.1109/SMC.2018.00289
10.1016/j.cosrev.2016.11.001
10.1080/15599612.2014.890686
10.1109/ICCVW.2015.125
10.1007/978-3-642-02282-1_33
10.1109/CVPR.2018.00084
10.1109/ACCESS.2018.2817129
10.1109/IJCNN.2011.6033261
10.1016/0031-3203(95)00163-8
10.1109/CVPR.2017.17
10.1109/TPAMI.2012.132
10.1016/j.patrec.2018.08.002
10.1109/MSP.2018.2826566
10.1016/j.cviu.2013.07.007
10.1109/ICCVW.2017.188
10.1007/978-3-319-10584-0_35
10.1109/TNNLS.2013.2242092
10.1016/j.neunet.2018.10.016
10.1109/TIP.2016.2598681
10.1109/IJCNN.2017.7966300
10.1109/CVPR.2018.00125
10.1109/TIP.2017.2695882
10.1109/ICCV.2015.123
10.1007/978-3-642-04146-4_63
10.1109/AVSS.2018.8639077
10.1109/CVPR.2016.517
10.1109/ICSPCC.2012.6335632
10.1109/ICIP.2012.6467087
10.1109/AVSS.2010.45
10.1007/s12530-012-9047-4
10.24963/ijcai.2018/378
10.1109/ICPR.2018.8545597
10.1016/j.cviu.2016.08.005
10.1109/ICPR.2016.7899616
10.1109/CVPR.2016.308
10.1111/2041-210X.13011
10.1109/CVPR.2015.7298594
10.1109/ICCVW.2017.221
10.1109/CVPR.2017.565
10.1109/AVSS.2017.8078475
10.1016/j.patrec.2017.01.011
10.1162/neco.2006.18.7.1527
10.1049/ic.2015.0105
10.1109/CVPR.2004.1315179
10.1109/ICPR.2008.4761047
10.1007/978-3-642-04697-1_39
10.1109/TCYB.2015.2419737
10.1109/TVCG.2018.2864500
10.1007/s00138-012-0421-9
10.1609/aaai.v33i01.33019176
10.1117/1.JEI.24.4.043011
10.1007/s11263-019-01151-x
10.1109/ICME.2014.6890140
10.1016/j.asoc.2018.05.018
10.5220/0005266303950402
10.1109/TIP.2004.836169
10.1109/ICCV.1999.791228
10.1109/CVPR.2009.5206848
10.1109/TPAMI.2016.2577031
10.1016/j.neucom.2019.01.079
10.1109/Cybermatics_2018.2018.00093
10.1007/11881599_110
10.1109/ICPR.2018.8545320
10.1109/AVSS.2015.7301753
10.1109/TENCONSpring.2016.7519418
10.1016/j.patcog.2014.10.020
10.1007/3-540-49256-9_16
10.1109/VCIP.2016.7805552
10.1007/s00138-013-0562-5
10.1109/CVPRW.2014.67
10.1007/BF00994018
10.1007/s10851-015-0610-z
10.1007/978-3-319-70742-6_24
10.1007/978-3-319-23222-5_60
10.1007/978-3-319-23222-5_57
10.1016/j.neucom.2018.01.092
10.1109/TITS.2017.2754099
10.1155/2011/972961
10.1109/ICOMIS.2018.8644960
10.1007/BF02551274
10.1109/WACV.2015.137
10.1609/aaai.v32i1.11668
10.1109/AVSS.2017.8078547
10.1109/CVPRW.2012.6238922
10.1007/978-3-642-31295-3_14
10.1007/978-3-319-70742-6_21
10.1109/ICIP.2015.7350841
10.1609/aaai.v30i1.10274
10.1016/j.cosrev.2018.01.004
10.1109/CVPR.2016.278
10.1117/1.JEI.28.1.013038
10.1109/SNSP.2018.00089
10.1109/TASLP.2018.2876169
10.1007/BF02478259
10.1609/aaai.v29i1.9481
10.1016/j.cosrev.2019.100204
10.1109/ICIP.2011.6116367
10.1007/978-3-642-33275-3_2
10.1016/j.cviu.2013.11.006
10.1016/j.patrec.2017.10.034
10.3390/jimaging4050071
10.1109/ICIP.2018.8451603
10.1109/ICASSP.2018.8461540
10.1109/ICME.2018.8486510
10.1109/WMVC.2009.5399242
10.1088/1361-6420/aa9a90
10.1109/ICCV.2013.419
10.1109/5.726791
10.1109/IJCNN.2014.6889404
10.3390/jimaging4060078
10.1109/MECO.2017.7977207
10.1145/2695664.2695863
ContentType Journal Article
Copyright 2019 Elsevier Ltd
Copyright © 2019 Elsevier Ltd. All rights reserved.
Attribution - NonCommercial
Copyright_xml – notice: 2019 Elsevier Ltd
– notice: Copyright © 2019 Elsevier Ltd. All rights reserved.
– notice: Attribution - NonCommercial
DBID AAYXX
CITATION
NPM
7X8
1XC
VOOES
DOI 10.1016/j.neunet.2019.04.024
DatabaseName CrossRef
PubMed
MEDLINE - Academic
Hyper Article en Ligne (HAL)
Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
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
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1879-2782
EndPage 66
ExternalDocumentID oai_HAL_hal_02118618v1
31129491
10_1016_j_neunet_2019_04_024
S0893608019301303
Genre Journal Article
Review
GroupedDBID ---
--K
--M
-~X
.DC
.~1
0R~
123
186
1B1
1RT
1~.
1~5
29N
4.4
457
4G.
53G
5RE
5VS
6TJ
7-5
71M
8P~
9JM
9JN
AABNK
AACTN
AADPK
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXLA
AAXUO
AAYFN
ABAOU
ABBOA
ABCQJ
ABEFU
ABFNM
ABFRF
ABHFT
ABIVO
ABJNI
ABLJU
ABMAC
ABXDB
ABYKQ
ACAZW
ACDAQ
ACGFO
ACGFS
ACIUM
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADGUI
ADJOM
ADMUD
ADRHT
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGWIK
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ARUGR
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
G8K
GBLVA
GBOLZ
HLZ
HMQ
HVGLF
HZ~
IHE
J1W
JJJVA
K-O
KOM
KZ1
LG9
LMP
M2V
M41
MHUIS
MO0
MOBAO
MVM
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SCC
SDF
SDG
SDP
SES
SEW
SNS
SPC
SPCBC
SSN
SST
SSV
SSW
SSZ
T5K
TAE
UAP
UNMZH
VOH
WUQ
XPP
ZMT
~G-
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGCQF
AGQPQ
AGRNS
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
BNPGV
CITATION
SSH
NPM
7X8
EFKBS
1XC
VOOES
ID FETCH-LOGICAL-c508t-a8d4361ef7c584814c8c1dbf76bbf748aaef3677a09a78cfd9c035ad3563573f3
IEDL.DBID .~1
ISSN 0893-6080
1879-2782
IngestDate Thu Jun 19 06:40:31 EDT 2025
Fri Sep 05 04:32:08 EDT 2025
Thu Apr 03 07:09:00 EDT 2025
Tue Jul 01 01:24:33 EDT 2025
Thu Apr 24 22:54:10 EDT 2025
Fri Feb 23 02:28:38 EST 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Generative adversarial networks
Restricted Boltzmann machines
Convolutional neural networks
Background subtraction
Auto-encoders networks
Language English
License Copyright © 2019 Elsevier Ltd. All rights reserved.
Attribution - NonCommercial: http://creativecommons.org/licenses/by-nc
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c508t-a8d4361ef7c584814c8c1dbf76bbf748aaef3677a09a78cfd9c035ad3563573f3
Notes ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Undefined-3
ORCID 0000-0003-4018-8856
OpenAccessLink https://hal.science/hal-02118618
PMID 31129491
PQID 2231849664
PQPubID 23479
PageCount 59
ParticipantIDs hal_primary_oai_HAL_hal_02118618v1
proquest_miscellaneous_2231849664
pubmed_primary_31129491
crossref_primary_10_1016_j_neunet_2019_04_024
crossref_citationtrail_10_1016_j_neunet_2019_04_024
elsevier_sciencedirect_doi_10_1016_j_neunet_2019_04_024
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate September 2019
2019-09-00
2019-Sep
20190901
2019-09
PublicationDateYYYYMMDD 2019-09-01
PublicationDate_xml – month: 09
  year: 2019
  text: September 2019
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Neural networks
PublicationTitleAlternate Neural Netw
PublicationYear 2019
Publisher Elsevier Ltd
Elsevier
Publisher_xml – name: Elsevier Ltd
– name: Elsevier
References Li, D., Jiang, M., Fang, Y., Huang, Y., & Zhao, C. (2018). Deep video foreground target extraction with complex scenes. In
Cohen, N., & Shashua, A. (2014). SimNets: A generalization of convolutional networks. In
Shahbaz, A., Hernandez, D., & Jo, K. (2017). Optimal color space based probabilistic foreground detector for video surveillance systems. In
(pp. 1140–1148).
Zhao, Wang, Cham (b391) 2011
Vosters, Shan, Gritti (b333) 2012; 30
Zheng, S., Song, Y., Leung, T., & Goodfellow, I. (2018). Improving the robustness of deep neural networks via stability training. In
Xiao, H., Feng, J., Lin, G., Liu, Y., & Zhang, M. (2018). MoNet: Deep motion exploitation for video object segmentation. In
Vidal (b331) 2017
Farcas, D., & Bouwmans, T. (2010). Background modeling via a supervised subspace learning. In
Wu, Lin, Tang (b360) 2015
Lee, Hedley (b189) 2002
Gu, Wang, Kuen, Ma, Shahroudy, Shuai (b122) 2018; 77
Javed, Mahmood, Bouwmans, Jung (b166) 2017; 26
Sasikumar (b283) 2018
Liang, X., Liao, S., Wang, X., Liu, W., Chen, Y., & Li, S. (2018). Deep background subtraction with guided learning. In
Farcas, Marghes, Bouwmans (b96) 2012; 23
Chacon-Muguia, M., Gonzalez-Duarte, S., & Vega, P. (2009). Simplified SOM-neural model for video segmentation of moving objects. In
Xu, P., Ye, M., Li, X., Liu, Q., Yang, Y., & Ding, J. (2014). Dynamic background learning through deep auto-encoder networks. In
.
Goel, Weng, Poupart (b113) 2018
Qu, Z., Yu, S., & Fu, M. (2016). Motion background modeling based on context-encoder. In
Fischer, Dosovitskiy, Ilg, Hausser, Hazirbas, Golkov (b101) 2015
Cohen, N., & Shashua, A. (2016). Convolutional rectifier networks as generalized tensor decompositions. In
Dumoulin, Visin (b90) 2018
Tavakkoli, A., Nicolescu, M., Nicolescu, M., & Bebis, G. (2008). Incremental SVDD training: Improving efficiency of background modeling in videos. In
Yang, Cheng, Su, Li (b369) 2016; 26
Huynh (b155) 2017
Szegedy, C., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In
Chan (b46) 2019; 28
Chen, Y., Wang, J., & Lu, H. (2015). Learning sharable models for robust background subtraction. In
(pp. 772–781).
Liang, D., Kaneko, S., Hashimoto, M., Iwata, K., Zhao, X., & Satoh, Y. (2013). Co-occurrence-based adaptive background model for robust object detection. In
(pp. 187–190).
Akilan, T., & Wu, J. (2018). Double encoding - slow decoding image to image CNN for foreground identification with application towards intelligent transportation. In
Chen, Papandreou, Kokkinos, Murphy, Yuille (b52) 2016
Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In
Yan, Y., Zhao, H., Kao, F., Vargas, V., Zhao, S., & Ren, J. (2018). Deep background subtraction of thermal and visible imagery for pedestrian detection in videos. In
Chang, B., Meng, L., Haber, E., Ruthotto, L., Begert, D., & Holtham, E. (2018). Reversible architectures for arbitrarily deep residual neural networks. In
Liang, Kaneko, Hashimoto, Iwata, Zhao, Satoh (b196) 2014
(pp. 63–68).
Wang, Chen (b337) 2018; 26
Goyette, N., Jodoin, P., Porikli, F., Konrad, J., & Ishwar, P. (2012). Changedetection.net: A new change detection benchmark dataset. In
Sultana, Jung (b307) 2019
Kawaguchi, K. (2016). Deep learning without poor local minima. In
Zin, T., Tin, P., Toriu, T., & Hama, H. A new background subtraction method using bivariate Poisson process. In
Xu, Ithapu, Mukherjee, Rehg, Singh (b364) 2013
Bouwmans, Zahzah (b30) 2014; 122
Javed, S., Sobral, A., Bouwmans, T., & Jung, S. (2015). OR-PCA with dynamic feature selection for robust background subtraction. In
Sobral, A., Javed, S., Jung, S., Bouwmans, T., & Zahzah, E. (2015). Online stochastic tensor decomposition for background subtraction in multispectral video sequences. In
Creswell, Bharath (b73) 2019; 30
Mehran, Bouwmans (b230) 2018; 28
Zhong, Wei, Lin, Zhang (b399) 2019; 110
Wang (b355) 2018; 1
Elgammal, A., & Davis, L. (2000). Non-parametric model for background subtraction. In
Hornik (b150) 1991; 4
(pp. 163–170).
Camplani, M., Maddalena, L., Alcover, G. M., Petrosino, A., & Salgado, L. (2017a). RGB-D dataset: Background learning for detection and tracking from RGBD videos. In
Suykens (b310) 2017; 29
Chacon-Murguia, M., Ramirez-Alonso, G., & Gonzalez-Duarte, S. (2013). Improvement of a neural-fuzzy motion detection vision model for complex scenario conditions. In
Basu, Mukhopadhyay, Karki, Biano, Ganguly, Nemani (b19) 2018; 97
Lopez-Rubio, F., Lopez-Rubio, E., Luque-Baena, R., Dominguez, E., & Palomo, E. (2014). Color space selection for self-organizing map based foreground detection in video sequences. In
Liang, Kaneko, Hashimoto, Iwata, Zhao (b194) 2015; 48
(pp. 585–593).
Krestinskaya, O., Salama, K., & James, A. (2018a). Analog back propagation learning circuits for memristive crossbar neural networks. In
Vaswani, N., Bouwmans, T., Javed, S., & Narayanamurth, P. (2018a). Robust PCA and robust subspace tracking: A comparative evaluation. In
Wang, Bebis, Nicolescu, Nicolescu, Miller (b335) 2008
Maddalena, L., & Petrosino, A. (2009a). Multivalued background/foreground separation for moving object detection. In
(pp. 1670–1675).
(pp. 410–414).
Bouwmans, T., & Garcia-Garcia, B. (2019). Background Subtraction in Real Applications: Challenges, Current Models and Future Directions, Preprint.
Javed, S., Bouwmans, T., & Jung, S. (2017). SBMI-LTD: Stationary background model initialization based on low-rank tensor decomposition. In
Zhao, Zhou, Xie, Zhang, Cichocki (b394) 2016
Fernandez-Sanchez, Rubio, Diaz, Ros (b100) 2014
Wang, Z., Zhang, L., & Bao, H. PNN based motion detection with adaptive learning rate. In
Gong, M., & Cheng, L. (2011). Incorporating estimated motion in real-time background subtraction. In
Brunettia, Buongiorno, Trotta, Bevilacqua (b34) 2018; 300
(pp. 2296–2300).
Chen, Zhang, Du (b55) 2018
(pp. 971–976).
Jodoin (b173) 2015
Guo, X., Wang, X., Yang, L., Cao, X., & Ma, Y. (2014). Robust Foreground Detection using Smoothness and Arbitrariness Constraints. In
Vacavant, A., Chateau, T., Wilhelm, A., & Lequievre, L. (2012). A benchmark dataset for foreground/background extraction. In
Zhao, Zhang, Fang (b392) 2015
(pp. 242–253).
Maddalena, Petrosino (b212) 2008
Yu, Wang, Davis (b376) 2018
Bianco, Ciocca, Schettini (b21) 2015
Cinelli (b65) 2017
Babaee, Dinh, Rigoll (b10) 2017
Stauffer, C., & Grimson, E. (1999). Adaptive background mixture models for real-time tracking. In
Choo, S., Seo, W., Jeong, D., & Cho, N. (2018a). Multi-scale recurrent encoder-decoder network for dense temporal classification. In
Laugraud, Pierard, Droogenbroeck (b185) 2017
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., & Goodfellow, I., et al. (2014). Intriguing properties of neural networks. In
Girshick, R. (2015). Fast R-CNN. In
Bouwmans, El Baf (b25) 2009; 1
(pp. 234–241).
Dai, Wang, Aston, Hua, Wipf (b81) 2018; 19
Huang, J., Huang, X., & Metaxas, D. (2009). Learning with dynamic group sparsity. In
Toyama, K., Krumm, J., Brumiit, B., & Meyers, B. (1999). Wallflower: Principles and practice of background maintenance. In
Guyon, C., Bouwmans, T., & Zahzah, E. (2012). Moving object detection by robust PCA solved via a linearized symmetric alternating direction method. In
Cohen, N., Tamari, R., & Shashua, A. (2018). Boosting dilated convolutional networks with mixed tensor decompositions. In
Schmidhuber (b284) 2015
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). C3D: generic features for video analysis. In
Wang, Luo, Jodoin (b346) 2016
Gil-Jimenez, P., Maldonado-Bascon, S., Gil-Pita, R., & Gomez-Moreno, H. (2003). Background pixel classification for motion detection in video image sequences. In
Zhou (b400) 2016
Maddalena, L., & Petrosino, A. (2012). The SOBS algorithm: What are the limits?. In
Wren, Azarbayejani (b359) 1997; 19
Malladi, S., & Sharapov, I. (2018). FastNorm: Improving numerical stability of deep network training with efficient normalization. In
Li, Huang (b191) 2004; 13
Lu, Shi, Jia (b209) 2011
Zheng, Wang, Wang (b398) 2018
Lin, H., Liu, T., & Chuang, J. (2002). A probabilistic SVM approach for background scene initialization
(pp. 1770–1778).
Zhang, Wang, Friedman (b385) 2018; 65
Maddalena, Petrosino (b213) 2008; 17
(pp. 5133–5141).
(pp. 652–661).
Silva, Bouwmans, Frelicot (b297) 2017
Braham, M., Pierard, S., & Droogenbroeck, M. V. (2017). Semantic background subtraction. In
Camplani, M., Maddalena, L., Alcover, G. M., Petrosino, A., & Salgado, L. (2017b). A benchmarking framework for background subtraction in RGBD videos. In
Z. Xu (b379) 2019; 71
Bakkay, M., Rashwan, H., Salmane, H., Khoudour, L., Puig, D., & Ruichek, Y. (2018). BSCGAN: Deep background subtraction with conditional generative adversarial networks. In
Haines, T., & Xiang, T. (2012). Background subtraction with Dirichlet processes. In
Patil, P., & Murala, S. (2019). FgGAN: A cascaded unpaired learning for background estimation and foreground segmentation. In
Zheng, Wang, Wang (b397) 2018
Farnoosh, Rezaei, Ostadabbas (b97) 2019
Zhou, T., & Tao, D. (2011). GoDec: Randomized low-rank and sparse matrix decomposition in noisy case. In
Zhou, Yang, Yu (b403) 2013; 35
Wang, Wan, Li (b349) 2018
Barron (b18) 1994; 14
Chiranjeevi, Sengupta (b59) 2016
Zhou, C., & Paffenroth, R. (2017). Anomaly detection with robust deep autoencoders. In
Haeffele, Vidal (b134) 2015
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., & Girshick, R., et al. (2014). Caffe: Convolutional architecture for fast feature embedding. In
Candès, Li, Ma, Wright (b40) 2011; 58
Sultana, Mahmood, Javed, Jung (b309) 2018
Elfwing, Uchibe, Doya (b91) 2018; 107
(pp. 3274–3281).
