Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes

•This paper is one of the first where fully convolutional neural network is used for anomaly detection.•Adapting a pre-trained classification CNN to an FCN for generating video regions to describe motion and shape concurrently.•Proposing a new FCN architecture for time-efficient anomaly detection an...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computer vision and image understanding Ročník 172; s. 88 - 97
Hlavní autori: Sabokrou, Mohammad, Fayyaz, Mohsen, Fathy, Mahmood, Moayed, Zahra, Klette, Reinhard
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Inc 01.07.2018
Predmet:
ISSN:1077-3142, 1090-235X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract •This paper is one of the first where fully convolutional neural network is used for anomaly detection.•Adapting a pre-trained classification CNN to an FCN for generating video regions to describe motion and shape concurrently.•Proposing a new FCN architecture for time-efficient anomaly detection and localization.•The proposed method performs as well as state-of-the-art methods, but our method outperforms those with respect to time; we ensure real-time for typical applications. The detection of abnormal behaviour in crowded scenes has to deal with many challenges. This paper presents an efficient method for detection and localization of anomalies in videos. Using fully convolutional neural networks (FCNs) and temporal data, a pre-trained supervised FCN is transferred into an unsupervised FCN ensuring the detection of (global) anomalies in scenes. High performance in terms of speed and accuracy is achieved by investigating the cascaded detection as a result of reducing computation complexities. This FCN-based architecture addresses two main tasks, feature representation and cascaded outlier detection. Experimental results on two benchmarks suggest that the proposed method outperforms existing methods in terms of accuracy regarding detection and localization.
AbstractList •This paper is one of the first where fully convolutional neural network is used for anomaly detection.•Adapting a pre-trained classification CNN to an FCN for generating video regions to describe motion and shape concurrently.•Proposing a new FCN architecture for time-efficient anomaly detection and localization.•The proposed method performs as well as state-of-the-art methods, but our method outperforms those with respect to time; we ensure real-time for typical applications. The detection of abnormal behaviour in crowded scenes has to deal with many challenges. This paper presents an efficient method for detection and localization of anomalies in videos. Using fully convolutional neural networks (FCNs) and temporal data, a pre-trained supervised FCN is transferred into an unsupervised FCN ensuring the detection of (global) anomalies in scenes. High performance in terms of speed and accuracy is achieved by investigating the cascaded detection as a result of reducing computation complexities. This FCN-based architecture addresses two main tasks, feature representation and cascaded outlier detection. Experimental results on two benchmarks suggest that the proposed method outperforms existing methods in terms of accuracy regarding detection and localization.
Author Moayed, Zahra
Sabokrou, Mohammad
Klette, Reinhard
Fayyaz, Mohsen
Fathy, Mahmood
Author_xml – sequence: 1
  givenname: Mohammad
  orcidid: 0000-0002-9409-2799
  surname: Sabokrou
  fullname: Sabokrou, Mohammad
  email: sabokro@ipm.ir
  organization: School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran PO Box 19395-5746, Iran
– sequence: 2
  givenname: Mohsen
  surname: Fayyaz
  fullname: Fayyaz, Mohsen
  email: fayyaz@iai.uni-bonn.de
  organization: University of Bonn, Germany
– sequence: 3
  givenname: Mahmood
  surname: Fathy
  fullname: Fathy, Mahmood
  email: mfathy@ipm.ir
  organization: School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran PO Box 19395-5746, Iran
– sequence: 4
  givenname: Zahra
  surname: Moayed
  fullname: Moayed, Zahra
  email: zmoayed@aut.ac.nz
  organization: School of Engineering, Computer and Mathematical Sciences, EEE Department, Auckland University of Technology, Auckland, New Zealand
– sequence: 5
  givenname: Reinhard
  surname: Klette
  fullname: Klette, Reinhard
  email: rklette@aut.ac.nz
  organization: School of Engineering, Computer and Mathematical Sciences, EEE Department, Auckland University of Technology, Auckland, New Zealand
BookMark eNp9kMtOwzAQRS1UJNrCD7DyDyT4kToJYoMKBaRKbEBigyw_JpJLald22qp_T0K7YtHVncWcGd0zQSMfPCB0S0lOCRV3q9zs3DZnhFY5YTkh4gKNKalJxvjsazTMZZlxWrArNElpRQilRU3H6PsJYJMpH9aqPdzjxbZtD9gEvwvttnPBqxZ72Ma_6PYh_uAmRNyo1OEThC10YIZd7Dw2MewtWJwMeEjX6LJRbYKbU07R5-L5Y_6aLd9f3uaPy8xwIbqM1VqxghJegapZoWeV5o2oal0KsJaCFcaICqy2GkwpKkpnJXDOhNYVLzXnU8SOd_v3KUVo5Ca6tYoHSYkcBMmVHATJQZAkTPaCeqj6BxnXqaFIF5Vrz6MPRxT6UjsHUSbjwBuwLvYupA3uHP4L6uGGGQ
CitedBy_id crossref_primary_10_32604_csse_2025_060387
crossref_primary_10_1109_TKDE_2024_3448473
crossref_primary_10_1007_s11042_023_17375_6
crossref_primary_10_1109_ACCESS_2022_3155123
crossref_primary_10_1007_s11760_025_04113_8
crossref_primary_10_1109_JAS_2021_1004045
crossref_primary_10_1109_TNNLS_2021_3053563
crossref_primary_10_1109_ACCESS_2024_3404553
crossref_primary_10_1109_ACCESS_2020_3009819
crossref_primary_10_1007_s11227_022_04410_w
crossref_primary_10_1007_s00521_021_06521_6
crossref_primary_10_1002_ett_3922
crossref_primary_10_1007_s00138_021_01182_w
crossref_primary_10_1109_TCSVT_2023_3327448
crossref_primary_10_1007_s10489_021_02736_1
crossref_primary_10_1007_s11760_024_03323_w
crossref_primary_10_1016_j_imavis_2021_104229
crossref_primary_10_1007_s11042_023_15872_2
crossref_primary_10_1145_3417989
crossref_primary_10_1016_j_neucom_2020_10_044
crossref_primary_10_1111_exsy_13784
crossref_primary_10_3390_s22166080
crossref_primary_10_3390_ma14154168
crossref_primary_10_1109_ACCESS_2024_3510039
crossref_primary_10_32604_cmc_2022_017522
crossref_primary_10_1016_j_inffus_2020_07_008
crossref_primary_10_1016_j_trc_2018_12_004
crossref_primary_10_1109_TPAMI_2022_3193611
crossref_primary_10_1016_j_cviu_2020_102920
crossref_primary_10_1186_s13638_020_01807_0
crossref_primary_10_1109_TPAMI_2023_3322604
crossref_primary_10_1007_s00500_019_04544_9
crossref_primary_10_3390_app13084956
crossref_primary_10_1007_s10723_020_09506_2
crossref_primary_10_1007_s00530_022_00975_x
crossref_primary_10_1007_s00371_023_03124_1
crossref_primary_10_1109_TCDS_2018_2866838
crossref_primary_10_1016_j_eswa_2022_117030
crossref_primary_10_1007_s11042_021_10570_3
crossref_primary_10_1007_s00138_017_0869_8
crossref_primary_10_1007_s11280_018_0582_1
crossref_primary_10_3233_JIFS_211556
crossref_primary_10_1109_TNNLS_2024_3441011
crossref_primary_10_1007_s42979_025_03979_2
crossref_primary_10_3233_JIFS_221925
crossref_primary_10_1007_s11042_023_15911_y
crossref_primary_10_1007_s11263_020_01400_4
crossref_primary_10_1007_s11760_023_02750_5
crossref_primary_10_1109_ACCESS_2024_3373199
crossref_primary_10_1016_j_simpat_2018_10_010
crossref_primary_10_1134_S1054661821040301
crossref_primary_10_3390_app9040757
crossref_primary_10_1117_1_JEI_32_6_063020
crossref_primary_10_1016_j_aej_2025_03_106
crossref_primary_10_32604_cmc_2021_014642
crossref_primary_10_1007_s00371_023_03210_4
crossref_primary_10_1016_j_patrec_2021_11_001
crossref_primary_10_1007_s42979_023_02260_8
crossref_primary_10_3390_s19112451
crossref_primary_10_1007_s10489_025_06797_4
crossref_primary_10_1016_j_patcog_2020_107355
crossref_primary_10_1007_s13735_022_00227_8
crossref_primary_10_1109_ACCESS_2020_3041790
crossref_primary_10_1007_s41060_024_00591_0
crossref_primary_10_1155_2022_3819409
crossref_primary_10_3390_jimaging9030060
crossref_primary_10_1016_j_imavis_2020_104078
crossref_primary_10_1177_0959651820954577
crossref_primary_10_1016_j_ymeth_2023_04_007
crossref_primary_10_3233_IDT_190360
crossref_primary_10_1007_s11042_020_09004_3
crossref_primary_10_1007_s42979_024_02945_8
crossref_primary_10_1016_j_eswa_2024_123658
crossref_primary_10_1016_j_cmpb_2025_109012
crossref_primary_10_1109_ACCESS_2023_3293108
crossref_primary_10_1093_comjnl_bxab166
crossref_primary_10_1088_1742_6596_1627_1_012014
crossref_primary_10_1007_s10489_022_03488_2
crossref_primary_10_1145_3428151
crossref_primary_10_3390_a18060326
crossref_primary_10_1007_s11042_022_13643_z
crossref_primary_10_1155_2021_9861533
crossref_primary_10_1007_s11063_024_11466_7
crossref_primary_10_1109_TSM_2024_3416055
crossref_primary_10_1109_TKDE_2023_3328882
crossref_primary_10_3390_computation12020019
crossref_primary_10_1016_j_neucom_2021_04_033
crossref_primary_10_1007_s11063_023_11347_5
crossref_primary_10_1007_s11042_023_14575_y
crossref_primary_10_1016_j_ipm_2023_103289
crossref_primary_10_1007_s11633_020_1247_y
crossref_primary_10_1007_s00371_024_03361_y
crossref_primary_10_3390_s22114040
crossref_primary_10_1109_TCSVT_2024_3376399
crossref_primary_10_1049_2024_2850804
crossref_primary_10_1016_j_cviu_2024_104074
crossref_primary_10_1016_j_neunet_2024_106106
crossref_primary_10_1109_TMM_2020_2984093
crossref_primary_10_1155_2022_1761655
crossref_primary_10_1109_TPAMI_2021_3074805
crossref_primary_10_1109_TASE_2021_3109353
crossref_primary_10_1007_s00138_020_01111_3
crossref_primary_10_1007_s00138_021_01179_5
crossref_primary_10_1038_s41598_025_01146_4
crossref_primary_10_3390_ai1010005
crossref_primary_10_1109_TKDE_2020_3035685
crossref_primary_10_1109_TIFS_2023_3300094
crossref_primary_10_1109_ACCESS_2020_2992804
crossref_primary_10_1016_j_cose_2020_102070
crossref_primary_10_3389_fphy_2019_00194
crossref_primary_10_3390_s21113664
crossref_primary_10_1109_TMM_2020_3046884
crossref_primary_10_1016_j_neunet_2019_11_002
crossref_primary_10_1109_TNNLS_2020_2979049
crossref_primary_10_1016_j_measurement_2020_108116
crossref_primary_10_3390_app9163337
crossref_primary_10_1109_TMM_2019_2929931
crossref_primary_10_1109_TPAMI_2020_3040591
crossref_primary_10_3233_JIFS_232177
crossref_primary_10_1007_s42514_024_00185_z
crossref_primary_10_3390_s23115024
crossref_primary_10_1109_ACCESS_2021_3083060
crossref_primary_10_1007_s11042_023_17425_z
crossref_primary_10_1109_ACCESS_2022_3171559
crossref_primary_10_1134_S1054661822020067
crossref_primary_10_1007_s42452_021_04528_1
crossref_primary_10_1155_2021_5513582
crossref_primary_10_1007_s40747_024_01422_2
crossref_primary_10_1109_ACCESS_2021_3118541
crossref_primary_10_1007_s11042_019_7702_5
crossref_primary_10_1049_cvi2_12082
crossref_primary_10_3390_app14219758
crossref_primary_10_1007_s10044_020_00901_9
crossref_primary_10_1109_TIFS_2019_2900907
crossref_primary_10_1109_ACCESS_2019_2946861
crossref_primary_10_1007_s11227_020_03391_y
crossref_primary_10_3233_JIFS_179003
crossref_primary_10_1109_TCC_2020_2990946
crossref_primary_10_1109_ACCESS_2023_3273770
crossref_primary_10_1016_j_compeleceng_2024_109879
crossref_primary_10_1016_j_ins_2021_11_001
crossref_primary_10_1109_TMM_2023_3292596
crossref_primary_10_3390_ijgi11030205
crossref_primary_10_1007_s11042_023_14425_x
crossref_primary_10_1109_TMM_2024_3414263
crossref_primary_10_3390_app12031374
crossref_primary_10_1016_j_media_2023_103067
crossref_primary_10_1109_ACCESS_2020_3011187
crossref_primary_10_1016_j_cviu_2023_103686
crossref_primary_10_1007_s11760_025_04640_4
crossref_primary_10_1016_j_micpro_2020_103303
crossref_primary_10_1016_j_patcog_2022_108860
crossref_primary_10_1109_TBDATA_2020_2991008
crossref_primary_10_1109_TNSM_2020_2971776
crossref_primary_10_1109_TIV_2022_3152084
crossref_primary_10_1016_j_eswa_2023_120599
crossref_primary_10_1109_ACCESS_2019_2941503
crossref_primary_10_1016_j_engappai_2023_107072
crossref_primary_10_1016_j_eswa_2025_128529
crossref_primary_10_3390_s22134658
crossref_primary_10_1016_j_engappai_2023_107830
crossref_primary_10_7717_peerj_cs_895
crossref_primary_10_1016_j_ssci_2021_105356
crossref_primary_10_1109_ACCESS_2020_2979869
crossref_primary_10_1007_s11042_023_17842_0
crossref_primary_10_3390_s23062938
crossref_primary_10_1109_TCSVT_2019_2962229
crossref_primary_10_1007_s00530_024_01320_0
crossref_primary_10_1016_j_patrec_2022_11_011
crossref_primary_10_1142_S0219467825500470
crossref_primary_10_3390_s19163549