Chollet (b60) 2015
Krizhevsky, A., Sutskever, I., & Hinton, G. (2012). ImageNet: Classification with deep convolutional neural networks. In
Javed, S., Bouwmans, T., Sultana, M., & Jung, S. (2017). Moving object detection on RGB-D videos using graph regularized spatiotemporal RPCA. In
Nishani, E., & Cico, B. (2017). Computer vision approaches based on deep learning and neural networks: Deep neural networks for video analysis of human pose estimati
Wu (10.1016/j.neunet.2019.04.024_b361) 2010; 64
10.1016/j.neunet.2019.04.024_b159
10.1016/j.neunet.2019.04.024_b158
Tavakkoli (10.1016/j.neunet.2019.04.024_b316) 2005
Babaee (10.1016/j.neunet.2019.04.024_b10) 2017
10.1016/j.neunet.2019.04.024_b270
Oreifej (10.1016/j.neunet.2019.04.024_b250) 2012
10.1016/j.neunet.2019.04.024_b274
10.1016/j.neunet.2019.04.024_b395
10.1016/j.neunet.2019.04.024_b152
10.1016/j.neunet.2019.04.024_b273
10.1016/j.neunet.2019.04.024_b272
10.1016/j.neunet.2019.04.024_b157
10.1016/j.neunet.2019.04.024_b154
10.1016/j.neunet.2019.04.024_b396
10.1016/j.neunet.2019.04.024_b149
10.1016/j.neunet.2019.04.024_b268
10.1016/j.neunet.2019.04.024_b389
Maddalena (10.1016/j.neunet.2019.04.024_b210) 2007; 4729
Wang (10.1016/j.neunet.2019.04.024_b346) 2016
Zhong (10.1016/j.neunet.2019.04.024_b399) 2019; 110
10.1016/j.neunet.2019.04.024_b142
10.1016/j.neunet.2019.04.024_b141
10.1016/j.neunet.2019.04.024_b140
10.1016/j.neunet.2019.04.024_b388
10.1016/j.neunet.2019.04.024_b266
10.1016/j.neunet.2019.04.024_b387
10.1016/j.neunet.2019.04.024_b144
10.1016/j.neunet.2019.04.024_b265
10.1016/j.neunet.2019.04.024_b386
10.1016/j.neunet.2019.04.024_b143
10.1016/j.neunet.2019.04.024_b139
10.1016/j.neunet.2019.04.024_b138
10.1016/j.neunet.2019.04.024_b137
10.1016/j.neunet.2019.04.024_b258
10.1016/j.neunet.2019.04.024_b136
10.1016/j.neunet.2019.04.024_b257
10.1016/j.neunet.2019.04.024_b378
Cai (10.1016/j.neunet.2019.04.024_b36) 2016; 25
Bouwmans (10.1016/j.neunet.2019.04.024_b25) 2009; 1
Lee (10.1016/j.neunet.2019.04.024_b189) 2002
Wang (10.1016/j.neunet.2019.04.024_b344) 2018; 97
10.1016/j.neunet.2019.04.024_b131
10.1016/j.neunet.2019.04.024_b130
10.1016/j.neunet.2019.04.024_b251
10.1016/j.neunet.2019.04.024_b372
10.1016/j.neunet.2019.04.024_b135
10.1016/j.neunet.2019.04.024_b377
10.1016/j.neunet.2019.04.024_b254
10.1016/j.neunet.2019.04.024_b375
Zeng (10.1016/j.neunet.2019.04.024_b382) 2018
10.1016/j.neunet.2019.04.024_b132
10.1016/j.neunet.2019.04.024_b253
10.1016/j.neunet.2019.04.024_b374
10.1016/j.neunet.2019.04.024_b128
10.1016/j.neunet.2019.04.024_b249
10.1016/j.neunet.2019.04.024_b127
10.1016/j.neunet.2019.04.024_b126
10.1016/j.neunet.2019.04.024_b247
10.1016/j.neunet.2019.04.024_b368
10.1016/j.neunet.2019.04.024_b367
Srivastava (10.1016/j.neunet.2019.04.024_b303) 2014; 15
10.1016/j.neunet.2019.04.024_b129
Petersen (10.1016/j.neunet.2019.04.024_b255) 2018; 108
Z. Xu (10.1016/j.neunet.2019.04.024_b379) 2019; 71
10.1016/j.neunet.2019.04.024_b120
10.1016/j.neunet.2019.04.024_b241
10.1016/j.neunet.2019.04.024_b124
10.1016/j.neunet.2019.04.024_b366
10.1016/j.neunet.2019.04.024_b244
10.1016/j.neunet.2019.04.024_b365
10.1016/j.neunet.2019.04.024_b243
Farcas (10.1016/j.neunet.2019.04.024_b96) 2012; 23
10.1016/j.neunet.2019.04.024_b121
10.1016/j.neunet.2019.04.024_b363
Wu (10.1016/j.neunet.2019.04.024_b362) 2019
Silva (10.1016/j.neunet.2019.04.024_b297) 2017
10.1016/j.neunet.2019.04.024_b1
10.1016/j.neunet.2019.04.024_b2
Cuevas (10.1016/j.neunet.2019.04.024_b75) 2016
Moya-Alcover (10.1016/j.neunet.2019.04.024_b240) 2016
10.1016/j.neunet.2019.04.024_b6
10.1016/j.neunet.2019.04.024_b9
10.1016/j.neunet.2019.04.024_b192
10.1016/j.neunet.2019.04.024_b197
10.1016/j.neunet.2019.04.024_b195
Hinton (10.1016/j.neunet.2019.04.024_b146) 2007
Zhang (10.1016/j.neunet.2019.04.024_b385) 2018; 65
10.1016/j.neunet.2019.04.024_b198
Moosavi-Dezfooli (10.1016/j.neunet.2019.04.024_b237) 2017
Dumoulin (10.1016/j.neunet.2019.04.024_b90) 2018
Wang (10.1016/j.neunet.2019.04.024_b335) 2008
Bouwmans (10.1016/j.neunet.2019.04.024_b28) 2018; 28
10.1016/j.neunet.2019.04.024_b182
Wang (10.1016/j.neunet.2019.04.024_b338) 2019
10.1016/j.neunet.2019.04.024_b180
Cohen (10.1016/j.neunet.2019.04.024_b66) 2005; 2
10.1016/j.neunet.2019.04.024_b184
10.1016/j.neunet.2019.04.024_b183
Yang (10.1016/j.neunet.2019.04.024_b370) 2019
10.1016/j.neunet.2019.04.024_b188
Elguebaly (10.1016/j.neunet.2019.04.024_b93) 2013
Goel (10.1016/j.neunet.2019.04.024_b113) 2018
Chen (10.1016/j.neunet.2019.04.024_b51) 2007; 10
Ramirez-Alonso (10.1016/j.neunet.2019.04.024_b263) 2015
Vosters (10.1016/j.neunet.2019.04.024_b333) 2012; 30
Cun (10.1016/j.neunet.2019.04.024_b78) 1998; 86
Wang (10.1016/j.neunet.2019.04.024_b343) 2018
Javed (10.1016/j.neunet.2019.04.024_b166) 2017; 26
Bianco (10.1016/j.neunet.2019.04.024_b21) 2015
Gast (10.1016/j.neunet.2019.04.024_b107) 2018
Agarwala (10.1016/j.neunet.2019.04.024_b3) 2004; 23
10.1016/j.neunet.2019.04.024_b171
10.1016/j.neunet.2019.04.024_b292
10.1016/j.neunet.2019.04.024_b170
10.1016/j.neunet.2019.04.024_b291
10.1016/j.neunet.2019.04.024_b175
10.1016/j.neunet.2019.04.024_b296
10.1016/j.neunet.2019.04.024_b295
10.1016/j.neunet.2019.04.024_b172
10.1016/j.neunet.2019.04.024_b178
10.1016/j.neunet.2019.04.024_b299
10.1016/j.neunet.2019.04.024_b177
10.1016/j.neunet.2019.04.024_b176
Ramirez-Alonso (10.1016/j.neunet.2019.04.024_b264) 2017
Sultana (10.1016/j.neunet.2019.04.024_b309) 2018
Lim (10.1016/j.neunet.2019.04.024_b201) 2018
Weinstein (10.1016/j.neunet.2019.04.024_b356) 2018
10.1016/j.neunet.2019.04.024_b169
Yang (10.1016/j.neunet.2019.04.024_b371) 2018; 19
Sasikumar (10.1016/j.neunet.2019.04.024_b283) 2018
Shafiee (10.1016/j.neunet.2019.04.024_b290) 2016
10.1016/j.neunet.2019.04.024_b160
10.1016/j.neunet.2019.04.024_b281
Maddalena (10.1016/j.neunet.2019.04.024_b212) 2008
10.1016/j.neunet.2019.04.024_b280
Patil (10.1016/j.neunet.2019.04.024_b252) 2018
Chang (10.1016/j.neunet.2019.04.024_b50) 2019
10.1016/j.neunet.2019.04.024_b163
10.1016/j.neunet.2019.04.024_b162
Garcia-Garcia (10.1016/j.neunet.2019.04.024_b105) 2018; 70
10.1016/j.neunet.2019.04.024_b161
Culloch (10.1016/j.neunet.2019.04.024_b77) 1943; 5
10.1016/j.neunet.2019.04.024_b168
10.1016/j.neunet.2019.04.024_b288
10.1016/j.neunet.2019.04.024_b165
10.1016/j.neunet.2019.04.024_b286
10.1016/j.neunet.2019.04.024_b315
10.1016/j.neunet.2019.04.024_b313
10.1016/j.neunet.2019.04.024_b312
10.1016/j.neunet.2019.04.024_b92
10.1016/j.neunet.2019.04.024_b319
10.1016/j.neunet.2019.04.024_b318
10.1016/j.neunet.2019.04.024_b317
Lim (10.1016/j.neunet.2019.04.024_b202) 2018; 112
Vaswani (10.1016/j.neunet.2019.04.024_b329) 2018; 35
Wang (10.1016/j.neunet.2019.04.024_b351) 2018
Vidal (10.1016/j.neunet.2019.04.024_b332) 2018
10.1016/j.neunet.2019.04.024_b89
10.1016/j.neunet.2019.04.024_b311
Wang (10.1016/j.neunet.2019.04.024_b349) 2018
10.1016/j.neunet.2019.04.024_b304
10.1016/j.neunet.2019.04.024_b301
10.1016/j.neunet.2019.04.024_b308
10.1016/j.neunet.2019.04.024_b80
Wang (10.1016/j.neunet.2019.04.024_b339) 2018; 19
10.1016/j.neunet.2019.04.024_b83
10.1016/j.neunet.2019.04.024_b306
10.1016/j.neunet.2019.04.024_b82
10.1016/j.neunet.2019.04.024_b305
Zhou (10.1016/j.neunet.2019.04.024_b400) 2016
Bahri (10.1016/j.neunet.2019.04.024_b14) 2018
10.1016/j.neunet.2019.04.024_b74
10.1016/j.neunet.2019.04.024_b76
Bouwmans (10.1016/j.neunet.2019.04.024_b29) 2017; 23
Rezaei (10.1016/j.neunet.2019.04.024_b269) 2018
10.1016/j.neunet.2019.04.024_b300
Akilan (10.1016/j.neunet.2019.04.024_b4) 2018
Chan (10.1016/j.neunet.2019.04.024_b46) 2019; 28
Chen (10.1016/j.neunet.2019.04.024_b54) 2017
Kingma (10.1016/j.neunet.2019.04.024_b179) 2013
Zhao (10.1016/j.neunet.2019.04.024_b394) 2016
Ren (10.1016/j.neunet.2019.04.024_b267) 2017; 39
Bouwmans (10.1016/j.neunet.2019.04.024_b24) 2014
Maddalena (10.1016/j.neunet.2019.04.024_b225) 2018
10.1016/j.neunet.2019.04.024_b402
10.1016/j.neunet.2019.04.024_b401
Zhang (10.1016/j.neunet.2019.04.024_b384) 2015
10.1016/j.neunet.2019.04.024_b405
Fan (10.1016/j.neunet.2019.04.024_b94) 2012
Suykens (10.1016/j.neunet.2019.04.024_b310) 2017; 29
Zhao (10.1016/j.neunet.2019.04.024_b393) 2018
Fischer (10.1016/j.neunet.2019.04.024_b102) 2012; 7441
Vidal (10.1016/j.neunet.2019.04.024_b331) 2017
Maddalena (10.1016/j.neunet.2019.04.024_b226) 2018
Nouiehed (10.1016/j.neunet.2019.04.024_b248) 2018
Farnoosh (10.1016/j.neunet.2019.04.024_b97) 2019
Brunettia (10.1016/j.neunet.2019.04.024_b34) 2018; 300
Barnich (10.1016/j.neunet.2019.04.024_b17) 2011; 20
10.1016/j.neunet.2019.04.024_b95
Munteanu (10.1016/j.neunet.2019.04.024_b242) 2015; 60
Tan (10.1016/j.neunet.2019.04.024_b314) 2019; 27
10.1016/j.neunet.2019.04.024_b238
10.1016/j.neunet.2019.04.024_b116
10.1016/j.neunet.2019.04.024_b115
10.1016/j.neunet.2019.04.024_b236
Cao (10.1016/j.neunet.2019.04.024_b42) 2016; 46
10.1016/j.neunet.2019.04.024_b114
10.1016/j.neunet.2019.04.024_b235
10.1016/j.neunet.2019.04.024_b119
10.1016/j.neunet.2019.04.024_b118
10.1016/j.neunet.2019.04.024_b239
Feng (10.1016/j.neunet.2019.04.024_b99) 2018; 26
10.1016/j.neunet.2019.04.024_b49
10.1016/j.neunet.2019.04.024_b48
10.1016/j.neunet.2019.04.024_b41
Zhou (10.1016/j.neunet.2019.04.024_b403) 2013; 35
10.1016/j.neunet.2019.04.024_b43
Maddalena (10.1016/j.neunet.2019.04.024_b217) 2010
Radford (10.1016/j.neunet.2019.04.024_b260) 2015
Wang (10.1016/j.neunet.2019.04.024_b354) 2019; 27
10.1016/j.neunet.2019.04.024_b44
10.1016/j.neunet.2019.04.024_b112
10.1016/j.neunet.2019.04.024_b233
10.1016/j.neunet.2019.04.024_b47
10.1016/j.neunet.2019.04.024_b111
10.1016/j.neunet.2019.04.024_b353
10.1016/j.neunet.2019.04.024_b110
10.1016/j.neunet.2019.04.024_b231
10.1016/j.neunet.2019.04.024_b106
10.1016/j.neunet.2019.04.024_b227
10.1016/j.neunet.2019.04.024_b348
10.1016/j.neunet.2019.04.024_b103
10.1016/j.neunet.2019.04.024_b224
10.1016/j.neunet.2019.04.024_b345
10.1016/j.neunet.2019.04.024_b109
10.1016/j.neunet.2019.04.024_b108
10.1016/j.neunet.2019.04.024_b229
10.1016/j.neunet.2019.04.024_b228
Hinton (10.1016/j.neunet.2019.04.024_b147) 2006; 18
Sajid (10.1016/j.neunet.2019.04.024_b277) 2017; 26
Chen (10.1016/j.neunet.2019.04.024_b55) 2018
Akilan (10.1016/j.neunet.2019.04.024_b8) 2019
Camplani (10.1016/j.neunet.2019.04.024_b37) 2014
10.1016/j.neunet.2019.04.024_b38
10.1016/j.neunet.2019.04.024_b39
Lim (10.1016/j.neunet.2019.04.024_b199) 2018
10.1016/j.neunet.2019.04.024_b340
Zhao (10.1016/j.neunet.2019.04.024_b392) 2015
Prativadibhayankaram (10.1016/j.neunet.2019.04.024_b256) 2018
Radford (10.1016/j.neunet.2019.04.024_b259) 2015
10.1016/j.neunet.2019.04.024_b32
Akilan (10.1016/j.neunet.2019.04.024_b5) 2018
10.1016/j.neunet.2019.04.024_b31
10.1016/j.neunet.2019.04.024_b223
Maddalena (10.1016/j.neunet.2019.04.024_b221) 2014
10.1016/j.neunet.2019.04.024
References_xml – year: 2016
  ident: b75
  article-title: Labeled dataset for integral evaluation of moving object detection algorithms: LASIESTA
  publication-title: Computer Vision and Image Understanding
– year: 2011
  ident: b209
  article-title: Online robust dictionary learning
  publication-title: EURASIP Journal on Image and Video Processing, IVP 2011
– start-page: 16010
  year: 2018
  end-page: 16021
  ident: b381
  article-title: Background subtraction using multiscale fully convolutional network
  publication-title: IEEE Access
– reference: Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., & Efros, A. (2016). Context encoders: Feature learning by inpainting. In
– reference: Zhou, T., & Tao, D. (2011). GoDec: Randomized low-rank and sparse matrix decomposition in noisy case. In
– year: 2015
  ident: b384
  article-title: Deep learning driven blockwise moving object detection with binary scene modeling
  publication-title: Neurocomputing
– reference: Guo, H., Qiu, C., & Vaswani, N. (2013). Practical ReProCS for Separating Sparse and Low-dimensional Signal Sequences from their Sum. Preprint.
– year: 2016
  ident: b400
  article-title: Robust auto-encoders
– reference: Ramirez-Quintana, J., & Chacon-Murguia, M. (2013). Self-organizing retinotopic maps applied to background modeling for dynamic object segmentation in video sequences. In
– reference: Baf, F. E., Bouwmans, T., & Vachon, B. (2008a). Foreground detection using the Choquet integral. In
– year: 2017
  ident: b297
  article-title: Superpixel-based online wagging one-class ensemble for feature selection in background/foreground separation
  publication-title: Pattern Recognition Letters
– volume: 9
  start-page: 1735
  year: 1997
  end-page: 1780
  ident: b148
  article-title: Long short-term memory
  publication-title: Neural Computation
– volume: 77
  start-page: 354
  year: 2018
  end-page: 377
  ident: b122
  article-title: Recent advances in convolutional neural networks
  publication-title: Pattern Recognition
– volume: 26
  start-page: 3249
  year: 2017
  end-page: 3260
  ident: b277
  article-title: Universal multimode background subtraction
  publication-title: IEEE Transactions on Image Processing
– reference: Silva, C., Bouwmans, T., & Frelicot, C. (2016). Online weighted one-class ensemble for feature selection in background/foreground separation. In
– reference: (pp. 887–893).