crossref_primary_10_1038_s41598_025_07486_5
crossref_primary_10_3389_frsc_2023_1197434
crossref_primary_10_1007_s11042_023_17889_z
crossref_primary_10_1049_ipr2_12104
crossref_primary_10_1109_ACCESS_2020_2970497
crossref_primary_10_1109_TPAMI_2024_3461718
crossref_primary_10_1016_j_ecolind_2022_108583
crossref_primary_10_1109_ACCESS_2024_3396219
crossref_primary_10_1016_j_fss_2025_109460
crossref_primary_10_1109_TII_2019_2938527
crossref_primary_10_1007_s11042_023_14922_z
crossref_primary_10_1016_j_neucom_2019_08_044
crossref_primary_10_3390_electronics13071194
crossref_primary_10_1016_j_patcog_2020_107515
crossref_primary_10_1016_j_neucom_2023_126770
crossref_primary_10_1109_JIOT_2021_3097437
crossref_primary_10_1007_s11042_019_7447_1
crossref_primary_10_1007_s11760_021_02049_3
crossref_primary_10_1109_OJCOMS_2025_3593311
crossref_primary_10_1016_j_neucom_2020_07_058
crossref_primary_10_1016_j_neucom_2024_127246
crossref_primary_10_1109_TIM_2021_3098381
crossref_primary_10_1007_s13369_023_08038_7
crossref_primary_10_1049_ipr2_12239
crossref_primary_10_1016_j_future_2021_02_001
crossref_primary_10_1007_s00371_023_02783_4
crossref_primary_10_1016_j_neucom_2021_05_112
crossref_primary_10_1007_s11042_020_08786_w
crossref_primary_10_1016_j_jvcir_2023_103860
crossref_primary_10_1111_exsy_70013
crossref_primary_10_1007_s12652_022_03861_6
crossref_primary_10_1007_s12652_021_03425_0
crossref_primary_10_1109_ACCESS_2023_3315739
crossref_primary_10_3390_app13010049
crossref_primary_10_1016_j_neucom_2020_12_025
crossref_primary_10_3390_s20174943
crossref_primary_10_1109_TDSC_2020_3034331
crossref_primary_10_1109_TCSVT_2019_2929855
crossref_primary_10_1186_s40537_023_00779_4
crossref_primary_10_1109_JIOT_2020_2975418
crossref_primary_10_1016_j_patcog_2021_107969
crossref_primary_10_1049_ipr2_12006
crossref_primary_10_1109_TMM_2019_2893549
crossref_primary_10_1007_s11042_023_14827_x
crossref_primary_10_1016_j_engappai_2023_107706
crossref_primary_10_3390_s24123711
crossref_primary_10_1109_ACCESS_2021_3118009
crossref_primary_10_1049_cmu2_12265
crossref_primary_10_1109_ACCESS_2019_2925838
crossref_primary_10_3390_ma15103727
crossref_primary_10_3390_s222410016
crossref_primary_10_3390_s18103533
crossref_primary_10_1109_ACCESS_2021_3091081
crossref_primary_10_1109_TITS_2020_2984735
crossref_primary_10_1109_TITS_2022_3157254
crossref_primary_10_1002_sam_11562
crossref_primary_10_1007_s10462_022_10258_6
crossref_primary_10_1109_TMM_2022_3175611
crossref_primary_10_1049_gtd2_12756
crossref_primary_10_1109_TIP_2023_3293772
crossref_primary_10_3389_fcomp_2024_1242690
crossref_primary_10_1016_j_jvcir_2022_103598
crossref_primary_10_1002_ett_3865
crossref_primary_10_1016_j_imavis_2024_105011
crossref_primary_10_1016_j_compind_2023_103852
crossref_primary_10_1007_s10489_022_04233_5
crossref_primary_10_1016_j_imavis_2024_104950
crossref_primary_10_1109_ACCESS_2021_3091980
crossref_primary_10_1109_TPAMI_2021_3092999
crossref_primary_10_1038_s41598_025_16653_7
crossref_primary_10_1007_s11042_021_11781_4
Cites_doi 10.1007/s11263-006-0009-9
10.1109/TIP.2017.2670780
10.1016/j.imavis.2010.11.003
10.1109/TPAMI.2011.64
10.1109/TIFS.2013.2272243
10.1049/el.2016.0440
10.1109/TCYB.2014.2330853
10.1109/TCSVT.2015.2395752
10.1007/978-1-4471-6714-3
10.1016/j.cviu.2013.06.007
10.1109/TPAMI.2006.176
10.1016/j.sigpro.2009.03.016
10.1016/j.cviu.2011.03.003
10.1109/TCSVT.2008.2005599
10.1016/j.neucom.2014.12.064
10.1016/j.cviu.2010.10.008
10.1109/TPAMI.2007.70825
10.1016/j.patrec.2006.02.004
10.1016/j.cviu.2011.09.009
10.1109/LSP.2015.2410031
10.1016/j.neucom.2014.06.011
ContentType Journal Article
Copyright 2018 Elsevier Inc.
Copyright_xml – notice: 2018 Elsevier Inc.
DBID AAYXX
CITATION
DOI 10.1016/j.cviu.2018.02.006
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
Computer Science
EISSN 1090-235X
EndPage 97
ExternalDocumentID 10_1016_j_cviu_2018_02_006
S1077314218300249
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1~.
1~5
29F
4.4
457
4G.
5GY
5VS
6TJ
7-5
71M
8P~
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKC
AAIKJ
AAKOC
AALRI
AAMNW
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABEFU
ABFNM
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADFGL
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CAG
COF
CS3
DM4
DU5
EBS
EFBJH
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HF~
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG5
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSV
SSZ
T5K
TN5
XPP
ZMT
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
SST
~HD
ID FETCH-LOGICAL-c366t-29ba241038ea924b58b3f689b76edd1ed6cc68edbdbec7681157e3326bb837b33
ISICitedReferencesCount 303
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000454184500008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1077-3142
IngestDate Tue Nov 18 21:02:58 EST 2025
Sat Nov 29 06:43:53 EST 2025
Fri Feb 23 02:26:54 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Real-time processing
Video anomaly detection
CNN
Transfer learning
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c366t-29ba241038ea924b58b3f689b76edd1ed6cc68edbdbec7681157e3326bb837b33
ORCID 0000-0002-9409-2799
PageCount 10
ParticipantIDs crossref_primary_10_1016_j_cviu_2018_02_006
crossref_citationtrail_10_1016_j_cviu_2018_02_006
elsevier_sciencedirect_doi_10_1016_j_cviu_2018_02_006
PublicationCentury 2000
PublicationDate July 2018
2018-07-00
PublicationDateYYYYMMDD 2018-07-01
PublicationDate_xml – month: 07
  year: 2018
  text: July 2018
PublicationDecade 2010
PublicationTitle Computer vision and image understanding
PublicationYear 2018
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References Morris, Trivedi (bib0029) 2011; 33
Zhu, Nayak, Roy-Chowdhury (bib0064) 2013
Lee, Suk, Park, Lee (bib0022) 2015; 25
Lu, Shi, Jia (bib0026) 2013
Deng, Dong, Socher, Li, Li, Fei-Fei (bib0012) 2009
Kratz, Nishino (bib0020) 2009
Cong, Yuan, Tang (bib0010) 2013; 8
Jia, Shelhamer, Donahue, Karayev, Long, Girshick, Guadarrama, Darrell (bib0017) 2014
Roshtkhari, Levine (bib0036) 2013; 117
Tsung-Han, Jia, Gao, Lu, Zeng, Ma (bib0046) 2015
MIT places database, 2017.
Reddy, Sanderson, Lovell (bib0034) 2011
Li, Wu, Xu, Guo, Feng (bib0023) 2015; 155
Yachuang, Yuan, Xiaoqiang (bib0058) 2017
Zaharescu, Wildes (bib0060) 2010; 1
Sabokrou, Fayyaz, Fathy, Klette (bib0041) 2017
Shelhamer, Long, Darrell (bib0044) 2016
Benezeth, Jodoin, Saligrama, Rosenberger (bib0004) 2009
Sabokrou, Fathy, Moayed, Klette (bib0040) 2017; 28
Giusti, Ciresan, Masci, Gambardella, Schmidhuber (bib0014) 2013
Tung, Zelek, Clausi (bib0047) 2011; 29
Jiang, Yuan, Tsaftaris, Katsaggelos (bib0018) 2011; 115
.
Cheng, Chen, Fang (bib0008) 2015
Ullah, Tenuti, Conci (bib0050) 2013
Li, Mahadevan, Vasconcelos (bib0024) 2014
Sabokrou, Fathy, Hoseini (bib0038) 2016
Antonakaki, Kosmopoulos, Perantonis (bib0003) 2009; 89
Piciarelli, Foresti (bib0032) 2006; 27
Krizhevsky, Sutskever, Hinton (bib0021) 2012
Ren, He, Girshick, Sun (bib0035) 2015
Girshick, Donahue, Darrell, Malik (bib0013) 2014
Boiman, Irani (bib0006) 2007; 74
Ullah, Conci (bib0049) 2012
Ullah, Ullah, Conci (bib0052) 2014
Mehran, Oyama, Shah (bib0028) 2009
Yuan, Fang, Wang (bib0059) 2015
Zhang, Gatica-Perez, Bengio, McCowan (bib0061) 2005; 1
Mahadevan, Li, Bhalodia, Vasconcelos (bib0027) 2010
Adam, Rivlin, Shimshoni, Reinitz (bib0001) 2008; 30
Hu, Xiao, Fu, Xie, Tan, Maybank (bib0015) 2006; 28
Xiao, Zhang, Zha (bib0055) 2015; 22
Calderara, Heinemann, Prati, Cucchiara, Tishby (bib0007) 2011; 115
Simonyan, K., Zisserman, A.,. Two-stream convolutional networks for action recognition in videos. CoRR, arXiv
Mousavi, Nabi, Galoogahi, Perina, Murino (bib0030) 2015
Saligrama, Chen (bib0042) 2012
Ullah, Ullah, Conci (bib0051) 2014
Vincent, Larochelle, Bengio, Manzagol (bib0053) 2008
Cong, Yuan, Liu (bib0009) 2011
Zhijun, Fei, Fang, Lee, Xiong, Shu, Chen (bib0062) 2016
Piciarelli, Micheloni, Foresti (bib0033) 2008; 18
Oquab, Bottou, Laptev, Sivic (bib0031) 2014
2017. Ucsd anomaly detection dataset.
Kim, Grauman (bib0019) 2009
Xu, Song, Wu, Li, Feng, Qian (bib0057) 2014; 143
ImageNet, 2017.
Long, Shelhamer, Darrell (bib0025) 2015
Roshtkhari, Levine (bib0037) 2013
Antic, Ommer (bib0002) 2011
Wu, Moore, Shah (bib0054) 2010
Zhou, Lapedriza, Xiao, Torralba, Oliva (bib0063) 2014
Bertini, Bimbo, Seidenari (bib0005) 2012
Xu, Ricci, Yan, Song, Sebe (bib0056) 2015
Sabokrou, Fathy, Hoseini, Klette (bib0039) 2015
10.1016/j.cviu.2018.02.006_bib0011
Ullah (10.1016/j.cviu.2018.02.006_bib0049) 2012
10.1016/j.cviu.2018.02.006_bib0016
Jia (10.1016/j.cviu.2018.02.006_bib0017) 2014
Xu (10.1016/j.cviu.2018.02.006_bib0057) 2014; 143
Xiao (10.1016/j.cviu.2018.02.006_bib0055) 2015; 22
Giusti (10.1016/j.cviu.2018.02.006_bib0014) 2013
Ullah (10.1016/j.cviu.2018.02.006_sbref0046) 2013
Deng (10.1016/j.cviu.2018.02.006_bib0012) 2009
Vincent (10.1016/j.cviu.2018.02.006_bib0053) 2008
Yuan (10.1016/j.cviu.2018.02.006_bib0059) 2015
Antic (10.1016/j.cviu.2018.02.006_bib0002) 2011
Girshick (10.1016/j.cviu.2018.02.006_bib0013) 2014
Li (10.1016/j.cviu.2018.02.006_bib0024) 2014
Mahadevan (10.1016/j.cviu.2018.02.006_bib0027) 2010
Zhu (10.1016/j.cviu.2018.02.006_bib0064) 2013
Boiman (10.1016/j.cviu.2018.02.006_bib0006) 2007; 74
Bertini (10.1016/j.cviu.2018.02.006_bib0005) 2012
10.1016/j.cviu.2018.02.006_bib0045
Roshtkhari (10.1016/j.cviu.2018.02.006_bib0037) 2013
Xu (10.1016/j.cviu.2018.02.006_bib0056) 2015
Long (10.1016/j.cviu.2018.02.006_bib0025) 2015
Reddy (10.1016/j.cviu.2018.02.006_bib0034) 2011
10.1016/j.cviu.2018.02.006_bib0048
Zaharescu (10.1016/j.cviu.2018.02.006_bib0060) 2010; 1
Lee (10.1016/j.cviu.2018.02.006_bib0022) 2015; 25
Piciarelli (10.1016/j.cviu.2018.02.006_bib0032) 2006; 27
Sabokrou (10.1016/j.cviu.2018.02.006_bib0039) 2015
Tsung-Han (10.1016/j.cviu.2018.02.006_bib0046) 2015
Antonakaki (10.1016/j.cviu.2018.02.006_bib0003) 2009; 89
Krizhevsky (10.1016/j.cviu.2018.02.006_bib0021) 2012
Oquab (10.1016/j.cviu.2018.02.006_bib0031) 2014
Ren (10.1016/j.cviu.2018.02.006_bib0035) 2015
Hu (10.1016/j.cviu.2018.02.006_bib0015) 2006; 28
Cheng (10.1016/j.cviu.2018.02.006_bib0008) 2015
Morris (10.1016/j.cviu.2018.02.006_bib0029) 2011; 33
Calderara (10.1016/j.cviu.2018.02.006_bib0007) 2011; 115
Roshtkhari (10.1016/j.cviu.2018.02.006_bib0036) 2013; 117
Wu (10.1016/j.cviu.2018.02.006_bib0054) 2010
Sabokrou (10.1016/j.cviu.2018.02.006_bib0041) 2017
Mehran (10.1016/j.cviu.2018.02.006_bib0028) 2009
Benezeth (10.1016/j.cviu.2018.02.006_bib0004) 2009
Lu (10.1016/j.cviu.2018.02.006_bib0026) 2013
Sabokrou (10.1016/j.cviu.2018.02.006_bib0040) 2017; 28
Kratz (10.1016/j.cviu.2018.02.006_bib0020) 2009
Piciarelli (10.1016/j.cviu.2018.02.006_bib0033) 2008; 18
Sabokrou (10.1016/j.cviu.2018.02.006_bib0038) 2016
Zhou (10.1016/j.cviu.2018.02.006_bib0063) 2014
Ullah (10.1016/j.cviu.2018.02.006_sbref0048) 2014
Cong (10.1016/j.cviu.2018.02.006_bib0010) 2013; 8
Mousavi (10.1016/j.cviu.2018.02.006_bib0030) 2015
Adam (10.1016/j.cviu.2018.02.006_bib0001) 2008; 30
Zhijun (10.1016/j.cviu.2018.02.006_bib0062) 2016
Saligrama (10.1016/j.cviu.2018.02.006_bib0042) 2012
Tung (10.1016/j.cviu.2018.02.006_bib0047) 2011; 29
Zhang (10.1016/j.cviu.2018.02.006_bib0061) 2005; 1
Cong (10.1016/j.cviu.2018.02.006_bib0009) 2011
Kim (10.1016/j.cviu.2018.02.006_bib0019) 2009
Li (10.1016/j.cviu.2018.02.006_bib0023) 2015; 155
Jiang (10.1016/j.cviu.2018.02.006_bib0018) 2011; 115
Ullah (10.1016/j.cviu.2018.02.006_bib0051) 2014
Yachuang (10.1016/j.cviu.2018.02.006_bib0058) 2017
Shelhamer (10.1016/j.cviu.2018.02.006_bib0044) 2016
References_xml – year: 2015
  ident: bib0056
  article-title: Learning deep representations of appearance and motion for anomalous event detection
  publication-title: BMVC
– start-page: 548
  year: 2017
  end-page: 556
  ident: bib0058
  article-title: Learning deep event models for crowd anomaly detection
  publication-title: Neurocomputing
– start-page: 1975
  year: 2010
  end-page: 1981
  ident: bib0027