– year: 2018
  ident: b325
  article-title: About pyramid structure in convolutional neural networks
– year: 2019
  ident: b307
  article-title: Illumination invariant foreground object segmentation using foregan
– reference: Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). C3D: generic features for video analysis. In
– reference: Cohen, N., & Shashua, A. (2014). SimNets: A generalization of convolutional networks. In
– year: 2019
  ident: b57
  article-title: A survey of model compression and accelerationfor deep neural networks
– year: 2018
  ident: b187
  article-title: Survey on deep learning techniques for person re-identification task
  publication-title: Neurocomputing
– year: 2015
  ident: b360
  article-title: Adjustable bounded rectifiers: Towards deep binary representations
– reference: Rosell-Ortega, J., Andreu, G., Atienza, V., & Lopez-Garcia, F. (2010). Background modeling with motion criterion and multi-modal support. In
– reference: Mittal, A. (2004). Motion-based background subtraction using adaptive kernel density estimation. In
– volume: 18
  start-page: 1527
  year: 2006
  end-page: 1554
  ident: b147
  article-title: A fast learning algorithm for deep belief nets
  publication-title: Neural Computation
– volume: 46
  start-page: 1014
  year: 2016
  end-page: 1027
  ident: b42
  article-title: Total variation regularized RPCA for irregularly moving object detection under dynamic background
  publication-title: IEEE Transactions on Cybernetics
– reference: . (pp. 1637–1641).
– year: 2018
  ident: b246
  article-title: Change detection by training a triplet network for motion feature extraction
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– reference: Zhao, C., Cham, T., Ren, X., Cai, J., & Zhu, H. (2018). Background subtraction based on deep pixel distribution learning. In
– volume: 300
  start-page: 17
  year: 2018
  end-page: 33
  ident: b34
  article-title: Computer vision and deep learning techniques for pedestrian detection and tracking: A survey
  publication-title: Neurocomputing
– reference: Pulgarin-Giraldo, J., Alvarez-Meza, A., Insuasti-Ceballos, D., Bouwmans, T., & Castellanos-Dominguez, G. (2016). GMM background modeling using divergence-based weight updating. In
– reference: (pp. 1097–1105).
– reference: Sedky, M., Moniri, M., & Chibelushi, C. (2014). Spectral-360: A physics-based technique for change detection. In
– volume: 19
  start-page: 254
  year: 2018
  end-page: 262
  ident: b371
  article-title: Deep background modeling using fully convolutional network
  publication-title: IEEE Transactions on Intelligent Transportation Systems
– reference: Malladi, S., & Sharapov, I. (2018). FastNorm: Improving numerical stability of deep network training with efficient normalization. In
– reference: Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., & Goodfellow, I., et al. (2014). Intriguing properties of neural networks. In
– reference: Graszka, P. (2014). Median mixture model for background-foreground segmentation in video sequences. In
– volume: 48
  start-page: 1374
  year: 2015
  end-page: 1390
  ident: b194
  article-title: Co-occurrence probability based pixel pairs background model for robust object detection in dynamic scenes
  publication-title: Pattern Recognition
– year: 2019
  ident: b282
  article-title: Automatic fish detection in underwater videos by a deep neural network-based hybrid motion learning system
  publication-title: ICES Journal of Marine Science
– reference: Caelles, S., et al. One-shot video object segmentation. In
– year: 2019
  ident: b97
  article-title: DeepPBM: Deep probabilistic background model estimation from video sequences
– reference: Shakeri, M., & Zhang, H. (2017). Moving object detection in time-lapse or motion trigger image sequences using low-rank and invariant sparse decomposition. In
– reference: Chang, F., Tran, A., Hassner, T., Masi, I., Nevatia, R., & Medioni, G. (2017). FacePoseNet: Making a case for landmark-free face alignment. In
– reference: Marghes, C., Bouwmans, T., & Vasiu, R. (2012). Background modeling and foreground detection via a reconstructive and discriminative subspace learning approach. In
– volume: 2
  start-page: 359
  year: 1989
  end-page: 366
  ident: b151
  article-title: Multilayer feedforward networks are universal approximators
  publication-title: Neural Networks
– reference: Krizhevsky, A., Sutskever, I., & Hinton, G. (2012). ImageNet: Classification with deep convolutional neural networks. In
– reference: Cohen, N., Sharir, O., & Shashua, A. (2016a). Deep SimNets. In
– volume: 30
  start-page: 968
  year: 2019
  end-page: 984
  ident: b73
  article-title: Denoising adversarial autoencoders
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– reference: Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In
– reference: Tavakkoli, A., Nicolescu, M., Nicolescu, M., & Bebis, G. (2008). Incremental SVDD training: Improving efficiency of background modeling in videos. In
– reference: Guyon, C., Bouwmans, T., & Zahzah, E. (2012). Foreground detection by robust PCA solved via a linearized alternating direction method. In
– reference: (pp. 63–68).
– reference: Javed, S., Oh, S., Sobral, A., Bouwmans, T., & Jung, S. (2015). Background subtraction via superpixel-based online matrix decomposition with structured foreground constraints. In
– volume: 4729
  start-page: 181
  year: 2007
  end-page: 190
  ident: b210
  article-title: A self-organizing approach to detection of moving patterns for real-time applications
  publication-title: Advances in Brain, Vision, and Artificial Intelligence
– reference: . (pp. 1440–1448).
– year: 2018
  ident: b356
  article-title: Scene-specific convolutional neural networks for video-based biodiversity detection
  publication-title: Methods in Ecology and Evolution
– reference: (pp. 3265–3268).
– year: 2016
  ident: b85
  article-title: Tutorial on variational autoencoders
– reference: Kawaguchi, K. (2016). Deep learning without poor local minima. In
– reference: (pp. 971–976).
– year: 2017
  ident: b104
  article-title: A review on deep learning techniques applied to semantic segmentation
– start-page: 1
  year: 2017
  end-page: 19
  ident: b279
  article-title: End-to-end video background subtraction with 3D convolutional neural networks
  publication-title: Multimedia Tools and Applications
– reference: Mukherjee, D., & Wu, J. (2012). Real-time video segmentation using Student’s t mixture model. In
– reference: (pp. 163–170).
– reference: Toyama, K., Krumm, J., Brumiit, B., & Meyers, B. (1999). Wallflower: Principles and practice of background maintenance. In
– reference: Xu, P., Ye, M., Liu, Q., Li, X., Pei, L., & Ding, J. (2014). Motion detection via a couple of auto-encoder networks. In
– volume: 24
  start-page: 723
  year: 2013
  end-page: 735
  ident: b219
  article-title: Stopped object detection by learning foreground model in videos
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– reference: Tombari, F., Lanza, A., Stefano, L. D., & Mattoccia, S. (2009). Non-linear parametric bayesian regression for robust background subtraction. In
– year: 2018
  ident: b287
  article-title: How robust are deep neural networks?
– reference: Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., & Anguelov, D., et al. (2015). Going deeper with convolutions. In
– year: 2015
  ident: b263
  article-title: Self-adaptive SOM-CNN neural system for dynamic object detection in normal and complex scenarios
  publication-title: Pattern Recognition
– year: 2014
  ident: b24
  article-title: Traditional approaches in background modeling for video surveillance
  publication-title: Handbook background modeling and foreground detection for video surveillance
– reference: (pp. 301–306).
– reference: (pp. 2818–2826).
– reference: (pp. 889–892).
– reference: Mopuri, K., Ojha, U., Garg, U., & Babu, R. (2018). NAG: Network for adversary generation. In
– reference: Jang, W., & Kim, C. (2017). Online video object segmentation via convolutional trident network. In
– reference: Salehinejad, H., & Valaee, S. (2019). Ising-dropout: a regularization method for training and compression of deep neural networks. In
– reference: Akilan, T., Wu, J., Jiang, W., Safaei, A., & Huo, J. (2018). New trend in video foreground detection using deep learning. In
– reference: . (pp. 209–214).
– reference: Gong, M., & Cheng, L. (2011). Incorporating estimated motion in real-time background subtraction. In
– volume: 26
  start-page: 903
  year: 2016
  end-page: 916
  ident: b369
  article-title: Pixel-to-model distance for robust background reconstruction
  publication-title: IEEE Transactions on Circuits Systems and Video Technology
– reference: Javed, S., Mahmood, A., Bouwmans, T., & Jung, S. (2017c). Superpixels based manifold structured sparse RPCA for moving object detectio. In
– reference: Vaswani, N., Bouwmans, T., Javed, S., & Narayanamurth, P. (2018a). Robust PCA and robust subspace tracking: A comparative evaluation. In
– volume: 57
  start-page: 3
  year: 2019
  end-page: 13
  ident: b352
  article-title: GETNET: A general end-to-end 2-d CNN framework for hyperspectral image change detection
  publication-title: IEEE Transactions on Geoscience and Remote Sensing
– reference: (pp. 395–403).
– volume: 11
  year: 2014
  ident: b23
  article-title: Traditional and recent approaches in background modeling for foreground detection: An overview
  publication-title: Computer Science Review
– volume: 26
  start-page: 117
  year: 2018
  end-page: 130
  ident: b99
  article-title: A fuzzy restricted Boltzmann machine: Novel learning algorithms based on the crisp possibilistic mean value of fuzzy numbers
  publication-title: IEEE Transactions on Fuzzy Systems
– reference: (pp. 223–238.
– reference: Cinar, G., & Principe, J. (2011). Adaptive background estimation using an information theoretic cost for hidden state estimation. In
– reference: Maddalena, L., & Petrosino, A. (2017). Exploiting color and depth for background subtraction. In
– start-page: 1
  year: 2008
  end-page: 19
  ident: b335
  article-title: Improving target detection by coupling it with tracking
  publication-title: Machine Vision and Application
– reference: Guyon, C., Bouwmans, T., & Zahzah, E. (2012). Moving object detection by robust PCA solved via a linearized symmetric alternating direction method. In
– reference: Maddalena, L., & Petrosino, A. (2016). Extracting a background image by a multi-modal scene background model. In
– year: 2018
  ident: b256
  article-title: Compressive online video background–Foreground separation using multiple prior information and optical flow
  publication-title: MDPI Journal of Imaging
– volume: 2
  start-page: 1034
  year: 2005
  end-page: 1041
  ident: b66
  article-title: Background estimation as a labeling problem
  publication-title: International Conference on Computer Vision, ICCV 2005
– year: 2015
  ident: b298
  article-title: Very deep convolutional networks for large-scale image recognition
  publication-title: International Conference on Learning Representation, ICLR 2015
– reference: Sultana, M., Mahmood, A., Javed, S., & Jung, S. (2018a). Unsupervised RGBD video object segmentation using GANs. ACCV-Workshops 2018.
– reference: Qu, Z., Yu, S., & Fu, M. (2016). Motion background modeling based on context-encoder. In
– reference: Zhao, Z., Bouwmans, T., Zhang, X., & Fang, Y. (2012). A fuzzy background modeling approach for motion detection in dynamic backgrounds. In
– volume: 7441
  start-page: 14
  year: 2012
  end-page: 36
  ident: b102
  article-title: An introduction to restricted Boltzmann machines
  publication-title: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
– year: 2016
  ident: b394
  article-title: Tensor ring decomposition
– reference: Girshick, R. (2015). Fast R-CNN. In
– reference: St-Charles, P., Bilodeau, G., & Bergevin, R. (2014). Flexible background subtraction with self-balanced local sensitivity. In
– reference: Wang, Y., Jodoin, P., Porikli, F., Konrad, J., Benezeth, Y., & Ishwar, P. (2014). CDnet 2014: An expanded change detection benchmark dataset. In
– year: 2012
  ident: b94
  article-title: Online variational learning of finite Dirichlet mixture models
  publication-title: Evolving Systems
– reference: Dai, J., Li, Y., He, K., & Sun, J. (2016). R-FCN: Object detection via region-based fully convolutional networks. In
– reference: (pp. 9329–9338).
– reference: Marghes, C., & Bouwmans, T. (2010). Background modeling via incremental maximum margin criterion. In
– volume: 35
  start-page: 597
  year: 2013
  end-page: 610
  ident: b403
  article-title: Moving object detection by detecting contiguous outliers in the low-rank representation
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– volume: 71
  start-page: 1
  year: 2019
  end-page: 12
  ident: b379
  article-title: A robust background initialization algorithm with superpixel motion detection
  publication-title: Signal Processing: Image Communication
– start-page: 315
  year: 2002
  end-page: 320
  ident: b189
  article-title: Background estimation for video surveillance
  publication-title: Image and Vision Computing New Zealand, IVCNZ 2002
– reference: Patil, P., Murala, S., Dhall, A., & Chaudhary, S. (2018). MsEDNet: Multi-scale deep saliency learning for moving object detection. In
– volume: 70
  start-page: 41
  year: 2018
  end-page: 65
  ident: b105
  article-title: A survey on deep learning techniques for image and video semantic segmentation
  publication-title: Applied Soft Computing
– reference: Szegedy, C., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In
– year: 2016
  ident: b164
  article-title: Spatiotemporal low-rank modeling for complex scene background initialization
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– reference: Camplani, M., Maddalena, L., Alcover, G. M., Petrosino, A., & Salgado, L. (2017b). A benchmarking framework for background subtraction in RGBD videos. In
– year: 2018
  ident: b245
  article-title: Stable tensor neural networks for rapid deep learning
– year: 2019
  ident: b88
  article-title: Tensor robust principal component analysis: Better recovery with atomic norm regularization
– volume: 65
  start-page: 677
  year: 2018
  end-page: 686
  ident: b385
  article-title: Memristor-based circuit design for multilayer neural networks
  publication-title: IEEE Transactions on Circuits and Systems. I. Regular Papers
– reference: Lin, C., Yan, B., & Tan, W. (2018). Foreground detection in surveillance video with fully convolutional semantic network. In
– reference: (pp. 187–190).
– reference: Maddalena, L., & Petrosino, A. (2008a). A self-organizing neural system for background and foreground modeling. In
– reference: Sobral, A., Javed, S., Jung, S., Bouwmans, T., & Zahzah, E. (2015). Online stochastic tensor decomposition for background subtraction in multispectral video sequences. In
– reference: St-Charles, P., Bilodeau, G., & Bergevin, R. (2015). A self-adjusting approach to change detection based on background word consensus. In
– reference: Shahbaz, A., Hernandez, D., & Jo, K. (2017). Optimal color space based probabilistic foreground detector for video surveillance systems. In
– volume: 23
  start-page: 294
  year: 2004
  end-page: 302
  ident: b3
  article-title: Interactive digital photomontage
  publication-title: ACM Transactions on Graphics
– reference: (pp. 440–445).
– reference: Lim, K., Jang, W., & Kim, C. (2017). Background subtraction using encoder-decoder structured convolutional neural network. In
– reference: Goodfellow, I., et al. Generative adversarial networks. In
– reference: Abadi, M., et al. (2016). TensorFlow: Large-scale machine learning on heterogeneous distributed systems. In
– reference: (pp. 585–593).
– start-page: 57
  year: 2008
  end-page: 64
  ident: b212
  article-title: Neural model-based segmentation of image motion
  publication-title: KES 2008
– year: 2015
  ident: b101
  article-title: Flownet: Learning optical flow with convolutional networks
– reference: . (pp. 772–781).
– reference: (pp. 40–49).
– volume: 2
  start-page: 303
  year: 1989
  end-page: 314
  ident: b79
  article-title: Approximation by superpositions of a sigmoidal function
  publication-title: Mathematics of Control Signals and Systems
– reference: (pp. 1–7).
– reference: (pp. 2296–2300).
– volume: 29
  start-page: 2123
  year: 2017
  end-page: 2163
  ident: b310
  article-title: Deep restricted kernel machines using conjugate feature duality
  publication-title: Neural Computation
– reference: Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In
– reference: Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., & Girshick, R., et al. (2014). Caffe: Convolutional architecture for fast feature embedding. In
– reference: Javed, S., Sobral, A., Bouwmans, T., & Jung, S. (2015). OR-PCA with dynamic feature selection for robust background subtraction. In
– reference: (pp. 1–6).
– reference: (pp. 524–533).
– year: 2005
  ident: b316
  article-title: Foreground-background segmentation in video sequences using neural networks
  publication-title: Intelligent Systems: Neural Networks and Applications
– volume: 107
  start-page: 3
  year: 2018
  end-page: 11
  ident: b91
  article-title: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning
  publication-title: Neural Networks
– year: 2017
  ident: b156
  article-title: Image to- image translation with conditional adversarial networks
– reference: Wang, Z., Zhang, L., & Bao, H. PNN based motion detection with adaptive learning rate. In
– volume: 28
  year: 2018
  ident: b230
  article-title: New trends on moving object detection in video images Captured by a moving Camera: A survey
  publication-title: Computer Science Review
– year: 2017
  ident: b289
  article-title: Real-time embedded motion detection via neural response mixture modeling
  publication-title: Journal of Signal Processing Systems
– reference: (pp. 718–725).
– year: 2015
  ident: b60
  article-title: Keras
– year: 2015
  ident: b134
  article-title: Global optimality in tensor factorization, deep learning, and beyond.
– reference: Gil-Jimenez, P., Maldonado-Bascon, S., Gil-Pita, R., & Gomez-Moreno, H. (2003). Background pixel classification for motion detection in video image sequences. In
– reference: He, K., Zhang, X., Ren, S., & Sun, J. Delving deep into rectifiers: Surpassing human-level performance on Imagenet classification. In
– reference: Javed, S., Bouwmans, T., & Jung, S. (2015a). Combining ARF and OR-PCA background subtraction of noisy videos. In
– volume: 30
  start-page: 1004
  year: 2012
  end-page: 1015
  ident: b333
  article-title: Real-time robust background subtraction under rapidly changing illumination conditions
  publication-title: Image Vision and Computing
– reference: Bautista, C., Dy, C., Manalac, M., Orbe, R., & Cordel, M. (2016). Convolutional neural network for vehicle detection in low resolution traffic videos. In
– year: 2016
  ident: b59
  article-title: Interval-valued model level Fuzzy aggregation-based background subtraction
  publication-title: IEEE Transactions on Cybernetics
– reference: Liao, J., Guo, G., Yan, Y., & Wang, H. (2018). Multiscale cascaded scene-specific convolutional neural networks for background subtraction. In
– year: 2015
  ident: b21
  article-title: How far Can you get by combining change detection algorithms?
– reference: Vacavant, A., Chateau, T., Wilhelm, A., & Lequievre, L. (2012). A benchmark dataset for foreground/background extraction. In
– year: 2019
  ident: b7
  article-title: An improved video foreground extraction strategy using multi-view receptive field and EnDec CNN
  publication-title: IEEE Transactions on Industrial Informatics
– volume: 110
  start-page: 104
  year: 2019
  end-page: 115
  ident: b399
  article-title: ADA-Tucker: Compressing deep neural networks via adaptive dimension adjustment tucker decomposition, neural networks
  publication-title: Neural Networks
– year: 2019
  ident: b208
  article-title: Tensor robust principal component analysis with a new tensor nuclear norm
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– year: 2018
  ident: b190
  article-title: Background subtraction using the factored 3-way restricted Boltzmann machines
– reference: (pp. 419–422).
– year: 2018
  ident: b262
  article-title: Attention-based few-shot person re-identification using meta learning
– year: 2018
  ident: b226
  article-title: Self-organizing background subtraction using color and depth data
  publication-title: Multimedia Tools and Applications
– year: 2015
  ident: b260
  article-title: Unsupervised representation learning with deep convolutional generative adversarial networks
  publication-title: Computer Science
– reference: (pp. 234–241).