  article-title: Anomaly detection in crowded scenes
  publication-title: Comput. Vis. Pattern Recognit.
– start-page: 2054
  year: 2010
  end-page: 2060
  ident: bib0054
  article-title: Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes
  publication-title: Computer Vision Pattern Recognition
– start-page: 548
  year: 2015
  end-page: 561
  ident: bib0059
  article-title: Online anomaly detection in crowd scenes via structure analysis
  publication-title: IEEE Trans. Cybern.s
– volume: 143
  start-page: 144
  year: 2014
  end-page: 152
  ident: bib0057
  article-title: Video anomaly detection based on a hierarchical activity discovery within spatio-temporal contexts
  publication-title: Neurocomputing
– start-page: 18
  year: 2014
  end-page: 32
  ident: bib0024
  article-title: Anomaly detection and localization in crowded scenes
  publication-title: IEEE Trans. Pattern Analysis Machine Intelligence
– start-page: 935
  year: 2009
  end-page: 942
  ident: bib0028
  article-title: Abnormal crowd behavior detection using social force model
  publication-title: Computer Vision Pattern Recognition
– volume: 89
  start-page: 1723
  year: 2009
  end-page: 1738
  ident: bib0003
  article-title: Detecting abnormal human behaviour using multiple cameras
  publication-title: Signal Process.
– reference: ImageNet, 2017.
– start-page: 487
  year: 2014
  end-page: 495
  ident: bib0063
  article-title: Learning deep features for scene recognition using places database
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 74
  start-page: 17
  year: 2007
  end-page: 31
  ident: bib0006
  article-title: Detecting irregularities in images and in video
  publication-title: Int. J. Comput. Vis.
– start-page: 1992
  year: 2017
  end-page: 2004
  ident: bib0041
  article-title: Deep-cascade: cascading 3d deep neural networks for fast anomaly detection and localization in crowded scenes
  publication-title: IEEE Trans. Image Process.
– volume: 1
  start-page: 611
  year: 2005
  end-page: 618
  ident: bib0061
  article-title: Semi-supervised adapted HMMS for unusual event detection
  publication-title: Computer Vision Pattern Recognition
– year: 2015
  ident: bib0035
  article-title: Faster R-CNN: towards real-time object detection with region proposal networks
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 2921
  year: 2009
  end-page: 2928
  ident: bib0019
  article-title: Observe locally, infer globally: a space-time MRF for detecting abnormal activities with incremental updates
  publication-title: Computer Vision Pattern Recognition
– volume: 30
  start-page: 555
  year: 2008
  end-page: 560
  ident: bib0001
  article-title: Robust real-time unusual event detection using multiple fixed-location monitors
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 2112
  year: 2012
  end-page: 2119
  ident: bib0042
  article-title: Video anomaly detection based on local statistical aggregates
  publication-title: Computer Vision Pattern Recognition
– volume: 117
  start-page: 1436
  year: 2013
  end-page: 1452
  ident: bib0036
  article-title: An on-line, real-time learning method for detecting anomalies in videos using spatio-temporal compositions
  publication-title: Comput. Vis. Image Underst.
– start-page: 4034
  year: 2013
  end-page: 4038
  ident: bib0014
  article-title: Fast image scanning with deep max-pooling convolutional neural networks
  publication-title: IEEE International Conference on Image Processing
– start-page: 1096
  year: 2008
  end-page: 1103
  ident: bib0053
  article-title: Extracting and composing robust features with denoising autoencoders
  publication-title: International Conference on Machine Learning
– start-page: 248
  year: 2009
  end-page: 255
  ident: bib0012
  article-title: ImageNet: a large-scale hierarchical image database
  publication-title: Computer Vision Pattern Recognition
– start-page: 1717
  year: 2014
  end-page: 1724
  ident: bib0031
  article-title: Learning and transferring mid-level image representations using convolutional neural networks
  publication-title: Computer Vision Pattern Recognition
– start-page: 1446
  year: 2009
  end-page: 1453
  ident: bib0020
  article-title: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models
  publication-title: Computer Vision Pattern Recognition
– volume: 28
  start-page: 1450
  year: 2006
  end-page: 1464
  ident: bib0015
  article-title: A system for learning statistical motion patterns
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 3449
  year: 2011
  end-page: 3456
  ident: bib0009
  article-title: Sparse reconstruction cost for abnormal event detection
  publication-title: Computer Vision Pattern Recognition
– volume: 25
  start-page: 1612
  year: 2015
  end-page: 1623
  ident: bib0022
  article-title: Motion influence map for unusual human activity detection and localization in crowded scenes
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– volume: 28
  start-page: 965
  year: 2017
  end-page: 985
  ident: bib0040
  article-title: Fast and accurate detection and localization of abnormal behavior in crowded scenes
  publication-title: Machine Vision and Applications
– start-page: 2458
  year: 2009
  end-page: 2465
  ident: bib0004
  article-title: Abnormal events detection based on spatio-temporal co-occurrences
  publication-title: Computer Vision Pattern Recognition
– start-page: 580
  year: 2014
  end-page: 587
  ident: bib0013
  article-title: Rich feature hierarchies for accurate object detection and semantic segmentation
  publication-title: Computer Vision Pattern Recognition
– start-page: 2415
  year: 2011
  end-page: 2422
  ident: bib0002
  article-title: Video parsing for abnormality detection
  publication-title: International Conference on Computer Vision
– reference: MIT places database, 2017.
– start-page: 1122
  year: 2016
  end-page: 1124
  ident: bib0038
  article-title: Video anomaly detection and localisation based on the sparsity and reconstruction error of auto-encoder
  publication-title: Electron. Lett.
– start-page: 14617
  year: 2016
  end-page: 14639
  ident: bib0062
  article-title: Abnormal event detection in crowded scenes based on deep learning
  publication-title: Multim. Tools Appl.
– volume: 155
  start-page: 309
  year: 2015
  end-page: 319
  ident: bib0023
  article-title: Spatio-temporal context analysis within video volumes for anomalous-event detection and localization
  publication-title: Neurocomputing
– year: 2016
  ident: bib0044
  article-title: Fully convolutional networks for semantic segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 1
  start-page: 563
  year: 2010
  end-page: 576
  ident: bib0060
  article-title: Anomalous behaviour detection using spatiotemporal oriented energies, subset inclusion histogram comparison and event-driven processing
  publication-title: European Conference on Computer Vision
– volume: 27
  start-page: 1835
  year: 2006
  end-page: 1842
  ident: bib0032
  article-title: On-line trajectory clustering for anomalous events detection
  publication-title: Pattern Recognit. Lett.
– reference: Simonyan, K., Zisserman, A.,. Two-stream convolutional networks for action recognition in videos. CoRR, arXiv:
– start-page: 675
  year: 2014
  end-page: 678
  ident: bib0017
  article-title: Caffe: convolutional architecture for fast feature embedding
  publication-title: ACM International Conference on Multimedia
– volume: 8
  start-page: 1590
  year: 2013
  end-page: 1599
  ident: bib0010
  article-title: Video anomaly search in crowded scenes via spatio-temporal motion context
  publication-title: IEEE Trans. Inf. Forensics Secur.
– start-page: 722
  year: 2015
  end-page: 732
  ident: bib0030
  article-title: Abnormality detection with improved histogram of oriented tracklets
  publication-title: International Conference on Image Analysis Processing
– volume: 18
  start-page: 1544
  year: 2008
  end-page: 1554
  ident: bib0033
  article-title: Trajectory-based anomalous event detection
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– start-page: 2611
  year: 2013
  end-page: 2618
  ident: bib0037
  article-title: Online dominant and anomalous behavior detection in videos
  publication-title: Computer Vision Pattern Recognition
– start-page: 2491
  year: 2013
  end-page: 2498
  ident: bib0064
  article-title: Context-aware modeling and recognition of activities in video
  publication-title: Computer Vision Pattern Recognition
– start-page: 55
  year: 2011
  end-page: 61
  ident: bib0034
  article-title: Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture
  publication-title: Computer Vision Pattern Recognition Workshops
– start-page: 2909
  year: 2015
  end-page: 2917
  ident: bib0008
  article-title: Video anomaly detection and localization using hierarchical feature representation and gaussian process regression
  publication-title: Computer Vision Pattern Recognition
– volume: 115
  start-page: 1099
  year: 2011
  end-page: 1111
  ident: bib0007
  article-title: Detecting anomalies in people’s trajectories using spectral graph analysis
  publication-title: Comput. Vis. Image Underst.
– reference: .
– start-page: 1097
  year: 2012
  end-page: 1105
  ident: bib0021
  article-title: ImageNet classification with deep convolutional neural networks
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 56
  year: 2015
  end-page: 62
  ident: bib0039
  article-title: Real-time anomaly detection and localization in crowded scenes
  publication-title: Computer Vision Pattern Recognition Workshops
– volume: 115
  start-page: 323
  year: 2011
  end-page: 333
  ident: bib0018
  article-title: Anomalous video event detection using spatiotemporal context
  publication-title: Comput. Vis. Image Underst.
– year: 2014
  ident: bib0052
  article-title: Real-time anomaly detection in dense crowded scenes
  publication-title: SPIE Electronic Imaging
– volume: 33
  start-page: 2287
  year: 2011
  end-page: 2301
  ident: bib0029
  article-title: Trajectory learning for activity understanding: unsupervised, multilevel, and long-term adaptive approach
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– year: 2015
  ident: bib0025
  article-title: Fully convolutional networks for semantic segmentation
  publication-title: Computer Vision Pattern Recognition
– year: 2012
  ident: bib0049
  article-title: Crowd motion segmentation and anomaly detection via multi-label optimization
  publication-title: ICPR Workshop Pattern Recognition Crowd Analysis
– start-page: 5017
  year: 2015
  end-page: 5032
  ident: bib0046
  article-title: PcaNet: a simple deep learning baseline for image classification?
  publication-title: IEEE Trans. Image Process.
– year: 2013
  ident: bib0050
  article-title: Gaussian mixtures for anomaly detection, in crowded scenes
  publication-title: SPIE Electronic Imaging
– volume: 29
  start-page: 230
  year: 2011
  end-page: 240
  ident: bib0047
  article-title: Goal-based trajectory analysis for unusual behaviour detection in intelligent surveillance
  publication-title: Image Vis. Comput.
– start-page: 62
  year: 2014
  end-page: 72
  ident: bib0051
  article-title: Dominant motion analysis in regular and irregular crowd scenes
  publication-title: International Workshop on Human Behavior Understanding
– volume: 22
  start-page: 1477
  year: 2015
  end-page: 1481
  ident: bib0055
  article-title: Learning to detect anomalies in surveillance video
  publication-title: IEEE Signal Process. Lett.
– reference: 2017. Ucsd anomaly detection dataset.
– start-page: 320
  year: 2012
  end-page: 329
  ident: bib0005
  article-title: Multi-scale and real-time non-parametric approach for anomaly detection and localization
  publication-title: Comput. Vis. Image Underst.