– year: 2015
  ident: b167
  article-title: Robust background subtraction to global illumination changes via multiple features based OR-PCA with MRF
  publication-title: Journal of Electronic Imaging
– year: 2018
  ident: b283
  article-title: Investigating the application of deep convolutional neural networks in semi-supervised video object segmentation
– volume: 15
  year: 2018
  ident: b232
  article-title: On the implicit bias of dropout
  publication-title: International Conference on Machine Learning, ICML 2018
– volume: 27
  start-page: 773
  year: 2006
  end-page: 780
  ident: b406
  article-title: Efficient adaptive density estimation per image pixel for the task of background subtraction
  publication-title: Pattern Recognition Letters
– year: 2018
  ident: b383
  article-title: Multiscale fully convolutional network for foreground object detection in infrared videos
  publication-title: IEEE Geoscience and Remote Sensing Letters
– reference: Gregorio, M., & Giordano, M. (2015). Background modeling by weightless neural networks. In
– year: 2012
  ident: b250
  article-title: Simultaneous video stabilization and moving object detection in turbulence
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI 2012
– year: 2017
  ident: b331
  article-title: Mathematics of deep learning
– year: 2015
  ident: b173
  article-title: Motion detection: Unsolved issues and [potential] solutions
– reference: (pp. 1–5).
– reference: Wang, J., Bebis, G., & Miller, R. (2006). Robust video-based surveillance by integrating target detection with tracking. In
– reference: Yi, H., Shiyu, S., Xiusheng, D., & Zhigang, C. (2016). A study on deep neural networks framework. In
– year: 2018
  ident: b269
  article-title: Moving object detection through robust matrix completion augmented with objectness
  publication-title: IEEE Journal of Selected Topics in Signal Processing
– reference: Davies, R., Mihaylova, L., Pavlidis, N., & Eckley, I. (2013). The effect of recovery algorithms on compressive sensing background subtraction. In
– reference: (pp. 242–253).
– reference: Choo, S., Seo, W., Jeong, D., & Cho, N. (2018a). Multi-scale recurrent encoder-decoder network for dense temporal classification. In
– volume: 108
  start-page: 296
  year: 2018
  end-page: 330
  ident: b255
  article-title: Optimal approximation of piecewise smooth functions using deep relu neural networks
  publication-title: Neural Networks
– year: 2017
  ident: b54
  article-title: Pixel-wise deep sequence learning for moving object detection
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– reference: Varadarajan, S., Miller, P., & Zhou, H. (2013). Spatial mixture of Gaussians for dynamic background modelling. In
– reference: (pp. 103–108).
– reference: Javed, S., Bouwmans, T., & Jung, S. (2017). SBMI-LTD: Stationary background model initialization based on low-rank tensor decomposition. In
– reference: Braham, M., & Droogenbroeck, M. V. (2016). Deep background subtraction with scene-specific convolutional neural networks. In
– year: 2018
  ident: b181
  article-title: Learning in memristive neural network architectures using analog backpropagation circuits
– volume: 31
  start-page: 539
  year: 2009
  end-page: 555
  ident: b347
  article-title: Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– reference: (pp. 410–414).
– year: 2019
  ident: b370
  article-title: FSNet: Compression of deep convolutional neural networks by filter summary
– volume: 1
  start-page: 137
  year: 2018
  end-page: 145
  ident: b355
  article-title: Fully memristive neural networks for pattern classification with unsupervised learning
  publication-title: Nature Electronics
– year: 2018
  ident: b14
  article-title: Online illumination invariant moving object detection by generative neural network
– volume: 12
  start-page: 1398
  year: 2011
  end-page: 1412
  ident: b98
  article-title: Adaptive background modeling integrated with luminosity sensors and occlusion processing for reliable vehicle detection
  publication-title: IEEE Transactions on Intelligent Transportation Systems
– reference: Le, D., & Pham, T. (2018). Encoder-decoder convolutional neural network for change detection. In
– reference: Chacon-Muguia, M., Gonzalez-Duarte, S., & Vega, P. (2009). Simplified SOM-neural model for video segmentation of moving objects. In
– reference: Kahng, M., Thorat, N., Chau, D., Viegas, F., & Wattenberg, M. (2019). GAN Lab: Understanding complex deep generative models using interactive visual experimentation. In
– volume: 118
  start-page: 14
  year: 2019
  end-page: 22
  ident: b373
  article-title: A review of convolutional-neural-network-based action recognition
  publication-title: Pattern Recognition Letters
– volume: 122
  start-page: 65
  year: 2014
  end-page: 73
  ident: b220
  article-title: The 3dSOBS+ algorithm for moving object detection
  publication-title: Computer Vision and Image Understanding, CVIU 2014
– reference: Tavakkoli, A., Nicolescu, M., & Bebis, G. (2006). Novelty detection approach for foreground region detection in videos with quasi-stationary backgrounds. In
– reference: Guyon, C., Bouwmans, T., & Zahzah, E. (2012). Foreground detection based on low-rank and block-sparse matrix decomposition. In
– reference: Cohen, N., Tamari, R., & Shashua, A. (2018). Boosting dilated convolutional networks with mixed tensor decompositions. In
– reference: Li, D., Jiang, M., Fang, Y., Huang, Y., & Zhao, C. (2018). Deep video foreground target extraction with complex scenes. In
– reference: Minematsu, T., Shimada, A., & Taniguchi, R. (2017). Analytics of deep neural network in change detection. In
– year: 2017
  ident: b185
  article-title: A method based on motion detection for generating the background of a scene
  publication-title: Pattern Recognition Letters
– year: 2018
  ident: b90
  article-title: A guide to convolution arithmetic for deep learning
– volume: 27
  start-page: 457
  year: 2019
  end-page: 468
  ident: b350
  article-title: Combining spectral and spatial features for deep learning based blind speaker separation
  publication-title: IEEE/ACM Transactions on Audio, Speech, and Language Processing
– reference: Lin, H., Liu, T., & Chuang, J. (2002). A probabilistic SVM approach for background scene initialization,
– year: 2014
  ident: b221
  article-title: Background model initialization for static Cameras
  publication-title: Handbook on background modeling and foreground detection for video surveillance
– reference: Rezaei, B., & Ostadabbas, S. (2017). Background subtraction via fast robust matrix completion. In
– reference: (pp. 1–9).
– reference: Kim, J., Rivera, A., Kim, B., Roy, K., & Chae, O. (2017). Background modeling using adaptive properties of hybrid features. In
– start-page: 1
  year: 2019
  end-page: 21
  ident: b117
  article-title: Dynamic background modeling using deep learning autoencoder network
  publication-title: Multimedia Tools and Applications
– start-page: 14
  year: 2014
  end-page: 29
  ident: b196
  article-title: Robust object detection in severe imaging conditions using co-occurrence background model
  publication-title: International Journal of Optomechatronics
– volume: 4
  start-page: 251
  year: 1991
  end-page: 257
  ident: b150
  article-title: Approximation capabilities of multilayer feedforwardnetworks
  publication-title: Neural Networks
– year: 2015
  ident: b259
  article-title: Unsupervised representation learning with deep convolutional generative adversarial networks
– reference: (pp. 770–778).
– reference: Javed, S., Bouwmans, T., & Jung, S. (2015b). Depth extended online RPCA with spatiotemporal constraints for robust background subtraction. In
– year: 2017
  ident: b193
  article-title: Adaptive deep convolutional neural networks for scene-specific object detection
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– reference: Gregorio, M., & Giordano, M. (2017). CwisarDH+: Background detection in RGBD videos by learning of weightless neural networks. In
– reference: (pp. 5133–5141).
– reference: (pp. 675–678).
– year: 2018
  ident: b393
  article-title: Object detection with deep learning: A review
– reference: Silva, C., Bouwmans, T., & Frelicot, C. (2015). An eXtended center-symmetric local binary pattern for background modeling and subtraction in videos. In
– year: 2018
  ident: b278
  article-title: Illumination-aware multi-task GANs for foreground segmentation
  publication-title: IEEE Access
– reference: Xu, P., Ye, M., Li, X., Liu, Q., Yang, Y., & Ding, J. (2014). Dynamic background learning through deep auto-encoder networks. In
– volume: 28
  start-page: 013038
  year: 2019
  ident: b46
  article-title: Deep learning-based scene-awareness approach for intelligent change detection in videos
  publication-title: Journal of Electronic Imaging
– year: 2018
  ident: b201
  article-title: Foreground segmentation using a triplet convolutional neural network for multiscale feature encoding
– reference: Maddalena, L., & Petrosino, A. (2009a). Multivalued background/foreground separation for moving object detection. In
– volume: 19
  start-page: 780
  year: 1997
  end-page: 785
  ident: b359
  article-title: Pfinder: Real-time tracking of the human body
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– reference: Deng, J., Dong, W., Socher, R., Li, L., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. In
– reference: Xu, L., Li, Y., Wang, Y., & Chen, E. (2015). Temporally adaptive restricted Boltzmann machine for background modeling. In
– reference: Choromanska, A., Henaff, M., Mathieu, M., Arous, G., & LeCun, Y. (2015). The loss surfaces of multilayer networks. In
– year: 2010
  ident: b86
  article-title: Adaptive learning of multi-subspace for foreground detection under illumination changes
  publication-title: Computer Vision and Image Understanding
– reference: Farcas, D., & Bouwmans, T. (2010). Background modeling via a supervised subspace learning. In
– volume: 23
  start-page: 1
  year: 2017
  end-page: 71
  ident: b29
  article-title: Decomposition into low-rank plus additive matrices for background/foreground separation: A review for a comparative evaluation with a large-scale dataset
  publication-title: Computer Science Review
– year: 2018
  ident: b397
  article-title: Background subtraction algorithm based on Bayesian generative adversarial networks
  publication-title: Acta Automatica Sinica
– reference: Yang, J., Yang, J., Yang, X., & Yue, H. (2016). Background recovery from video sequences via online motion-assisted RPCA. In
– year: 2014
  ident: b100
  article-title: Background subtraction model based on color and depth cues
  publication-title: Machine Vision and Applications
– year: 2019
  ident: b362
  article-title: Deep learning-based methods for person re-identification: A comprehensive review
  publication-title: Neurocomputing
– reference: (pp. 1519–1522).
– reference: (pp. 2724–2730).
– year: 1962
  ident: b357
  article-title: Generalization and information storage in networks of ADALINE
  publication-title: Self Organizing Systems
– reference: Shafiee, M., Siva, P., Fieguth, P., & Wong, A. (2016). Embedded motion detection via neural response mixture background modeling. In
– volume: 122
  start-page: 74
  year: 2014
  end-page: 83
  ident: b302
  article-title: A texton-based kernel density estimation approach for background modeling under extreme conditions
  publication-title: Computer Vision and Image Understanding, CVIU 2014
– volume: 234
  start-page: 11
  year: 2017
  end-page: 26
  ident: b205
  article-title: A survey of deep neural network architectures and their applications
  publication-title: Neurocomputing
– year: 2017
  ident: b27
  article-title: Scene background initialization: a taxonomy
  publication-title: Pattern Recognition Letters
– volume: 26
  start-page: 5840
  year: 2017
  end-page: 5854
  ident: b166
  article-title: Background-foreground modeling based on spatio-temporal sparse subspace clustering
  publication-title: IEEE Transactions on Image Processing
– reference: (pp. 469–476).
– reference: Nishani, E., & Cico, B. (2017). Computer vision approaches based on deep learning and neural networks: Deep neural networks for video analysis of human pose estimation. In
– reference: Narayanamurthy, P., & Vaswani, N. (2018). A fast and memory-efficient algorithm for robust PCA (MEROP). In
– volume: 86
  start-page: 2278
  year: 1998
  end-page: 2324
  ident: b78
  article-title: Gradient-based learning applied to document recognition
  publication-title: Proceedings of IEEE
– volume: 15
  start-page: 1929
  year: 2014
  end-page: 1958
  ident: b303
  article-title: Dropout: A simple way to prevent neural networks from overfitting
  publication-title: Journal of Machine Learning Research (JMLR)
– reference: Cheng, Y., Diakonikolas, I., Kane, D., & Stewart, A. (2018). Robust learning of fixed-structure Bayesian networks. In
– volume: 23
  start-page: 1083
  year: 2012
  end-page: 1101
  ident: b96
  article-title: Background subtraction via incremental maximum margin criterion: A discriminative approach
  publication-title: Machine Vision and Applications
– reference: (pp. 422–433).
– year: 2018
  ident: b332
  article-title: Mathematics of deep learning
– reference: Javed, S., Mahmood, A., Bouwmans, T., & Jung, S. (2016a). Motion-aware graph regularized RPCA for background modeling of complex scenes. In
– volume: 55
  start-page: 1
  year: 2016
  end-page: 18
  ident: b271
  article-title: Incremental principal component pursuit for video background modeling
  publication-title: Journal of Mathematical Imaging and Vision
– reference: Rodriguez, P., & Wohlberg, B. 2015. Translational and rotational jitter invariant incremental principalcomponent pursuit for video background modeling. In
– reference: Yan, Y., Zhao, H., Kao, F., Vargas, V., Zhao, S., & Ren, J. (2018). Deep background subtraction of thermal and visible imagery for pedestrian detection in videos. In
– reference: Lopez-Rubio, F., Lopez-Rubio, E., Luque-Baena, R., Dominguez, E., & Palomo, E. (2014). Color space selection for self-organizing map based foreground detection in video sequences. In
– year: 2017
  ident: b237
  article-title: Analysis of universal adversarial perturbations
– reference: (pp. 742–751).
– year: 2019
  ident: b404
  article-title: Deconstructing generative adversarial networks
– reference: (pp. 751–767).
– reference: Haines, T., & Xiang, T. (2012). Background subtraction with Dirichlet processes. In
– year: 2016
  ident: b346
  article-title: Interactive deep learning method for segmenting moving objects
  publication-title: Pattern Recognition Letters
– reference: Patil, P., & Murala, S. (2019). FgGAN: A cascaded unpaired learning for background estimation and foreground segmentation. In
– reference: Haeffele, B., & Vidal, R. (2017). Global optimality in neural network training. In
– reference: Chacon-Murguia, M., Ramirez-Alonso, G., & Gonzalez-Duarte, S. (2013). Improvement of a neural-fuzzy motion detection vision model for complex scenario conditions. In
– reference: Cane, T., & Ferryman, J. Evaluating deep semantic segmentation networks for object detection in maritime surveillance. In
– reference: Baf, F. E., Bouwmans, T., & Vachon, B. (2008b). Fuzzy integral for moving object detection. In
– reference: (pp. 2811–2818).
– reference: (pp. 1–4).
– reference: Zheng, S., Song, Y., Leung, T., & Goodfellow, I. (2018). Improving the robustness of deep neural networks via stability training. In
– reference: Nair, V., & Hinton, G. (2010). Rectified linear units improve restricted Boltzmann machines. In
– reference: . (pp. 1729–1736).
– reference: Cuevas, C., & Garcia, N. (2010). Tracking-based non-parametric background-foreground classification in a chromaticity-gradient space. In
– year: 2018
  ident: b380
  article-title: Background subtraction with real-time semantic segmentation
– volume: 25
  start-page: 1
  year: 2016
  end-page: 13
  ident: b36
  article-title: DehazeNet: AN end-to-end system for single image haze removal
  publication-title: IEEE Transactions on Image Processing
– reference: (pp. 192–204).
– reference: Wang, X., Liu, L., Li, G., Dong, X., Zhao, P., & Feng, X. (2018). Background subtraction on depth videos with convolutional neural networks. In
– reference: Mopuri, K., Garg, U., & Babu, R. (2017). Fast feature fool: A data independent approach to universal adversarial perturbations. In
– reference: Camplani, M., Maddalena, L., Alcover, G. M., Petrosino, A., & Salgado, L. (2017a). RGB-D dataset: Background learning for detection and tracking from RGBD videos. In
– volume: 27
  start-page: 178
  year: 2019
  end-page: 188
  ident: b354
  article-title: Robust speaker localization guided by deep learning-based time-frequency masking
  publication-title: IEEE/ACM Transactions on Audio, Speech, and Language Processing
– reference: Hasan, R., Taha, T., & Yakopcic, C. (2017). On-chip training of memristor based deep neural networks. In
– reference: Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In
– reference: He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In
– reference: (pp. 3274–3281).
– reference: Zheng, Z., & Hong, P. (2018). Robust detection of adversarial attacks by modeling the intrinsic properties of deep neural networks. In
– reference: Cheng, M., Xia, L., Zhu, Z., Cai, Y., Xie, Y., & Wang, Y., et al. (2017). Time: A training-in-memory architecture for memristor-based deep neural networks. In
– volume: 13
  start-page: 1459
  year: 2004
  end-page: 1472
  ident: b191
  article-title: Statistical modeling of complex background for foreground object detection
  publication-title: IEEE Transaction on Image Processing
– volume: 29
  start-page: 1421
  year: 1996
  end-page: 1428
  ident: b285
  article-title: A system for counting people in video images using neural networks to identify the background scene
  publication-title: Pattern Recognition
– reference: Krestinskaya, O., Salama, K., & James, A. (2018a). Analog back propagation learning circuits for memristive crossbar neural networks. In
– reference: Chang, B., Meng, L., Haber, E., Ruthotto, L., Begert, D., & Holtham, E. (2018). Reversible architectures for arbitrarily deep residual neural networks. In
– reference: Zin, T., Tin, P., Toriu, T., & Hama, H. A new background subtraction method using bivariate Poisson process. In
– reference: Giryes, R., Sapiro, G., & Bronstein, A. (2015). On the stability of deep networks. In
– year: 2018
  ident: b343
  article-title: Scene classification with recurrent attention of VHR remote sensing images
  publication-title: IEEE Transactions on Geoscience and Remote Sensing
– volume: 78
  start-page: 1415
  year: 1990
  end-page: 1442
  ident: b358
  article-title: 30 years of adaptive neural networks: perceptron, madaline, and backpropagation
  publication-title: Proceedings of the IEEE
– start-page: 103
  year: 2012
  end-page: 139
  ident: b22
  article-title: Background subtraction for visual surveillance: A fuzzy approach
  publication-title: Handbook on soft computing for video surveillance
– reference: Moosavi-Dezfooli, S., Fawzi, A., Fawzi, O., & Frossard, P. (2017). Universal adversarial perturbations. In
– reference: Xiao, H., Feng, J., Lin, G., Liu, Y., & Zhang, M. (2018). MoNet: Deep motion exploitation for video object segmentation. In
– reference: Yoon, J., Rameau, F., Kim, J., Lee, S., Shin, S., & Kweon, I. S. (2017). Pixel-level matching for video object segmen-tation using convolutional neural networks. In
– reference: Javed, S., Sobral, A., Oh, S., Bouwmans, T., & Jung, S. (2014). OR-PCA with MRF for robust foreground detection in highly dynamic backgrounds. In
– volume: 4
  year: 2018
  ident: b186
  article-title: Labgen-p-semantic: A first step for leveraging semantic segmentation in background generation
  publication-title: MDPI Journal of Imaging
– reference: (pp. 1670–1675).
– year: 2013
  ident: b364
  article-title: GOSUS: Grassmannian online subspace updates with structured-sparsity
  publication-title: International Conference on Computer Vision, ICCV 2013
– reference: Braham, M., Pierard, S., & Droogenbroeck, M. V. (2017). Semantic background subtraction. In
– reference: Graves, A., Mohamed, A., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. In
– reference: Guyon, C., Bouwmans, T., & Zahzah, E. (2012). Robust principal component analysis for background subtraction: Systematic evaluation and comparative analysis. In
– reference: Maddalena, L., & Petrosino, A. (2009b). 3D neural model-based stopped object detection. In
– reference: Baf, F. E., Bouwmans, T., & Vachon, B. (2008c). Type-2 fuzzy mixture of Gaussians model: Application to background modeling. In
– volume: 60
  year: 2015
  ident: b242
  article-title: The detection of moving objects in video by background subtraction using dempster-shafer theory
  publication-title: Transactions on Electronics and Communications
– volume: 64
  start-page: 739
  year: 2010
  end-page: 747
  ident: b361
  article-title: Spatio-temporal context for codebook-based dynamic background subtraction
  publication-title: AEU-International Journal of Electronic Communication
– reference: He, J., Balzano, L., & Szlam, A. (2012). Incremental gradient on the grassmannian for online foreground and background separation in subsampled video. In
– volume: 26
  start-page: 1702
  year: 2018
  end-page: 1726
  ident: b337
  article-title: Supervised speech separation based on deep learning: An overview
  publication-title: IEEE/ACM Transactions on Audio, Speech, and Language Processing
– reference: Bouwmans, T., & Garcia-Garcia, B. (2019). Background Subtraction in Real Applications: Challenges, Current Models and Future Directions, Preprint.
– volume: 19
  start-page: 230
  year: 2018
  end-page: 241
  ident: b339
  article-title: Embedding structured contour and location prior in siamesed fully convolutional networks for road detection
  publication-title: IEEE Transactions on Intelligent Transportation Systems
– year: 2018
  ident: b153
  article-title: 3D atrous convolutional long short-term memory network for background subtraction
  publication-title: IEEE Access
– reference: (pp. 6645–6649).
– reference: Teng, X., Yan, M., Ertugrul, A., & Lin, Y. (2018). Deep into hypersphere: Robust and unsupervised anomaly discovery in dynamic networks. In
– reference: Laugraud, B., Pierard, S., & Droogenbroeck, M. V. (2016). LaBGen-P: A pixel-level stationary background generation method based on LaBGen. In
– reference: , 2014.
– reference: Yuan, Y., & Z. Xiong, a. Q. W. (2019). ACM: Adaptive cross-modal graph convolutional neural networks for RGB-D scene recognition. In
– year: 2011
  ident: b391
  article-title: Background subtraction via robust dictionary learning
  publication-title: EURASIP Journal on Image and Video Processing, IVP 2011
– reference: Ranzato, M., Krizhevsky, A., & Hinton, G. (2010). Factored 3-Way restricted Boltzmann machines for modeling natural images. In
– volume: 1
  start-page: 265
  year: 2009
  end-page: 277
  ident: b25
  article-title: Modeling of dynamic backgrounds by type-2 Fuzzy Gaussians mixture models
  publication-title: MASAUM Journal of Basic and Applied Sciences
– volume: 27
  start-page: 189
  year: 2019
  end-page: 198
  ident: b314
  article-title: Gated residual networks with dilated convolutions for monaural speech enhancement
  publication-title: IEEE/ACM Transactions on Audio, Speech, and Language Processing
– reference: Zhang, H., & Xu, D. 2006a. Fusing color and gradient features for background model. In
– reference: He, K., Zhang, X., & Ren, S. (2016). Deep residual learning for image recognition. In
– reference: Karadag, O., & Erdas, O. (2018). Evaluation of the robustness of deep features on the change detection problem. In
– year: 2018
  ident: b248
  article-title: Learning deep models: Critical points and local openness
– year: 2016
  ident: b240
  article-title: Modelling depth for nonparametric foreground segmentation using RGBD devices
  publication-title: Pattern Recognition Letters
– reference: (pp. 1770–1778).
– year: 2018
  ident: b351
  article-title: Foreground detection with deeply learned multi-scale spatial-temporal features
  publication-title: MDPI Sensors
– year: 2017
  ident: b276
  article-title: Real-time adaptive histogram min-max bucket (HMMB) model for background subtraction
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– reference: .
– volume: 35
  start-page: 32
  year: 2018
  end-page: 55
  ident: b329
  article-title: Robust subspace learning: Robust PCA, robust subspace tracking and robust subspace recovery
  publication-title: IEEE Signal Processing Magazine
– reference: Du, Y., Yuan, C., Hu, W., & Maybank, S. (2017). Spatio-temporal self-organizing map deep network for dynamic object detection from videos. In
– reference: (pp. 893–896).
– year: 2019
  ident: b8
  article-title: sEnDec: An improved image to image CNN for foreground localization
  publication-title: IEEE Intelligent Transportation Systems Transactions
– reference: (pp. 3431–3440).
– reference: Stauffer, C., & Grimson, E. (1999). Adaptive background mixture models for real-time tracking. In
– reference: Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved techniques for training GANs. In
– reference: Wang, R., Bunyak, F., Seetharaman, G., & Palaniappa, K. (2014). Static and moving object detection using flux tensor with split Gaussian models. In
– year: 2017
  ident: b390
  article-title: Joint background reconstruction and foreground segmentation via a two-stage convolutional neural network
– reference: Goyette, N., Jodoin, P., Porikli, F., Konrad, J., & Ishwar, P. (2012). Changedetection.net: A new change detection benchmark dataset. In
– reference: Guo, R., & Qi, H. (2013). Partially-sparse restricted Boltzmann machine for background modeling and subtraction. In
– year: 2014
  ident: b37
  article-title: Advanced background modeling with RGB-D sensors through classifiers combination and inter-frame foreground prediction
  publication-title: Machine Vision and Applications
– year: 2019
  ident: b50
  article-title: Deep, landmark-free FAME: Face alignment, modeling, and expression estimation
  publication-title: International Journal of Computer Vision
– volume: 20
  start-page: 273
  year: 1995
  end-page: 297
  ident: b72
  article-title: Support-vector networks
  publication-title: Machine Learning
– reference: Wang, H., Lai, Y., Cheng, W., Cheng, C., & Hua, K. (2017). Background extraction based on joint gaussian conditional random fields. In
– reference: Liang, X., Liao, S., Wang, X., Liu, W., Chen, Y., & Li, S. (2018). Deep background subtraction with guided learning. In
– volume: 5
  start-page: 115
  year: 1943
  end-page: 133
  ident: b77
  article-title: A logical calculus of the ideas immanent in nervous activity
  publication-title: Bulletin of Mathematical Biophysics
– reference: Tao, Y., Palasek, P., Ling, Z., & Patras, I. (2017). Background modelling based on generative Unet. In
– reference: Messelodi, S., Modena, C., Segata, N., & Zanin, M. (2005). A Kalman filter based background updating algorithm robust to sharp illumination changes. In
– reference: Maddalena, L., & Petrosino, A. (2009c). Self organizing and fuzzy modelling for parked vehicles detection. In
– year: 2015
  ident: b392
  article-title: Stacked multi-layer self-organizing map for background modeling
  publication-title: IEEE Transactions on Image Processing
– reference: Cohen, N., & Shashua, A. (2016). Convolutional rectifier networks as generalized tensor decompositions. In
– volume: 4
  start-page: 79
  year: 2018
  ident: b123
  article-title: Deep learning with a spatiotemporal descriptor of appearance and motion estimation for video anomaly detection
  publication-title: MDPI Journal of Imaging
– year: 2018
  ident: b382
  article-title: Combining background subtraction algorithms with convolutional neural network
– year: 2013
  ident: b179
  article-title: Auto-encoding variational bayes
– year: 2018
  ident: b4
  article-title: Video foreground localization from traditional methods to deep learning
– volume: 19
  start-page: 1
  year: 2018
  end-page: 42
  ident: b81
  article-title: Connections with robust PCA and the role of emergent sparsity in variational autoencoder models
  publication-title: Journal of Machine Learning Research (JMLR)
– reference: Culibrk, D., Marques, O., Socek, D., Kalva, H., & Furht, B. (2006). A neural network approach to Bayesian background modeling for video object segmentation. In
– reference: He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on Imagenet classification. In
– reference: Sobral, A., Bouwmans, T., & Zahzah, E. (2015a). Comparison of matrix completion algorithms for background initialization in videos. In
– reference: Yun, C., Sra, S., & Jadbabaie, A. (2018). A critical view of global optimality in deep learning. In
– reference: Javed, S., Bouwmans, T., & Jung, S. (2015c). Stochastic decomposition into low rank and sparse tensor for robust background subtraction. In
– year: 2018
  ident: b55
  article-title: Learning to detect instantaneous changes with retrospective convolution and static sample synthesis
– reference: -norm stacked robust autoencoders for domain adaptation. In
– reference: Chang, T., Ghandi, T., & Trivedi, M. (2004). Vision modules for a multi sensory bridge monitoring approach. In
– volume: 39
  start-page: 1137
  year: 2017
  end-page: 1149
  ident: b267
  article-title: Faster R-CNN: Towards real-time object detection with region proposal networks
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– reference: Bai, J., Zhang, H., & Li, Z. (2018). The generalized detection method for the dim small targets by faster R-CNN integrated with GAN. In
– year: 2013
  ident: b93
  article-title: Finite asymmetric generalized Gaussian mixture models learning for infrared object detection
  publication-title: Computer Vision and Image Understanding
– year: 2018
  ident: b107
  article-title: Lightweight probabilistic deep networks
– reference: (pp. 4118–4122).
– year: 2007
  ident: b146
  article-title: Deep belief nets
  publication-title: NIPS Tutorial
– start-page: 1
  year: 2018
  end-page: 23
  ident: b87
  article-title: Background subtraction based on deep convolutional neural networks features
  publication-title: Multimedia Tools and Applications
– year: 2018
  ident: b5
  article-title: A foreground inference network for video surveillance using multi-view receptive field
– reference: Gemignani, G., & Rozza, A. (2015). A novel background subtraction approach based on multi-layered self organizing maps. In
– reference: (pp. 1140–1148).
– year: 2018
  ident: b376
  article-title: ReMotENet: EFficient relevant motion event detection for large-scale home surveillance videos
– reference: Halfaoui, I., Bouzaraa, F., & Urfalioglu, O. (2016). CNN-based initial background estimation. In
– volume: 25
  start-page: 1006
  year: 2017
  end-page: 1012
  ident: b84
  article-title: A hierarchical fused Fuzzy deep neural network for data classification
  publication-title: IEEE Transactions on Fuzzy Systems
– reference: (pp. 263–270).
– year: 2018
  ident: b252
  article-title: MSFgNet: A novel compact end-to-end deep network for moving object detection
  publication-title: IEEE Transactions on Intelligent Transportation Systems
– year: 2017
  ident: b10
  article-title: A deep convolutional neural network for background subtraction
  publication-title: Pattern Recognition
– year: 2019
  ident: b338
  article-title: Deep face recognition: A survey
– year: 2018
  ident: b234
  article-title: Analytics of deep neural network-based background subtraction
  publication-title: MDPI Journal of Imaging
– year: 2018
  ident: b113
  article-title: Unsupervised video object segmentation for deep reinforcement learning
– year: 2018
  ident: b294
  article-title: Background subtraction using Gaussian
  publication-title: IET Image Processing
– reference: (pp. 255–261).
– reference: Lanza, A., Tombari, F., & Stefano, L. D. (2010). Accurate and efficient background subtraction by monotonic second-degree polynomial fitting. In
– reference: Hofmann, M., Tiefenbacher, P., & Rigoll, G. (2012). Background Segmentation with Feedback: The Pixel-Based Adaptive Segmenter. In
– reference: Chen, Y., Wang, J., & Lu, H. (2015). Learning sharable models for robust background subtraction. In
– reference: Gao, Y., Cai, H., Zhang, X., Lan, L., & Luo, Z. (2018). Background subtraction via 3D convolutional neural networks. In
– year: 2017
  ident: b65
  article-title: Anomaly detection in surveillance videos using deep residual networks
– reference: Cohen, N., Sharir, O., & Shashua, A. (2016b). On the expressive power of deep learning: A tensor analysis. In
– year: 2018
  ident: b349
  article-title: Robust hierarchical deep learning for vehicular management
  publication-title: IEEE Transactions on Vehicular Technology
– reference: (pp. 652–661).
– reference: (pp. 219–229).
– year: 2017
  ident: b45
  article-title: Robust, deep and inductive anomaly detection
– reference: (pp. 3347–3354).
– reference: Wang, W., Sun, Y., Eriksson, B., Duke, W., & Aggarwal, V. Wide compression: Tensor ring net. In
– reference: (pp. 1271–1276).
– year: 2016
  ident: b290
  article-title: Stochasticnet: Forming deep neural networks via stochastic connectivity
  publication-title: IEEE Access
– volume: 28
  start-page: 26
  year: 2018
  end-page: 91
  ident: b28
  article-title: On the role and the importance of features for background modeling and foreground detection
  publication-title: Computer Science Review
– start-page: 165
  year: 2014
  end-page: 169
  ident: b261
  article-title: Background scene modeling for PTZ cameras using RBM
  publication-title: International Conference on Control, Automation and Information Sciences, ICCAIS 2014
– reference: Sobral, A., Bouwmans, T., & Zahzah, E. (2015b). Double-constrained RPCA based on saliency maps for foreground detection in automated maritime surveillance. In
– reference: (pp. 3527–3534).
– reference: Jiang, W., Gao, H., Chung, F., & Huang, H. (2016). The
– volume: 1
  start-page: 22
  year: 2019
  end-page: 53
  ident: b293
  article-title: Performance analysis of moving object detection using BGS techniques in visual surveillance
  publication-title: International Journal of Spatio-Temporal Data Science, Inderscience
– start-page: 254
  year: 2017
  end-page: 257
  ident: b155
  article-title: Deep neural network accelerator based on FPGA
  publication-title: NAFOSTED 2017
– reference: Thekumparampil, K., Khetan, A., Lin, Z., & Oh, S. (2018). Robustness of conditional GANs to noisy labels. In
– year: 2018
  ident: b199
  article-title: Learning multi-scale features for foreground segmentation
– volume: 28
  start-page: 657
  year: 2006
  end-page: 662
  ident: b145
  article-title: A texture-based method for modeling the background and detecting moving objects
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI 2006
– year: 1957
  ident: b275
  publication-title: The perceptron–a perceiving and recognizing automaton
– volume: 58
  year: 2011
  ident: b40
  article-title: Robust principal component analysis?
  publication-title: International Journal of ACM
– volume: 97
  start-page: 173
  year: 2018
  end-page: 182
  ident: b19
  article-title: Deep neural networks for texture classification: A theoretical analysis
  publication-title: Neural Networks
– reference: Choo, S., Seo, W., Jeong, D., & Cho, N. 2018b. Learning background subtraction by video synthesis and multi-scale recurrent networks. In
– reference: (pp. 153–160).
– start-page: 85
  year: 2015
  end-page: 117
  ident: b284
  article-title: Deep learning in neural networks: An overview
  publication-title: Neural Networks
– reference: He, J., Balzano, L., & Luiz, J. (2011). Online robust subspace tracking from partial information. In
– year: 2018
  ident: b398
  article-title: A novel background subtraction algorithm based on parallel vision and Bayesian GANs
  publication-title: Neurocomputing
– volume: 17
  start-page: 1168
  year: 2008
  end-page: 1177
  ident: b213
  article-title: A self organizing approach to background subtraction for visual surveillance applications
  publication-title: IEEE Transactions on Image Processing
– reference: (pp. 474–480).
– reference: Afonso, B., Cinelli, L., Thomaz, L., da Silva, A., da Silva, E., & Netto, S. (2018). Moving-camera video surveillance in cluttered environments using deep features. In
– year: 2017
  ident: b125
  article-title: A review of semantic segmentation using deep neural networks
  publication-title: International Journal of Multimedia Information Retrieval
– reference: Huang, J., Huang, X., & Metaxas, D. (2009). Learning with dynamic group sparsity. In
– reference: Liang, D., Kaneko, S., Hashimoto, M., Iwata, K., Zhao, X., & Satoh, Y. (2013). Co-occurrence-based adaptive background model for robust object detection. In
– volume: 10
  start-page: 40
  year: 2007
  ident: b51
  article-title: Efficient hierarchical method for background subtraction
  publication-title: Pattern Recognition
– volume: 26
  start-page: 5244
  year: 2017
  end-page: 5256
  ident: b174
  article-title: Extensive benchmark and survey of modeling methods for scene background initialization
  publication-title: IEEE Transactions on Image Processing
– reference: Garcia-Gonzalez, J., de Lazcano-Lobato, J. O., Luque-Baena, R., & Molina-Cabello, M. (2018). Background modeling for video sequences by stacked denoising autoencoders. In
– reference: Rosell-Ortega, J., Andreu-Garcia, G., Rodas-Jorda, A., & Atienza-Vanacloig, V. (2008). Background modelling in demanding situations with confidence measure. In
– reference: (pp. 246–252).
– reference: Zhang, H., & Xu, D. (2006b). Fusing color and texture features for background model. In
– volume: 14
  start-page: 115
  year: 1994
  end-page: 133
  ident: b18
  article-title: Approximation and estimation bounds for artificial neural networks
  publication-title: Neural Networks
– reference: (pp. 341–350).
– reference: Bakkay, M., Rashwan, H., Salmane, H., Khoudour, L., Puig, D., & Ruichek, Y. (2018). BSCGAN: Deep background subtraction with conditional generative adversarial networks. In
– volume: 20
  start-page: 1709
  year: 2011
  end-page: 1724
  ident: b17
  article-title: ViBe: A universal background subtraction algorithm for video sequences
  publication-title: IEEE Transactions on Image Processing
– year: 2017
  ident: b264
  article-title: Temporal weighted learning model for background estimation with an automatic re-initialization stage and adaptive parameters update
  publication-title: Pattern Recognition Letters
– reference: Hu, Y., Huang, J., & Schwing, A. (2017). MaskRNN: Instance level video object segmentation. In
– reference: Oliver, N., Rosario, B., & Pentland, A. (1999). A Bayesian computer vision system for modeling human interactions. In
– reference: (pp. 254–265).
– year: 2016
  ident: b330
  article-title: Matconvnet: Convolutional neural networks for MATLAB
– volume: 97
  start-page: 162
  year: 2018
  end-page: 172
  ident: b344
  article-title: Visualizing deep neural network by alternately image blurring and deblurring
  publication-title: Neural Networks
– volume: 122
  start-page: 22
  year: 2014
  end-page: 34
  ident: b30
  article-title: Robust PCA via principal component pursuit: A review for a comparative evaluation in video surveillance
  publication-title: Special Issue on Background Models Challenge, Computer Vision and Image Understanding, CVIU 2014
– reference: Guo, L., & Du, M. (2012). Student’s t-distribution mixture background model for efficient object detection. In
– start-page: 1
  year: 2010
  end-page: 8
  ident: b217
  article-title: A fuzzy spatial coherence-based approach to background/foreground separation for moving object detection
  publication-title: Neural Computing and Applications, NCA 2010
– year: 2018
  ident: b225
  article-title: Background subtraction for moving object detection in RGB-D data: A survey
  publication-title: MDPI Journal of Imaging
– volume: 112
  start-page: 256
  year: 2018
  end-page: 262
  ident: b202
  article-title: Foreground segmentation using convolutional neural networks for multiscale feature encoding
  publication-title: Pattern Recognition Letters
– reference: Zhou, C., & Paffenroth, R. (2017). Anomaly detection with robust deep autoencoders. In
– reference: Tavakkoli, A., Ambardekar, A., Nicolescu, M., & Louis, S. (2007). A genetic approach to training support vector data descriptors for background modeling in video data. In
– reference: (pp. 1026–1034).