– start-page: 2720
  year: 2013
  end-page: 2727
  ident: bib0026
  article-title: Abnormal event detection at 150 fps in MATLAB
  publication-title: International Conference on Computer Vision
– year: 2014
  ident: 10.1016/j.cviu.2018.02.006_sbref0048
  article-title: Real-time anomaly detection in dense crowded scenes
– start-page: 56
  year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0039
  article-title: Real-time anomaly detection and localization in crowded scenes
– ident: 10.1016/j.cviu.2018.02.006_bib0016
– start-page: 18
  year: 2014
  ident: 10.1016/j.cviu.2018.02.006_bib0024
  article-title: Anomaly detection and localization in crowded scenes
– volume: 74
  start-page: 17
  issue: 1
  year: 2007
  ident: 10.1016/j.cviu.2018.02.006_bib0006
  article-title: Detecting irregularities in images and in video
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-006-0009-9
– year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0035
  article-title: Faster R-CNN: towards real-time object detection with region proposal networks
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 1992
  year: 2017
  ident: 10.1016/j.cviu.2018.02.006_bib0041
  article-title: Deep-cascade: cascading 3d deep neural networks for fast anomaly detection and localization in crowded scenes
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2017.2670780
– volume: 29
  start-page: 230
  issue: 4
  year: 2011
  ident: 10.1016/j.cviu.2018.02.006_bib0047
  article-title: Goal-based trajectory analysis for unusual behaviour detection in intelligent surveillance
  publication-title: Image Vis. Comput.
  doi: 10.1016/j.imavis.2010.11.003
– start-page: 2921
  year: 2009
  ident: 10.1016/j.cviu.2018.02.006_bib0019
  article-title: Observe locally, infer globally: a space-time MRF for detecting abnormal activities with incremental updates
– start-page: 2054
  year: 2010
  ident: 10.1016/j.cviu.2018.02.006_bib0054
  article-title: Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes
– start-page: 1446
  year: 2009
  ident: 10.1016/j.cviu.2018.02.006_bib0020
  article-title: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models
– volume: 33
  start-page: 2287
  issue: 11
  year: 2011
  ident: 10.1016/j.cviu.2018.02.006_bib0029
  article-title: Trajectory learning for activity understanding: unsupervised, multilevel, and long-term adaptive approach
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2011.64
– year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0025
  article-title: Fully convolutional networks for semantic segmentation
– ident: 10.1016/j.cviu.2018.02.006_bib0045
– start-page: 62
  year: 2014
  ident: 10.1016/j.cviu.2018.02.006_bib0051
  article-title: Dominant motion analysis in regular and irregular crowd scenes
– volume: 8
  start-page: 1590
  issue: 10
  year: 2013
  ident: 10.1016/j.cviu.2018.02.006_bib0010
  article-title: Video anomaly search in crowded scenes via spatio-temporal motion context
  publication-title: IEEE Trans. Inf. Forensics Secur.
  doi: 10.1109/TIFS.2013.2272243
– start-page: 487
  year: 2014
  ident: 10.1016/j.cviu.2018.02.006_bib0063
  article-title: Learning deep features for scene recognition using places database
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 1122
  year: 2016
  ident: 10.1016/j.cviu.2018.02.006_bib0038
  article-title: Video anomaly detection and localisation based on the sparsity and reconstruction error of auto-encoder
  publication-title: Electron. Lett.
  doi: 10.1049/el.2016.0440
– start-page: 548
  year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0059
  article-title: Online anomaly detection in crowd scenes via structure analysis
  publication-title: IEEE Trans. Cybern.s
  doi: 10.1109/TCYB.2014.2330853
– start-page: 4034
  year: 2013
  ident: 10.1016/j.cviu.2018.02.006_bib0014
  article-title: Fast image scanning with deep max-pooling convolutional neural networks
– start-page: 1717
  year: 2014
  ident: 10.1016/j.cviu.2018.02.006_bib0031
  article-title: Learning and transferring mid-level image representations using convolutional neural networks
– volume: 25
  start-page: 1612
  issue: 10
  year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0022
  article-title: Motion influence map for unusual human activity detection and localization in crowded scenes
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2015.2395752
– start-page: 2909
  year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0008
  article-title: Video anomaly detection and localization using hierarchical feature representation and gaussian process regression
  doi: 10.1007/978-1-4471-6714-3
– start-page: 14617
  year: 2016
  ident: 10.1016/j.cviu.2018.02.006_bib0062
  article-title: Abnormal event detection in crowded scenes based on deep learning
  publication-title: Multim. Tools Appl.
– year: 2012
  ident: 10.1016/j.cviu.2018.02.006_bib0049
  article-title: Crowd motion segmentation and anomaly detection via multi-label optimization
– volume: 117
  start-page: 1436
  issue: 10
  year: 2013
  ident: 10.1016/j.cviu.2018.02.006_bib0036
  article-title: An on-line, real-time learning method for detecting anomalies in videos using spatio-temporal compositions
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2013.06.007
– start-page: 1096
  year: 2008
  ident: 10.1016/j.cviu.2018.02.006_bib0053
  article-title: Extracting and composing robust features with denoising autoencoders
– start-page: 548
  year: 2017
  ident: 10.1016/j.cviu.2018.02.006_bib0058
  article-title: Learning deep event models for crowd anomaly detection
  publication-title: Neurocomputing
– year: 2016
  ident: 10.1016/j.cviu.2018.02.006_bib0044
  article-title: Fully convolutional networks for semantic segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 5017
  year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0046
  article-title: PcaNet: a simple deep learning baseline for image classification?
  publication-title: IEEE Trans. Image Process.
– volume: 28
  start-page: 1450
  issue: 9
  year: 2006
  ident: 10.1016/j.cviu.2018.02.006_bib0015
  article-title: A system for learning statistical motion patterns
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2006.176
– start-page: 675
  year: 2014
  ident: 10.1016/j.cviu.2018.02.006_bib0017
  article-title: Caffe: convolutional architecture for fast feature embedding
– start-page: 580
  year: 2014
  ident: 10.1016/j.cviu.2018.02.006_bib0013
  article-title: Rich feature hierarchies for accurate object detection and semantic segmentation
– start-page: 2112
  year: 2012
  ident: 10.1016/j.cviu.2018.02.006_bib0042
  article-title: Video anomaly detection based on local statistical aggregates
– start-page: 3449
  year: 2011
  ident: 10.1016/j.cviu.2018.02.006_bib0009
  article-title: Sparse reconstruction cost for abnormal event detection
– volume: 89
  start-page: 1723
  issue: 9
  year: 2009
  ident: 10.1016/j.cviu.2018.02.006_bib0003
  article-title: Detecting abnormal human behaviour using multiple cameras
  publication-title: Signal Process.
  doi: 10.1016/j.sigpro.2009.03.016
– ident: 10.1016/j.cviu.2018.02.006_bib0048
– volume: 115
  start-page: 1099
  issue: 8
  year: 2011
  ident: 10.1016/j.cviu.2018.02.006_bib0007
  article-title: Detecting anomalies in people’s trajectories using spectral graph analysis
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2011.03.003
– year: 2013
  ident: 10.1016/j.cviu.2018.02.006_sbref0046
  article-title: Gaussian mixtures for anomaly detection, in crowded scenes
– start-page: 1975
  year: 2010
  ident: 10.1016/j.cviu.2018.02.006_bib0027
  article-title: Anomaly detection in crowded scenes
  publication-title: Comput. Vis. Pattern Recognit.
– start-page: 2720
  year: 2013
  ident: 10.1016/j.cviu.2018.02.006_bib0026
  article-title: Abnormal event detection at 150 fps in MATLAB
– volume: 18
  start-page: 1544
  issue: 11
  year: 2008
  ident: 10.1016/j.cviu.2018.02.006_bib0033
  article-title: Trajectory-based anomalous event detection
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2008.2005599
– volume: 155
  start-page: 309
  year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0023
  article-title: Spatio-temporal context analysis within video volumes for anomalous-event detection and localization
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2014.12.064
– volume: 115
  start-page: 323
  issue: 3
  year: 2011
  ident: 10.1016/j.cviu.2018.02.006_bib0018
  article-title: Anomalous video event detection using spatiotemporal context
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2010.10.008
– volume: 30
  start-page: 555
  issue: 3
  year: 2008
  ident: 10.1016/j.cviu.2018.02.006_bib0001
  article-title: Robust real-time unusual event detection using multiple fixed-location monitors
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2007.70825
– volume: 27
  start-page: 1835
  year: 2006
  ident: 10.1016/j.cviu.2018.02.006_bib0032
  article-title: On-line trajectory clustering for anomalous events detection
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2006.02.004
– year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0056
  article-title: Learning deep representations of appearance and motion for anomalous event detection
  publication-title: BMVC
– volume: 1
  start-page: 611
  year: 2005
  ident: 10.1016/j.cviu.2018.02.006_bib0061
  article-title: Semi-supervised adapted HMMS for unusual event detection
– start-page: 2491
  year: 2013
  ident: 10.1016/j.cviu.2018.02.006_bib0064
  article-title: Context-aware modeling and recognition of activities in video
– start-page: 320
  year: 2012
  ident: 10.1016/j.cviu.2018.02.006_bib0005
  article-title: Multi-scale and real-time non-parametric approach for anomaly detection and localization
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2011.09.009
– volume: 28
  start-page: 965
  year: 2017
  ident: 10.1016/j.cviu.2018.02.006_bib0040
  article-title: Fast and accurate detection and localization of abnormal behavior in crowded scenes
– start-page: 2458
  year: 2009
  ident: 10.1016/j.cviu.2018.02.006_bib0004
  article-title: Abnormal events detection based on spatio-temporal co-occurrences
– start-page: 2415
  year: 2011
  ident: 10.1016/j.cviu.2018.02.006_bib0002
  article-title: Video parsing for abnormality detection
– start-page: 2611
  year: 2013
  ident: 10.1016/j.cviu.2018.02.006_bib0037
  article-title: Online dominant and anomalous behavior detection in videos
– ident: 10.1016/j.cviu.2018.02.006_bib0011
– start-page: 1097
  year: 2012
  ident: 10.1016/j.cviu.2018.02.006_bib0021
  article-title: ImageNet classification with deep convolutional neural networks
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 22
  start-page: 1477
  issue: 9
  year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0055
  article-title: Learning to detect anomalies in surveillance video
  publication-title: IEEE Signal Process. Lett.
  doi: 10.1109/LSP.2015.2410031
– start-page: 55
  year: 2011
  ident: 10.1016/j.cviu.2018.02.006_bib0034
  article-title: Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture
– start-page: 248
  year: 2009
  ident: 10.1016/j.cviu.2018.02.006_bib0012
  article-title: ImageNet: a large-scale hierarchical image database
– volume: 143
  start-page: 144
  year: 2014
  ident: 10.1016/j.cviu.2018.02.006_bib0057
  article-title: Video anomaly detection based on a hierarchical activity discovery within spatio-temporal contexts
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2014.06.011
– start-page: 722
  year: 2015
  ident: 10.1016/j.cviu.2018.02.006_bib0030
  article-title: Abnormality detection with improved histogram of oriented tracklets
– volume: 1
  start-page: 563
  year: 2010
  ident: 10.1016/j.cviu.2018.02.006_bib0060
  article-title: Anomalous behaviour detection using spatiotemporal oriented energies, subset inclusion histogram comparison and event-driven processing
– start-page: 935
  year: 2009
  ident: 10.1016/j.cviu.2018.02.006_bib0028
  article-title: Abnormal crowd behavior detection using social force model
SSID ssj0011491
Score 2.670943
Snippet •This paper is one of the first where fully convolutional neural network is used for anomaly detection.•Adapting a pre-trained classification CNN to an FCN for...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 88
SubjectTerms CNN
Real-time processing
Transfer learning
Video anomaly detection
Title Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes
URI https://dx.doi.org/10.1016/j.cviu.2018.02.006
Volume 172
WOSCitedRecordID wos000454184500008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect Freedom Collection
  customDbUrl:
  eissn: 1090-235X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011491
  issn: 1077-3142
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF5FLQc48CggSlu0B26R0Tq2d-3eqtIKEKo4FBQhIWvXu6ukjZ0oL2p-Sn8tsw-7bikVPXBxok12nWS-jGfW33yD0FuIQikPFQliUbAgVokGP6h1QCOdRHogibRdIr59Zicn6XCYfen1LptamPWEVVV6cZHN_qupYQyMbUpn72HudlEYgOdgdDiC2eH4T4Z_r9Qs4NW05BOr5mSSzNqyy_1pwShGxdI-WA64pRpqvjBkczutL9VSFQ0NElz1TwlxqdF98ozDRtrAt4Touwp1dyOiNCygVbdmpt3FAcCdz6cruwk7HfGy5LLFD69r_su_sriqTzuGCLV2RUWj0je2dyRhXrt92u98NOfdzYswbYmujb8lzGyTxtcdsmvm412q6_rnL86Oy_uH23c7EGfvivV4Zeh6qdNhvUVj-8a1r2UkNmS3s9yskZs1cjLIrZr75oAlGXjMzYOPR8NP7T0qyC1Dx2h1X8GXZDn24M1PcnvY0wllTp-ixz4HwQcOO89QT1Vb6InPR7D39gsYauzbjG2hRx39yufoRxdr-9giDV9DGnZIwx5pGJCGDdKwn4RbpOFxhT3SsEPaC_T1-Oj08EPg-3UERUTpMhhkgkNASKJUcUjrRZKKSNM0E4wqKUMlaVHQVEkhwXFAmmt0nlQE-YMQacREFL1EG9W0Uq8QlpnMEhZqEkoVEx1mAhJ5JRiJC0ElSbZR2PyceeHF7E1PlUn-d0Nuo347Z-akXO58d9JYKffBqAsycwDdHfNe3-ssO-jh1d9iF20s5yu1hx4U6-V4MX_jEfcbU_GwXw
linkProvider Elsevier
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-anomaly%3A+Fully+convolutional+neural+network+for+fast+anomaly+detection+in+crowded+scenes&rft.jtitle=Computer+vision+and+image+understanding&rft.au=Sabokrou%2C+Mohammad&rft.au=Fayyaz%2C+Mohsen&rft.au=Fathy%2C+Mahmood&rft.au=Moayed%2C+Zahra&rft.date=2018-07-01&rft.issn=1077-3142&rft.volume=172&rft.spage=88&rft.epage=97&rft_id=info:doi/10.1016%2Fj.cviu.2018.02.006&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_cviu_2018_02_006
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-3142&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-3142&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-3142&client=summon