– reference: Elgammal, A., & Davis, L. (2000). Non-parametric model for background subtraction. In
– volume: 34
  start-page: 014004
  year: 2017
  ident: b133
  article-title: Stable architectures for deep neural networks
  publication-title: Inverse Problems
– year: 2018
  ident: b309
  article-title: Unsupervised deep context prediction for background estimation and foreground segmentation
  publication-title: Machine Vision and Applications
– reference: Akilan, T., & Wu, J. (2018). Double encoding - slow decoding image to image CNN for foreground identification with application towards intelligent transportation. In
– reference: Javed, S., Bouwmans, T., Sultana, M., & Jung, S. (2017). Moving object detection on RGB-D videos using graph regularized spatiotemporal RPCA. In
– reference: Guo, X., Wang, X., Yang, L., Cao, X., & Ma, Y. (2014). Robust Foreground Detection using Smoothness and Arbitrariness Constraints. In
– volume: 35
  start-page: 872
  year: 2013
  end-page: 1886
  ident: b33
  article-title: Invariant scattering convolution networks
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– reference: Maddalena, L., & Petrosino, A. (2015). Towards benchmarking scene background initialization. In
– reference: Wang, M., Li, W., & Wang, X. (2012). Transferring a generic pedestrian detector towards specific scenes. In:
– reference: (pp. 4480–4488).
– year: 2016
  ident: b52
  article-title: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution and fully connected CRFs
– reference: Maddalena, L., & Petrosino, A. (2012). The SOBS algorithm: What are the limits?. In
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b325
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b404
– ident: 10.1016/j.neunet.2019.04.024_b135
  doi: 10.1109/CVPR.2017.467
– ident: 10.1016/j.neunet.2019.04.024_b180
  doi: 10.1109/ISCAS.2018.8351344
– ident: 10.1016/j.neunet.2019.04.024_b162
  doi: 10.1007/978-3-319-70742-6_22
– volume: 30
  start-page: 1004
  issue: 12
  year: 2012
  ident: 10.1016/j.neunet.2019.04.024_b333
  article-title: Real-time robust background subtraction under rapidly changing illumination conditions
  publication-title: Image Vision and Computing
  doi: 10.1016/j.imavis.2012.08.017
– ident: 10.1016/j.neunet.2019.04.024_b345
  doi: 10.1109/IJCNN.2018.8489230
– ident: 10.1016/j.neunet.2019.04.024_b270
– ident: 10.1016/j.neunet.2019.04.024_b131
  doi: 10.1007/978-3-642-33179-4_41
– ident: 10.1016/j.neunet.2019.04.024_b43
  doi: 10.1109/IJCNN.2009.5178632
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b240
  article-title: Modelling depth for nonparametric foreground segmentation using RGBD devices
  publication-title: Pattern Recognition Letters
– start-page: 85
  year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b284
  article-title: Deep learning in neural networks: An overview
  publication-title: Neural Networks
  doi: 10.1016/j.neunet.2014.09.003
– ident: 10.1016/j.neunet.2019.04.024_b396
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b5
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b260
  article-title: Unsupervised representation learning with deep convolutional generative adversarial networks
  publication-title: Computer Science
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b88
– volume: 26
  start-page: 903
  issue: 5
  year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b369
  article-title: Pixel-to-model distance for robust background reconstruction
  publication-title: IEEE Transactions on Circuits Systems and Video Technology
  doi: 10.1109/TCSVT.2015.2424052
– start-page: 254
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b155
  article-title: Deep neural network accelerator based on FPGA
  publication-title: NAFOSTED 2017
– ident: 10.1016/j.neunet.2019.04.024_b326
– ident: 10.1016/j.neunet.2019.04.024_b223
  doi: 10.1109/ICPR.2016.7899623
– ident: 10.1016/j.neunet.2019.04.024_b161
  doi: 10.1145/3019612.3019687
– ident: 10.1016/j.neunet.2019.04.024_b281
– volume: 77
  start-page: 354
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b122
  article-title: Recent advances in convolutional neural networks
  publication-title: Pattern Recognition
  doi: 10.1016/j.patcog.2017.10.013
– ident: 10.1016/j.neunet.2019.04.024_b159
  doi: 10.1109/FCV.2015.7103745
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b346
  article-title: Interactive deep learning method for segmenting moving objects
  publication-title: Pattern Recognition Letters
– ident: 10.1016/j.neunet.2019.04.024_b157
  doi: 10.1109/CVPR.2017.790
– ident: 10.1016/j.neunet.2019.04.024_b233
  doi: 10.1109/AVSS.2017.8078550
– ident: 10.1016/j.neunet.2019.04.024_b286
  doi: 10.1109/CVPRW.2014.65
– ident: 10.1016/j.neunet.2019.04.024_b280
  doi: 10.1109/ICASSP.2019.8682914
– ident: 10.1016/j.neunet.2019.04.024_b1
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b14
– volume: 28
  start-page: 657
  issue: 4
  year: 2006
  ident: 10.1016/j.neunet.2019.04.024_b145
  article-title: A texture-based method for modeling the background and detecting moving objects
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI 2006
  doi: 10.1109/TPAMI.2006.68
– ident: 10.1016/j.neunet.2019.04.024_b197
  doi: 10.1109/ICME.2018.8486556
– volume: 4
  start-page: 251
  issue: 2
  year: 1991
  ident: 10.1016/j.neunet.2019.04.024_b150
  article-title: Approximation capabilities of multilayer feedforwardnetworks
  publication-title: Neural Networks
  doi: 10.1016/0893-6080(91)90009-T
– volume: 27
  start-page: 189
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b314
  article-title: Gated residual networks with dilated convolutions for monaural speech enhancement
  publication-title: IEEE/ACM Transactions on Audio, Speech, and Language Processing
  doi: 10.1109/TASLP.2018.2876171
– ident: 10.1016/j.neunet.2019.04.024_b92
  doi: 10.1007/3-540-45053-X_48
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b173
– volume: 19
  start-page: 230
  issue: 1
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b339
  article-title: Embedding structured contour and location prior in siamesed fully convolutional networks for road detection
  publication-title: IEEE Transactions on Intelligent Transportation Systems
  doi: 10.1109/TITS.2017.2749964
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b125
  article-title: A review of semantic segmentation using deep neural networks
  publication-title: International Journal of Multimedia Information Retrieval
– volume: 2
  start-page: 359
  issue: 5
  year: 1989
  ident: 10.1016/j.neunet.2019.04.024_b151
  article-title: Multilayer feedforward networks are universal approximators
  publication-title: Neural Networks
  doi: 10.1016/0893-6080(89)90020-8
– ident: 10.1016/j.neunet.2019.04.024_b109
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b382
– ident: 10.1016/j.neunet.2019.04.024_b126
  doi: 10.1109/ICMLA.2013.43
– start-page: 1
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b117
  article-title: Dynamic background modeling using deep learning autoencoder network
  publication-title: Multimedia Tools and Applications
– volume: 234
  start-page: 11
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b205
  article-title: A survey of deep neural network architectures and their applications
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.12.038
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b384
  article-title: Deep learning driven blockwise moving object detection with binary scene modeling
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.05.082
– ident: 10.1016/j.neunet.2019.04.024_b306
  doi: 10.1109/CVPR.1999.784637
– ident: 10.1016/j.neunet.2019.04.024_b405
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b309
  article-title: Unsupervised deep context prediction for background estimation and foreground segmentation
  publication-title: Machine Vision and Applications
– volume: 108
  start-page: 296
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b255
  article-title: Optimal approximation of piecewise smooth functions using deep relu neural networks
  publication-title: Neural Networks
  doi: 10.1016/j.neunet.2018.08.019
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b383
  article-title: Multiscale fully convolutional network for foreground object detection in infrared videos
  publication-title: IEEE Geoscience and Remote Sensing Letters
  doi: 10.1109/LGRS.2018.2841502
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b269
  article-title: Moving object detection through robust matrix completion augmented with objectness
  publication-title: IEEE Journal of Selected Topics in Signal Processing
  doi: 10.1109/JSTSP.2018.2869111
– ident: 10.1016/j.neunet.2019.04.024_b171
  doi: 10.1145/2647868.2654889
– ident: 10.1016/j.neunet.2019.04.024_b165
– volume: 30
  start-page: 968
  issue: 1
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b73
  article-title: Denoising adversarial autoencoders
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
  doi: 10.1109/TNNLS.2018.2852738
– ident: 10.1016/j.neunet.2019.04.024_b32
  doi: 10.1109/ICIP.2017.8297144
– start-page: 103
  year: 2012
  ident: 10.1016/j.neunet.2019.04.024_b22
  article-title: Background subtraction for visual surveillance: A fuzzy approach
– ident: 10.1016/j.neunet.2019.04.024_b368
  doi: 10.1007/978-3-030-00563-4_8
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b193
  article-title: Adaptive deep convolutional neural networks for scene-specific object detection
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– volume: 25
  start-page: 1006
  issue: 4
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b84
  article-title: A hierarchical fused Fuzzy deep neural network for data classification
  publication-title: IEEE Transactions on Fuzzy Systems
  doi: 10.1109/TFUZZ.2016.2574915
– ident: 10.1016/j.neunet.2019.04.024_b315
  doi: 10.1109/AVSS.2017.8078483
– volume: 1
  start-page: 22
  issue: 1
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b293
  article-title: Performance analysis of moving object detection using BGS techniques in visual surveillance
  publication-title: International Journal of Spatio-Temporal Data Science, Inderscience
  doi: 10.1504/IJSTDS.2019.097607
– ident: 10.1016/j.neunet.2019.04.024_b317
  doi: 10.1007/978-3-540-76856-2_31
– ident: 10.1016/j.neunet.2019.04.024_b11
– ident: 10.1016/j.neunet.2019.04.024_b132
  doi: 10.5772/38267
– ident: 10.1016/j.neunet.2019.04.024_b144
  doi: 10.1109/CVPR.2016.90
– ident: 10.1016/j.neunet.2019.04.024_b118
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b278
  article-title: Illumination-aware multi-task GANs for foreground segmentation
  publication-title: IEEE Access
– ident: 10.1016/j.neunet.2019.04.024_b395
– volume: 26
  start-page: 117
  issue: 1
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b99
  article-title: A fuzzy restricted Boltzmann machine: Novel learning algorithms based on the crisp possibilistic mean value of fuzzy numbers
  publication-title: IEEE Transactions on Fuzzy Systems
  doi: 10.1109/TFUZZ.2016.2639064
– ident: 10.1016/j.neunet.2019.04.024_b374
– ident: 10.1016/j.neunet.2019.04.024_b168
  doi: 10.1109/ICCVW.2015.123
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b134
– ident: 10.1016/j.neunet.2019.04.024_b47
  doi: 10.1109/ITSC.2004.1399038
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b252
  article-title: MSFgNet: A novel compact end-to-end deep network for moving object detection
  publication-title: IEEE Transactions on Intelligent Transportation Systems
– ident: 10.1016/j.neunet.2019.04.024_b288
  doi: 10.1109/CVPRW.2016.109
– volume: 12
  start-page: 1398
  issue: 4
  year: 2011
  ident: 10.1016/j.neunet.2019.04.024_b98
  article-title: Adaptive background modeling integrated with luminosity sensors and occlusion processing for reliable vehicle detection
  publication-title: IEEE Transactions on Intelligent Transportation Systems
  doi: 10.1109/TITS.2011.2159266
– volume: 19
  start-page: 1
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b81
  article-title: Connections with robust PCA and the role of emergent sparsity in variational autoencoder models
  publication-title: Journal of Machine Learning Research (JMLR)
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b45
– ident: 10.1016/j.neunet.2019.04.024_b158
  doi: 10.1007/978-3-319-23234-8_32
– ident: 10.1016/j.neunet.2019.04.024_b31
  doi: 10.1109/IWSSIP.2016.7502717
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b262
– ident: 10.1016/j.neunet.2019.04.024_b257
– volume: 122
  start-page: 74
  year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b302
  article-title: A texton-based kernel density estimation approach for background modeling under extreme conditions
  publication-title: Computer Vision and Image Understanding, CVIU 2014
  doi: 10.1016/j.cviu.2013.12.003
– volume: 31
  start-page: 539
  issue: 3
  year: 2009
  ident: 10.1016/j.neunet.2019.04.024_b347
  article-title: Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/TPAMI.2008.87
– ident: 10.1016/j.neunet.2019.04.024_b328
– ident: 10.1016/j.neunet.2019.04.024_b388
  doi: 10.1007/978-3-642-35286-7_23
– ident: 10.1016/j.neunet.2019.04.024_b299
  doi: 10.1007/978-3-319-23222-5_62
– volume: 65
  start-page: 677
  issue: 2
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b385
  article-title: Memristor-based circuit design for multilayer neural networks
  publication-title: IEEE Transactions on Circuits and Systems. I. Regular Papers
  doi: 10.1109/TCSI.2017.2729787
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b60
– volume: 17
  start-page: 1168
  issue: 7
  year: 2008
  ident: 10.1016/j.neunet.2019.04.024_b213
  article-title: A self organizing approach to background subtraction for visual surveillance applications
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2008.924285
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b97
– start-page: 57
  year: 2008
  ident: 10.1016/j.neunet.2019.04.024_b212
  article-title: Neural model-based segmentation of image motion
  publication-title: KES 2008
– ident: 10.1016/j.neunet.2019.04.024_b170
– ident: 10.1016/j.neunet.2019.04.024_b336
  doi: 10.1109/CVPRW.2014.68
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b338
– year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b221
  article-title: Background model initialization for static Cameras
– volume: 26
  start-page: 5244
  issue: 11
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b174
  article-title: Extensive benchmark and survey of modeling methods for scene background initialization
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2017.2728181
– ident: 10.1016/j.neunet.2019.04.024_b163
  doi: 10.1109/ICPR.2016.7899619
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b360
– ident: 10.1016/j.neunet.2019.04.024_b9
  doi: 10.1109/MWSCAS.2018.8623825
– ident: 10.1016/j.neunet.2019.04.024_b204
  doi: 10.1109/ICIP.2018.8451816
– ident: 10.1016/j.neunet.2019.04.024_b152
– ident: 10.1016/j.neunet.2019.04.024_b198
  doi: 10.1007/978-3-030-00776-8_48
– volume: 26
  start-page: 1702
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b337
  article-title: Supervised speech separation based on deep learning: An overview
  publication-title: IEEE/ACM Transactions on Audio, Speech, and Language Processing
  doi: 10.1109/TASLP.2018.2842159
– volume: 27
  start-page: 457
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b350
  article-title: Combining spectral and spatial features for deep learning based blind speaker separation
  publication-title: IEEE/ACM Transactions on Audio, Speech, and Language Processing
  doi: 10.1109/TASLP.2018.2881912
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b298
  article-title: Very deep convolutional networks for large-scale image recognition
  publication-title: International Conference on Learning Representation, ICLR 2015
– volume: 35
  start-page: 872
  issue: 8
  year: 2013
  ident: 10.1016/j.neunet.2019.04.024_b33
  article-title: Invariant scattering convolution networks
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/TPAMI.2012.230
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b393
– volume: 118
  start-page: 14
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b373
  article-title: A review of convolutional-neural-network-based action recognition
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2018.05.018
– ident: 10.1016/j.neunet.2019.04.024_b53
– ident: 10.1016/j.neunet.2019.04.024_b231
  doi: 10.1007/11553595_20
– ident: 10.1016/j.neunet.2019.04.024_b292
  doi: 10.1109/ICCV.2017.548
– ident: 10.1016/j.neunet.2019.04.024_b313
– ident: 10.1016/j.neunet.2019.04.024_b89
  doi: 10.1109/CVPR.2017.452
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b52
– start-page: 1
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b87
  article-title: Background subtraction based on deep convolutional neural networks features
  publication-title: Multimedia Tools and Applications
– ident: 10.1016/j.neunet.2019.04.024_b253
  doi: 10.1109/WACV.2019.00193
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b330
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b256
  article-title: Compressive online video background–Foreground separation using multiple prior information and optical flow
  publication-title: MDPI Journal of Imaging
  doi: 10.3390/jimaging4070090
– volume: 26
  start-page: 5840
  issue: 12
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b166
  article-title: Background-foreground modeling based on spatio-temporal sparse subspace clustering
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2017.2746268
– ident: 10.1016/j.neunet.2019.04.024_b272
  doi: 10.1007/978-3-319-24574-4_28
– ident: 10.1016/j.neunet.2019.04.024_b353
  doi: 10.1109/CIS.2009.178
– ident: 10.1016/j.neunet.2019.04.024_b206
  doi: 10.1109/CVPR.2015.7298965
– ident: 10.1016/j.neunet.2019.04.024_b327
  doi: 10.1109/AVSS.2013.6636617
– ident: 10.1016/j.neunet.2019.04.024_b182
– volume: 23
  start-page: 294
  issue: 1
  year: 2004
  ident: 10.1016/j.neunet.2019.04.024_b3
  article-title: Interactive digital photomontage
  publication-title: ACM Transactions on Graphics
  doi: 10.1145/1015706.1015718
– ident: 10.1016/j.neunet.2019.04.024_b56
  doi: 10.1145/3194554
– ident: 10.1016/j.neunet.2019.04.024_b121
  doi: 10.1007/978-3-319-70742-6_23
– ident: 10.1016/j.neunet.2019.04.024_b265
  doi: 10.1109/IJCNN.2013.6706737
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b390
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b104
– ident: 10.1016/j.neunet.2019.04.024_b76
– ident: 10.1016/j.neunet.2019.04.024_b324
– ident: 10.1016/j.neunet.2019.04.024_b140
– ident: 10.1016/j.neunet.2019.04.024_b340
  doi: 10.1109/CVPRW.2014.126
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b8
  article-title: sEnDec: An improved image to image CNN for foreground localization
  publication-title: IEEE Intelligent Transportation Systems Transactions
– ident: 10.1016/j.neunet.2019.04.024_b136
  doi: 10.1007/978-3-642-33765-9_8
– volume: 19
  start-page: 780
  issue: 7
  year: 1997
  ident: 10.1016/j.neunet.2019.04.024_b359
  article-title: Pfinder: Real-time tracking of the human body
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/34.598236
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b27
  article-title: Scene background initialization: a taxonomy
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2016.12.024
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b10
  article-title: A deep convolutional neural network for background subtraction
  publication-title: Pattern Recognition
– ident: 10.1016/j.neunet.2019.04.024_b366
  doi: 10.1145/2647868.2654914
– ident: 10.1016/j.neunet.2019.04.024_b195
  doi: 10.1109/AVSS.2013.6636673
– volume: 4729
  start-page: 181
  year: 2007
  ident: 10.1016/j.neunet.2019.04.024_b210
  article-title: A self-organizing approach to detection of moving patterns for real-time applications
  publication-title: Advances in Brain, Vision, and Artificial Intelligence
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b351
  article-title: Foreground detection with deeply learned multi-scale spatial-temporal features
  publication-title: MDPI Sensors
  doi: 10.3390/s18124269
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b107
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b259
– ident: 10.1016/j.neunet.2019.04.024_b401
  doi: 10.1145/3097983.3098052
– ident: 10.1016/j.neunet.2019.04.024_b318
  doi: 10.1007/11919476_5
– volume: 97
  start-page: 162
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b344
  article-title: Visualizing deep neural network by alternately image blurring and deblurring
  publication-title: Neural Networks
  doi: 10.1016/j.neunet.2017.09.007
– start-page: 1
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b279
  article-title: End-to-end video background subtraction with 3D convolutional neural networks
  publication-title: Multimedia Tools and Applications
– ident: 10.1016/j.neunet.2019.04.024_b348
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b181
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b307
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b248
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b349
  article-title: Robust hierarchical deep learning for vehicular management
  publication-title: IEEE Transactions on Vehicular Technology
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b185
  article-title: A method based on motion detection for generating the background of a scene
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2016.11.022
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b392
  article-title: Stacked multi-layer self-organizing map for background modeling
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2015.2427519
– volume: 27
  start-page: 773
  issue: 7
  year: 2006
  ident: 10.1016/j.neunet.2019.04.024_b406
  article-title: Efficient adaptive density estimation per image pixel for the task of background subtraction
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2005.11.005
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b57
– ident: 10.1016/j.neunet.2019.04.024_b296
  doi: 10.1109/ICPR.2016.7899965
– volume: 15
  issue: 1
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b232
  article-title: On the implicit bias of dropout
  publication-title: International Conference on Machine Learning, ICML 2018
– volume: 64
  start-page: 739
  issue: 8
  year: 2010
  ident: 10.1016/j.neunet.2019.04.024_b361
  article-title: Spatio-temporal context for codebook-based dynamic background subtraction
  publication-title: AEU-International Journal of Electronic Communication
  doi: 10.1016/j.aeue.2009.05.004
– ident: 10.1016/j.neunet.2019.04.024_b63
– ident: 10.1016/j.neunet.2019.04.024_b139
– volume: 4
  start-page: 79
  issue: 6
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b123
  article-title: Deep learning with a spatiotemporal descriptor of appearance and motion estimation for video anomaly detection
  publication-title: MDPI Journal of Imaging
  doi: 10.3390/jimaging4060079
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b397
  article-title: Background subtraction algorithm based on Bayesian generative adversarial networks
  publication-title: Acta Automatica Sinica
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b263
  article-title: Self-adaptive SOM-CNN neural system for dynamic object detection in normal and complex scenarios
  publication-title: Pattern Recognition
  doi: 10.1016/j.patcog.2014.09.009
– ident: 10.1016/j.neunet.2019.04.024_b258
  doi: 10.1109/ICAIPR.2016.7585207
– ident: 10.1016/j.neunet.2019.04.024_b141
  doi: 10.1109/CVPR.2016.90
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b380
– ident: 10.1016/j.neunet.2019.04.024_b211
  doi: 10.1007/978-3-540-87536-9_67
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b370
– volume: 29
  start-page: 2123
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b310
  article-title: Deep restricted kernel machines using conjugate feature duality
  publication-title: Neural Computation
  doi: 10.1162/neco_a_00984
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b290
  article-title: Stochasticnet: Forming deep neural networks via stochastic connectivity
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2016.2551458
– volume: 57
  start-page: 3
  issue: 1
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b352
  article-title: GETNET: A general end-to-end 2-d CNN framework for hyperspectral image change detection
  publication-title: IEEE Transactions on Geoscience and Remote Sensing
  doi: 10.1109/TGRS.2018.2849692
– ident: 10.1016/j.neunet.2019.04.024_b2
  doi: 10.1109/ICIP.2018.8451540
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b394
– ident: 10.1016/j.neunet.2019.04.024_b111
  doi: 10.1109/CVPR.2014.81
– ident: 10.1016/j.neunet.2019.04.024_b266
– ident: 10.1016/j.neunet.2019.04.024_b74
  doi: 10.1109/ICIP.2010.5653489
– year: 1957
  ident: 10.1016/j.neunet.2019.04.024_b275
– volume: 9
  start-page: 1735
  issue: 8
  year: 1997
  ident: 10.1016/j.neunet.2019.04.024_b148
  article-title: Long short-term memory
  publication-title: Neural Computation
  doi: 10.1162/neco.1997.9.8.1735
– ident: 10.1016/j.neunet.2019.04.024_b176
  doi: 10.1109/SIU.2018.8404636
– start-page: 165
  year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b261
  article-title: Background scene modeling for PTZ cameras using RBM
  publication-title: International Conference on Control, Automation and Information Sciences, ICCAIS 2014
– ident: 10.1016/j.neunet.2019.04.024_b243
– year: 2010
  ident: 10.1016/j.neunet.2019.04.024_b86
  article-title: Adaptive learning of multi-subspace for foreground detection under illumination changes
  publication-title: Computer Vision and Image Understanding
– ident: 10.1016/j.neunet.2019.04.024_b127
– volume: 107
  start-page: 3
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b91
  article-title: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning
  publication-title: Neural Networks
  doi: 10.1016/j.neunet.2017.12.012
– ident: 10.1016/j.neunet.2019.04.024_b154
  doi: 10.1109/ICCV.2009.5459202
– ident: 10.1016/j.neunet.2019.04.024_b149
  doi: 10.1109/CVPRW.2012.6238925
– ident: 10.1016/j.neunet.2019.04.024_b106
  doi: 10.1007/978-3-030-00374-6_32
– ident: 10.1016/j.neunet.2019.04.024_b291
  doi: 10.1109/ISIE.2017.8001492
– volume: 28
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b230
  article-title: New trends on moving object detection in video images Captured by a moving Camera: A survey
  publication-title: Computer Science Review
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b156
– ident: 10.1016/j.neunet.2019.04.024_b116
– ident: 10.1016/j.neunet.2019.04.024_b119
  doi: 10.1109/ICASSP.2013.6638947
– year: 2013
  ident: 10.1016/j.neunet.2019.04.024_b179
– ident: 10.1016/j.neunet.2019.04.024_b44
  doi: 10.1109/IJCNN.2013.6706734
– ident: 10.1016/j.neunet.2019.04.024_b110
  doi: 10.1109/ICCV.2015.169
– volume: 1
  start-page: 137
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b355
  article-title: Fully memristive neural networks for pattern classification with unsupervised learning
  publication-title: Nature Electronics
  doi: 10.1038/s41928-018-0023-2
– ident: 10.1016/j.neunet.2019.04.024_b184
  doi: 10.1109/ICPR.2016.7899617
– ident: 10.1016/j.neunet.2019.04.024_b13
  doi: 10.1007/978-3-540-89639-5_74
– volume: 97
  start-page: 173
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b19
  article-title: Deep neural networks for texture classification: A theoretical analysis
  publication-title: Neural Networks
  doi: 10.1016/j.neunet.2017.10.001
– ident: 10.1016/j.neunet.2019.04.024_b58
  doi: 10.1145/3061639.3062326
– volume: 78
  start-page: 1415
  issue: 9
  year: 1990
  ident: 10.1016/j.neunet.2019.04.024_b358
  article-title: 30 years of adaptive neural networks: perceptron, madaline, and backpropagation
  publication-title: Proceedings of the IEEE
  doi: 10.1109/5.58323
– ident: 10.1016/j.neunet.2019.04.024_b321
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b294
  article-title: Background subtraction using Gaussian−bernoulli restricted Boltzmann machine
  publication-title: IET Image Processing
  doi: 10.1049/iet-ipr.2017.1055
– year: 2011
  ident: 10.1016/j.neunet.2019.04.024_b209
  article-title: Online robust dictionary learning
  publication-title: EURASIP Journal on Image and Video Processing, IVP 2011
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b343
  article-title: Scene classification with recurrent attention of VHR remote sensing images
  publication-title: IEEE Transactions on Geoscience and Remote Sensing
  doi: 10.1109/LGRS.2018.2859024
– volume: 20
  start-page: 1709
  issue: 6
  year: 2011
  ident: 10.1016/j.neunet.2019.04.024_b17
  article-title: ViBe: A universal background subtraction algorithm for video sequences
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2010.2101613
– ident: 10.1016/j.neunet.2019.04.024_b254
  doi: 10.1109/SMC.2018.00289
– volume: 23
  start-page: 1
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b29
  article-title: Decomposition into low-rank plus additive matrices for background/foreground separation: A review for a comparative evaluation with a large-scale dataset
  publication-title: Computer Science Review
  doi: 10.1016/j.cosrev.2016.11.001
– ident: 10.1016/j.neunet.2019.04.024_b241
– start-page: 14
  year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b196
  article-title: Robust object detection in severe imaging conditions using co-occurrence background model
  publication-title: International Journal of Optomechatronics
  doi: 10.1080/15599612.2014.890686
– volume: 60
  issue: 1
  year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b242
  article-title: The detection of moving objects in video by background subtraction using dempster-shafer theory
  publication-title: Transactions on Electronics and Communications
– ident: 10.1016/j.neunet.2019.04.024_b301
  doi: 10.1109/ICCVW.2015.125
– ident: 10.1016/j.neunet.2019.04.024_b378
– volume: 4
  issue: 7
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b186
  article-title: Labgen-p-semantic: A first step for leveraging semantic segmentation in background generation
  publication-title: MDPI Journal of Imaging
– ident: 10.1016/j.neunet.2019.04.024_b214
  doi: 10.1007/978-3-642-02282-1_33
– ident: 10.1016/j.neunet.2019.04.024_b239
  doi: 10.1109/CVPR.2018.00084
– start-page: 1
  year: 2008
  ident: 10.1016/j.neunet.2019.04.024_b335
  article-title: Improving target detection by coupling it with tracking
  publication-title: Machine Vision and Application
– start-page: 16010
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b381
  article-title: Background subtraction using multiscale fully convolutional network
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2018.2817129
– ident: 10.1016/j.neunet.2019.04.024_b64
  doi: 10.1109/IJCNN.2011.6033261
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b226
  article-title: Self-organizing background subtraction using color and depth data
  publication-title: Multimedia Tools and Applications
– volume: 29
  start-page: 1421
  year: 1996
  ident: 10.1016/j.neunet.2019.04.024_b285
  article-title: A system for counting people in video images using neural networks to identify the background scene
  publication-title: Pattern Recognition
  doi: 10.1016/0031-3203(95)00163-8
– volume: 71
  start-page: 1
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b379
  article-title: A robust background initialization algorithm with superpixel motion detection
  publication-title: Signal Processing: Image Communication
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b55
– ident: 10.1016/j.neunet.2019.04.024_b62
– ident: 10.1016/j.neunet.2019.04.024_b236
  doi: 10.1109/CVPR.2017.17
– volume: 35
  start-page: 597
  year: 2013
  ident: 10.1016/j.neunet.2019.04.024_b403
  article-title: Moving object detection by detecting contiguous outliers in the low-rank representation
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/TPAMI.2012.132
– volume: 112
  start-page: 256
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b202
  article-title: Foreground segmentation using convolutional neural networks for multiscale feature encoding
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2018.08.002
– volume: 35
  start-page: 32
  issue: 4
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b329
  article-title: Robust subspace learning: Robust PCA, robust subspace tracking and robust subspace recovery
  publication-title: IEEE Signal Processing Magazine
  doi: 10.1109/MSP.2018.2826566
– year: 2013
  ident: 10.1016/j.neunet.2019.04.024_b93
  article-title: Finite asymmetric generalized Gaussian mixture models learning for infrared object detection
  publication-title: Computer Vision and Image Understanding
  doi: 10.1016/j.cviu.2013.07.007
– ident: 10.1016/j.neunet.2019.04.024_b49
  doi: 10.1109/ICCVW.2017.188
– ident: 10.1016/j.neunet.2019.04.024_b115
– ident: 10.1016/j.neunet.2019.04.024_b228
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b331
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b283
– ident: 10.1016/j.neunet.2019.04.024_b128
  doi: 10.1007/978-3-319-10584-0_35
– volume: 24
  start-page: 723
  issue: 5
  year: 2013
  ident: 10.1016/j.neunet.2019.04.024_b219
  article-title: Stopped object detection by learning foreground model in videos
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
  doi: 10.1109/TNNLS.2013.2242092
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b289
  article-title: Real-time embedded motion detection via neural response mixture modeling
  publication-title: Journal of Signal Processing Systems
– volume: 110
  start-page: 104
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b399
  article-title: ADA-Tucker: Compressing deep neural networks via adaptive dimension adjustment tucker decomposition, neural networks
  publication-title: Neural Networks
  doi: 10.1016/j.neunet.2018.10.016
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b7
  article-title: An improved video foreground extraction strategy using multi-view receptive field and EnDec CNN
  publication-title: IEEE Transactions on Industrial Informatics
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b398
  article-title: A novel background subtraction algorithm based on parallel vision and Bayesian GANs
  publication-title: Neurocomputing
– volume: 2
  start-page: 1034
  year: 2005
  ident: 10.1016/j.neunet.2019.04.024_b66
  article-title: Background estimation as a labeling problem
  publication-title: International Conference on Computer Vision, ICCV 2005
– volume: 25
  start-page: 1
  year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b36
  article-title: DehazeNet: AN end-to-end system for single image haze removal
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2016.2598681
– ident: 10.1016/j.neunet.2019.04.024_b138
  doi: 10.1109/IJCNN.2017.7966300
– ident: 10.1016/j.neunet.2019.04.024_b363
  doi: 10.1109/CVPR.2018.00125
– volume: 26
  start-page: 3249
  issue: 7
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b277
  article-title: Universal multimode background subtraction
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2017.2695882
– ident: 10.1016/j.neunet.2019.04.024_b142
  doi: 10.1109/ICCV.2015.123
– ident: 10.1016/j.neunet.2019.04.024_b215
  doi: 10.1007/978-3-642-04146-4_63
– ident: 10.1016/j.neunet.2019.04.024_b41
  doi: 10.1109/AVSS.2018.8639077
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b113
– ident: 10.1016/j.neunet.2019.04.024_b67
  doi: 10.1109/CVPR.2016.517
– ident: 10.1016/j.neunet.2019.04.024_b124
  doi: 10.1109/ICSPCC.2012.6335632
– ident: 10.1016/j.neunet.2019.04.024_b129
  doi: 10.1109/ICIP.2012.6467087
– ident: 10.1016/j.neunet.2019.04.024_b183
  doi: 10.1109/AVSS.2010.45
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b4
– year: 2012
  ident: 10.1016/j.neunet.2019.04.024_b94
  article-title: Online variational learning of finite Dirichlet mixture models
  publication-title: Evolving Systems
  doi: 10.1007/s12530-012-9047-4
– year: 1962
  ident: 10.1016/j.neunet.2019.04.024_b357
  article-title: Generalization and information storage in networks of ADALINE
  publication-title: Self Organizing Systems
– ident: 10.1016/j.neunet.2019.04.024_b95
– ident: 10.1016/j.neunet.2019.04.024_b320
  doi: 10.24963/ijcai.2018/378
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b187
  article-title: Survey on deep learning techniques for person re-identification task
  publication-title: Neurocomputing
– volume: 58
  issue: 3
  year: 2011
  ident: 10.1016/j.neunet.2019.04.024_b40
  article-title: Robust principal component analysis?
  publication-title: International Journal of ACM
– ident: 10.1016/j.neunet.2019.04.024_b61
  doi: 10.1109/ICPR.2018.8545597
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b199
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b75
  article-title: Labeled dataset for integral evaluation of moving object detection algorithms: LASIESTA
  publication-title: Computer Vision and Image Understanding
  doi: 10.1016/j.cviu.2016.08.005
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b376
– ident: 10.1016/j.neunet.2019.04.024_b143
  doi: 10.1109/ICCV.2015.123
– ident: 10.1016/j.neunet.2019.04.024_b137
  doi: 10.1109/ICPR.2016.7899616
– ident: 10.1016/j.neunet.2019.04.024_b311
  doi: 10.1109/CVPR.2016.308
– volume: 14
  start-page: 115
  issue: 1
  year: 1994
  ident: 10.1016/j.neunet.2019.04.024_b18
  article-title: Approximation and estimation bounds for artificial neural networks
  publication-title: Neural Networks
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b246
  article-title: Change detection by training a triplet network for motion feature extraction
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b356
  article-title: Scene-specific convolutional neural networks for video-based biodiversity detection
  publication-title: Methods in Ecology and Evolution
  doi: 10.1111/2041-210X.13011
– ident: 10.1016/j.neunet.2019.04.024_b312
  doi: 10.1109/CVPR.2015.7298594
– start-page: 1
  year: 2010
  ident: 10.1016/j.neunet.2019.04.024_b217
  article-title: A fuzzy spatial coherence-based approach to background/foreground separation for moving object detection
  publication-title: Neural Computing and Applications, NCA 2010
– ident: 10.1016/j.neunet.2019.04.024_b268
  doi: 10.1109/ICCVW.2017.221
– ident: 10.1016/j.neunet.2019.04.024_b35
  doi: 10.1109/CVPR.2017.565
– ident: 10.1016/j.neunet.2019.04.024_b178
  doi: 10.1109/AVSS.2017.8078475
– year: 2005
  ident: 10.1016/j.neunet.2019.04.024_b316
  article-title: Foreground-background segmentation in video sequences using neural networks
  publication-title: Intelligent Systems: Neural Networks and Applications
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b153
  article-title: 3D atrous convolutional long short-term memory network for background subtraction
  publication-title: IEEE Access
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b264
  article-title: Temporal weighted learning model for background estimation with an automatic re-initialization stage and adaptive parameters update
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2017.01.011
– volume: 18
  start-page: 1527
  issue: 7
  year: 2006
  ident: 10.1016/j.neunet.2019.04.024_b147
  article-title: A fast learning algorithm for deep belief nets
  publication-title: Neural Computation
  doi: 10.1162/neco.2006.18.7.1527
– ident: 10.1016/j.neunet.2019.04.024_b160
  doi: 10.1049/ic.2015.0105
– ident: 10.1016/j.neunet.2019.04.024_b235
  doi: 10.1109/CVPR.2004.1315179
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b245
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b54
  article-title: Pixel-wise deep sequence learning for moving object detection
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b287
– ident: 10.1016/j.neunet.2019.04.024_b274
  doi: 10.1109/ICPR.2008.4761047
– ident: 10.1016/j.neunet.2019.04.024_b216
  doi: 10.1007/978-3-642-04697-1_39
– ident: 10.1016/j.neunet.2019.04.024_b38
– volume: 46
  start-page: 1014
  issue: 4
  year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b42
  article-title: Total variation regularized RPCA for irregularly moving object detection under dynamic background
  publication-title: IEEE Transactions on Cybernetics
  doi: 10.1109/TCYB.2015.2419737
– ident: 10.1016/j.neunet.2019.04.024_b334
– ident: 10.1016/j.neunet.2019.04.024_b175
  doi: 10.1109/TVCG.2018.2864500
– volume: 23
  start-page: 1083
  issue: 6
  year: 2012
  ident: 10.1016/j.neunet.2019.04.024_b96
  article-title: Background subtraction via incremental maximum margin criterion: A discriminative approach
  publication-title: Machine Vision and Applications
  doi: 10.1007/s00138-012-0421-9
– ident: 10.1016/j.neunet.2019.04.024_b229
– ident: 10.1016/j.neunet.2019.04.024_b377
  doi: 10.1609/aaai.v33i01.33019176
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b167
  article-title: Robust background subtraction to global illumination changes via multiple features based OR-PCA with MRF
  publication-title: Journal of Electronic Imaging
  doi: 10.1117/1.JEI.24.4.043011
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b50
  article-title: Deep, landmark-free FAME: Face alignment, modeling, and expression estimation
  publication-title: International Journal of Computer Vision
  doi: 10.1007/s11263-019-01151-x
– ident: 10.1016/j.neunet.2019.04.024_b367
  doi: 10.1109/ICME.2014.6890140
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b85
– volume: 70
  start-page: 41
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b105
  article-title: A survey on deep learning techniques for image and video semantic segmentation
  publication-title: Applied Soft Computing
  doi: 10.1016/j.asoc.2018.05.018
– ident: 10.1016/j.neunet.2019.04.024_b295
  doi: 10.5220/0005266303950402
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b164
  article-title: Spatiotemporal low-rank modeling for complex scene background initialization
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– ident: 10.1016/j.neunet.2019.04.024_b273
– volume: 13
  start-page: 1459
  issue: 11
  year: 2004
  ident: 10.1016/j.neunet.2019.04.024_b191
  article-title: Statistical modeling of complex background for foreground object detection
  publication-title: IEEE Transaction on Image Processing
  doi: 10.1109/TIP.2004.836169
– ident: 10.1016/j.neunet.2019.04.024_b12
– ident: 10.1016/j.neunet.2019.04.024_b323
  doi: 10.1109/ICCV.1999.791228
– ident: 10.1016/j.neunet.2019.04.024_b83
  doi: 10.1109/CVPR.2009.5206848
– volume: 39
  start-page: 1137
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b267
  article-title: Faster R-CNN: Towards real-time object detection with region proposal networks
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/TPAMI.2016.2577031
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b362
  article-title: Deep learning-based methods for person re-identification: A comprehensive review
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2019.01.079
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b65
– ident: 10.1016/j.neunet.2019.04.024_b203
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b208
  article-title: Tensor robust principal component analysis with a new tensor nuclear norm
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– volume: 11
  issue: 31–66
  year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b23
  article-title: Traditional and recent approaches in background modeling for foreground detection: An overview
  publication-title: Computer Science Review
– ident: 10.1016/j.neunet.2019.04.024_b6
  doi: 10.1109/Cybermatics_2018.2018.00093
– ident: 10.1016/j.neunet.2019.04.024_b238
– ident: 10.1016/j.neunet.2019.04.024_b387
  doi: 10.1007/11881599_110
– ident: 10.1016/j.neunet.2019.04.024_b103
  doi: 10.1109/ICPR.2018.8545320
– ident: 10.1016/j.neunet.2019.04.024_b300
  doi: 10.1109/AVSS.2015.7301753
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b400
– ident: 10.1016/j.neunet.2019.04.024_b70
– year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b282
  article-title: Automatic fish detection in underwater videos by a deep neural network-based hybrid motion learning system
  publication-title: ICES Journal of Marine Science
– ident: 10.1016/j.neunet.2019.04.024_b20
  doi: 10.1109/TENCONSpring.2016.7519418
– volume: 48
  start-page: 1374
  issue: 4
  year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b194
  article-title: Co-occurrence probability based pixel pairs background model for robust object detection in dynamic scenes
  publication-title: Pattern Recognition
  doi: 10.1016/j.patcog.2014.10.020
– ident: 10.1016/j.neunet.2019.04.024_b71
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b332
– ident: 10.1016/j.neunet.2019.04.024_b249
  doi: 10.1007/3-540-49256-9_16
– ident: 10.1016/j.neunet.2019.04.024_b372
  doi: 10.1109/VCIP.2016.7805552
– year: 2007
  ident: 10.1016/j.neunet.2019.04.024_b146
  article-title: Deep belief nets
  publication-title: NIPS Tutorial
– year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b100
  article-title: Background subtraction model based on color and depth cues
  publication-title: Machine Vision and Applications
  doi: 10.1007/s00138-013-0562-5
– year: 2012
  ident: 10.1016/j.neunet.2019.04.024_b250
  article-title: Simultaneous video stabilization and moving object detection in turbulence
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI 2012
– ident: 10.1016/j.neunet.2019.04.024_b304
  doi: 10.1109/CVPRW.2014.67
– volume: 20
  start-page: 273
  issue: 3
  year: 1995
  ident: 10.1016/j.neunet.2019.04.024_b72
  article-title: Support-vector networks
  publication-title: Machine Learning
  doi: 10.1007/BF00994018
– volume: 55
  start-page: 1
  issue: 1
  year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b271
  article-title: Incremental principal component pursuit for video background modeling
  publication-title: Journal of Mathematical Imaging and Vision
  doi: 10.1007/s10851-015-0610-z
– ident: 10.1016/j.neunet.2019.04.024_b224
  doi: 10.1007/978-3-319-70742-6_24
– ident: 10.1016/j.neunet.2019.04.024_b375
– ident: 10.1016/j.neunet.2019.04.024_b120
  doi: 10.1007/978-3-319-23222-5_60
– ident: 10.1016/j.neunet.2019.04.024_b341
– volume: 122
  start-page: 22
  year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b30
  article-title: Robust PCA via principal component pursuit: A review for a comparative evaluation in video surveillance
  publication-title: Special Issue on Background Models Challenge, Computer Vision and Image Understanding, CVIU 2014
– start-page: 315
  year: 2002
  ident: 10.1016/j.neunet.2019.04.024_b189
  article-title: Background estimation for video surveillance
  publication-title: Image and Vision Computing New Zealand, IVCNZ 2002
– ident: 10.1016/j.neunet.2019.04.024_b222
  doi: 10.1007/978-3-319-23222-5_57
– volume: 300
  start-page: 17
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b34
  article-title: Computer vision and deep learning techniques for pedestrian detection and tracking: A survey
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.01.092
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b21
– year: 2015
  ident: 10.1016/j.neunet.2019.04.024_b101
– volume: 19
  start-page: 254
  issue: 1
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b371
  article-title: Deep background modeling using fully convolutional network
  publication-title: IEEE Transactions on Intelligent Transportation Systems
  doi: 10.1109/TITS.2017.2754099
– year: 2011
  ident: 10.1016/j.neunet.2019.04.024_b391
  article-title: Background subtraction via robust dictionary learning
  publication-title: EURASIP Journal on Image and Video Processing, IVP 2011
  doi: 10.1155/2011/972961
– ident: 10.1016/j.neunet.2019.04.024_b112
– ident: 10.1016/j.neunet.2019.04.024_b82
– ident: 10.1016/j.neunet.2019.04.024_b15
  doi: 10.1109/ICOMIS.2018.8644960
– volume: 2
  start-page: 303
  issue: 4
  year: 1989
  ident: 10.1016/j.neunet.2019.04.024_b79
  article-title: Approximation by superpositions of a sigmoidal function
  publication-title: Mathematics of Control Signals and Systems
  doi: 10.1007/BF02551274
– ident: 10.1016/j.neunet.2019.04.024_b305
  doi: 10.1109/WACV.2015.137
– volume: 1
  start-page: 265
  issue: 2
  year: 2009
  ident: 10.1016/j.neunet.2019.04.024_b25
  article-title: Modeling of dynamic backgrounds by type-2 Fuzzy Gaussians mixture models
  publication-title: MASAUM Journal of Basic and Applied Sciences
– volume: 15
  start-page: 1929
  year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b303
  article-title: Dropout: A simple way to prevent neural networks from overfitting
  publication-title: Journal of Machine Learning Research (JMLR)
– ident: 10.1016/j.neunet.2019.04.024_b48
  doi: 10.1609/aaai.v32i1.11668
– ident: 10.1016/j.neunet.2019.04.024_b200
  doi: 10.1109/AVSS.2017.8078547
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b90
– ident: 10.1016/j.neunet.2019.04.024_b218
  doi: 10.1109/CVPRW.2012.6238922
– ident: 10.1016/j.neunet.2019.04.024_b386
– ident: 10.1016/j.neunet.2019.04.024_b130
  doi: 10.1007/978-3-642-31295-3_14
– year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b24
  article-title: Traditional approaches in background modeling for video surveillance
– ident: 10.1016/j.neunet.2019.04.024_b188
– year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b37
  article-title: Advanced background modeling with RGB-D sensors through classifiers combination and inter-frame foreground prediction
  publication-title: Machine Vision and Applications
– ident: 10.1016/j.neunet.2019.04.024_b39
  doi: 10.1007/978-3-319-70742-6_21
– ident: 10.1016/j.neunet.2019.04.024_b108
  doi: 10.1109/ICIP.2015.7350841
– ident: 10.1016/j.neunet.2019.04.024_b177
– ident: 10.1016/j.neunet.2019.04.024_b68
– ident: 10.1016/j.neunet.2019.04.024_b172
  doi: 10.1609/aaai.v30i1.10274
– ident: 10.1016/j.neunet.2019.04.024_b80
– ident: 10.1016/j.neunet.2019.04.024_b308
– volume: 28
  start-page: 26
  year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b28
  article-title: On the role and the importance of features for background modeling and foreground detection
  publication-title: Computer Science Review
  doi: 10.1016/j.cosrev.2018.01.004
– ident: 10.1016/j.neunet.2019.04.024_b251
  doi: 10.1109/CVPR.2016.278
– volume: 28
  start-page: 013038
  issue: 1
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b46
  article-title: Deep learning-based scene-awareness approach for intelligent change detection in videos
  publication-title: Journal of Electronic Imaging
  doi: 10.1117/1.JEI.28.1.013038
– ident: 10.1016/j.neunet.2019.04.024_b192
  doi: 10.1109/SNSP.2018.00089
– volume: 27
  start-page: 178
  year: 2019
  ident: 10.1016/j.neunet.2019.04.024_b354
  article-title: Robust speaker localization guided by deep learning-based time-frequency masking
  publication-title: IEEE/ACM Transactions on Audio, Speech, and Language Processing
  doi: 10.1109/TASLP.2018.2876169
– volume: 5
  start-page: 115
  year: 1943
  ident: 10.1016/j.neunet.2019.04.024_b77
  article-title: A logical calculus of the ideas immanent in nervous activity
  publication-title: Bulletin of Mathematical Biophysics
  doi: 10.1007/BF02478259
– ident: 10.1016/j.neunet.2019.04.024_b365
  doi: 10.1609/aaai.v29i1.9481
– year: 2016
  ident: 10.1016/j.neunet.2019.04.024_b59
  article-title: Interval-valued model level Fuzzy aggregation-based background subtraction
  publication-title: IEEE Transactions on Cybernetics
– ident: 10.1016/j.neunet.2019.04.024_b26
  doi: 10.1016/j.cosrev.2019.100204
– ident: 10.1016/j.neunet.2019.04.024_b114
  doi: 10.1109/ICIP.2011.6116367
– ident: 10.1016/j.neunet.2019.04.024_b319
– ident: 10.1016/j.neunet.2019.04.024_b227
– volume: 7441
  start-page: 14
  year: 2012
  ident: 10.1016/j.neunet.2019.04.024_b102
  article-title: An introduction to restricted Boltzmann machines
  publication-title: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
  doi: 10.1007/978-3-642-33275-3_2
– volume: 122
  start-page: 65
  year: 2014
  ident: 10.1016/j.neunet.2019.04.024_b220
  article-title: The 3dSOBS+ algorithm for moving object detection
  publication-title: Computer Vision and Image Understanding, CVIU 2014
  doi: 10.1016/j.cviu.2013.11.006
– ident: 10.1016/j.neunet.2019.04.024_b342
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b297
  article-title: Superpixel-based online wagging one-class ensemble for feature selection in background/foreground separation
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2017.10.034
– ident: 10.1016/j.neunet.2019.04.024_b69
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b225
  article-title: Background subtraction for moving object detection in RGB-D data: A survey
  publication-title: MDPI Journal of Imaging
  doi: 10.3390/jimaging4050071
– ident: 10.1016/j.neunet.2019.04.024_b16
  doi: 10.1109/ICIP.2018.8451603
– ident: 10.1016/j.neunet.2019.04.024_b244
  doi: 10.1109/ICASSP.2018.8461540
– ident: 10.1016/j.neunet.2019.04.024_b389
  doi: 10.1109/ICME.2018.8486510
– ident: 10.1016/j.neunet.2019.04.024_b322
  doi: 10.1109/WMVC.2009.5399242
– volume: 10
  start-page: 40
  year: 2007
  ident: 10.1016/j.neunet.2019.04.024_b51
  article-title: Efficient hierarchical method for background subtraction
  publication-title: Pattern Recognition
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b201
– volume: 34
  start-page: 014004
  issue: 1
  year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b133
  article-title: Stable architectures for deep neural networks
  publication-title: Inverse Problems
  doi: 10.1088/1361-6420/aa9a90
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b276
  article-title: Real-time adaptive histogram min-max bucket (HMMB) model for background subtraction
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– year: 2017
  ident: 10.1016/j.neunet.2019.04.024_b237
– year: 2013
  ident: 10.1016/j.neunet.2019.04.024_b364
  article-title: GOSUS: Grassmannian online subspace updates with structured-sparsity
  publication-title: International Conference on Computer Vision, ICCV 2013
  doi: 10.1109/ICCV.2013.419
– ident: 10.1016/j.neunet.2019.04.024_b402
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b190
– volume: 86
  start-page: 2278
  year: 1998
  ident: 10.1016/j.neunet.2019.04.024_b78
  article-title: Gradient-based learning applied to document recognition
  publication-title: Proceedings of IEEE
  doi: 10.1109/5.726791
– ident: 10.1016/j.neunet.2019.04.024_b207
  doi: 10.1109/IJCNN.2014.6889404
– year: 2018
  ident: 10.1016/j.neunet.2019.04.024_b234
  article-title: Analytics of deep neural network-based background subtraction
  publication-title: MDPI Journal of Imaging
  doi: 10.3390/jimaging4060078
– ident: 10.1016/j.neunet.2019.04.024_b247
  doi: 10.1109/MECO.2017.7977207
– ident: 10.1016/j.neunet.2019.04.024_b169
  doi: 10.1145/2695664.2695863
SSID ssj0006843
Score 2.6638496
SecondaryResourceType review_article
Snippet Conventional neural networks have been demonstrated to be a powerful framework for background subtraction in video acquired by static cameras. Indeed, the...
SourceID hal
proquest
pubmed
crossref
elsevier
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 8
SubjectTerms Auto-encoders networks
Background subtraction
Computer Science
Convolutional neural networks
Generative adversarial networks
Image Processing
Restricted Boltzmann machines
Title Deep neural network concepts for background subtraction:A systematic review and comparative evaluation
URI https://dx.doi.org/10.1016/j.neunet.2019.04.024
https://www.ncbi.nlm.nih.gov/pubmed/31129491
https://www.proquest.com/docview/2231849664
https://hal.science/hal-02118618
Volume 117
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NT9wwELWAXrhAP4BuP5CpuJpN1pPY6W1Fi7Yt5VKQuFm2Y4ulKKzY3R772zsTJ7vigJB6iZRoklgZ2_MmfvPM2DGOshC01SIWAAKijcKqrBIqjkY2d3UGnv5D_rwoJ1fw_bq43mCnfS0M0Sq7uT_N6e1s3V0Zdl9zOJtOh78yDLUlAh6EILT8RoqfAIr080_-rmkepU7MOTQWZN2Xz7UcryYsm0CMyrxqBU9H8FR42rwhnuRTILQNRmcv2U6HIvk4NfQV2wjNa7bb79DAuwH7hsUvIcw4aVaidZMY39ynSsU5R7zKnfW_qbKjqfl86RYPqc7h85ivJZ55Km_hFm38Wiycr4XC99jV2dfL04nodlYQHgHZQlhdgyzzEJUvSE8fvPZ57aIqHR5AWxuiLJWyWWWV9rGufCYLW8uC5OtklPtsq7lvwlvGMylrBxZk5itwDtM3CZXCrNti6uJtNWCy_6DGd7LjtPvFnen5ZbcmucGQG0wGBt0wYGJ11yzJbjxjr3pfmUfdx2BkeObOT-ja1UtIbXsyPjd0DeFPrstc_8kH7Kj3vMHhR2sqtgn3y7lBdIU5MuaM-KCD1CVWz5KEZaHK3_13496zbTpLnLYPbGvxsAwfEQQt3GHbyw_Zi_G3H5OLf6wSB08
linkProvider Elsevier
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NT9wwEB0BPbQXoJ8slNatenU3WTux09sKirbtwqUgcbNsxxa0VVixuz32tzMTJ7vigJB6ySGZJFbG9ryJ3zwDfMJRFoK2msdCSi6jjdyqrOIqjkY2d3UmPf2HPD0rJxfy-2VxuQFHfS0M0Sq7uT_N6e1s3Z0Zdl9zOLu-Hv7MMNSWCHgQgtDym9iEJ7IQirr2539rnkepE3UOrTmZ9_VzLcmrCcsmEKUyr1rF05F8KD5tXhFR8iEU2kajk13Y7mAkG6eWPoeN0LyAnX6LBtaN2JcQj0OYMRKtROsmUb6ZT6WKc4aAlTnrf1NpR1Oz-dItblOhw5cxW2s8s1Tfwiza-LVaOFsrhb-Ci5Ov50cT3m2twD0isgW3upaizENUviBBfem1z2sXVenwILW1IYpSKZtVVmkf68pnorC1KEi_TkTxGraamybsAcuEqJ20UmS-ks5h_iZkpTDttpi7eFsNQPQf1PhOd5y2v_hjeoLZL5PcYMgNJpMG3TAAvrprlnQ3HrFXva_Mvf5jMDQ8cudHdO3qJSS3PRlPDZ1D_JPrMtd_8wF86D1vcPzRooptws1ybhBeYZKMSSM-6E3qEqtnCQKzssr3_7tx7-Hp5Px0aqbfzn4cwDO6kghub2FrcbsMh4iIFu5d2-PvAK73COU
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=Deep+Neural+Network+Concepts+for+Background+Subtraction%3A+A+Systematic+Review+and+Comparative+Evaluation&rft.jtitle=Neural+networks&rft.au=Bouwmans%2C+Thierry&rft.au=Javed%2C+Sajid&rft.au=Sultana%2C+Maryam&rft.au=Soon%2C+Ki+Jung&rft.date=2019-09-01&rft.pub=Elsevier&rft.issn=0893-6080&rft.volume=117&rft.spage=8&rft.epage=66&rft_id=info:doi/10.1016%2Fj.neunet.2019.04.024&rft.externalDBID=HAS_PDF_LINK&rft.externalDocID=oai_HAL_hal_02118618v1
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon