Detecting spatiotemporal irregularities in videos via a 3D convolutional autoencoder

Spatiotemporal irregularities (i.e., the uncommon appearance and motion patterns) in videos are difficult to detect, as they are usually not well defined and appear rarely in videos. We tackle this problem by learning normal patterns from regular videos, while treating irregularities as deviations f...

Full description

Saved in:
Bibliographic Details
Published in:Journal of visual communication and image representation Vol. 67; p. 102747
Main Authors: Yan, Mengjia, Meng, Jingjing, Zhou, Chunluan, Tu, Zhigang, Tan, Yap-Peng, Yuan, Junsong
Format: Journal Article
Language:English
Published: Elsevier Inc 01.02.2020
Subjects:
ISSN:1047-3203, 1095-9076
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Spatiotemporal irregularities (i.e., the uncommon appearance and motion patterns) in videos are difficult to detect, as they are usually not well defined and appear rarely in videos. We tackle this problem by learning normal patterns from regular videos, while treating irregularities as deviations from normal patterns. To this end, we introduce a 3D fully convolutional autoencoder (3D-FCAE) that is trainable in an end-to-end manner to detect both temporal and spatiotemporal irregularities in videos using limited training data. Subsequently, temporal irregularities can be detected as frames with high reconstruction errors, and irregular spatiotemporal patterns can be detected as blurry regions that are not well reconstructed. Our approach can accurately locate temporal and spatiotemporal irregularities thanks to the 3D fully convolutional autoencoder and the explored effective architecture. We evaluate the proposed autoencoder for detecting irregular patterns on benchmark video datasets with weak supervision. Comparisons with state-of-the-art approaches demonstrate the effectiveness of our approach. Moreover, the learned autoencoder shows good generalizability across multiple datasets.
AbstractList Spatiotemporal irregularities (i.e., the uncommon appearance and motion patterns) in videos are difficult to detect, as they are usually not well defined and appear rarely in videos. We tackle this problem by learning normal patterns from regular videos, while treating irregularities as deviations from normal patterns. To this end, we introduce a 3D fully convolutional autoencoder (3D-FCAE) that is trainable in an end-to-end manner to detect both temporal and spatiotemporal irregularities in videos using limited training data. Subsequently, temporal irregularities can be detected as frames with high reconstruction errors, and irregular spatiotemporal patterns can be detected as blurry regions that are not well reconstructed. Our approach can accurately locate temporal and spatiotemporal irregularities thanks to the 3D fully convolutional autoencoder and the explored effective architecture. We evaluate the proposed autoencoder for detecting irregular patterns on benchmark video datasets with weak supervision. Comparisons with state-of-the-art approaches demonstrate the effectiveness of our approach. Moreover, the learned autoencoder shows good generalizability across multiple datasets.
ArticleNumber 102747
Author Meng, Jingjing
Zhou, Chunluan
Tan, Yap-Peng
Tu, Zhigang
Yan, Mengjia
Yuan, Junsong
Author_xml – sequence: 1
  givenname: Mengjia
  orcidid: 0000-0002-6729-6518
  surname: Yan
  fullname: Yan, Mengjia
  email: YANM0006@e.ntu.edu.sg
  organization: School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave., Singapore 639798, Singapore
– sequence: 2
  givenname: Jingjing
  surname: Meng
  fullname: Meng, Jingjing
  email: jmeng2@buffalo.edu
  organization: Computer Science and Engineering Department, University at Buffalo, the State University of New York, United States
– sequence: 3
  givenname: Chunluan
  surname: Zhou
  fullname: Zhou, Chunluan
  email: chunluan@buffalo.edu
  organization: Computer Science and Engineering Department, University at Buffalo, the State University of New York, United States
– sequence: 4
  givenname: Zhigang
  orcidid: 0000-0002-4395-6614
  surname: Tu
  fullname: Tu, Zhigang
  email: tuzhigang@whu.edu.cn
  organization: State Key Lab of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Ruoyu Road 129, Wuhan, China
– sequence: 5
  givenname: Yap-Peng
  surname: Tan
  fullname: Tan, Yap-Peng
  email: eyptan@ntu.edu.sg
  organization: School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave., Singapore 639798, Singapore
– sequence: 6
  givenname: Junsong
  surname: Yuan
  fullname: Yuan, Junsong
  email: jsyuan@buffalo.edu
  organization: Computer Science and Engineering Department, University at Buffalo, the State University of New York, United States
BookMark eNqFkMtOwzAQRS0EEm3hC9jkB1LGjzy8YIFaXlIlNmVtuc6kcpTale1G4u9JKCsWsLqj0ZyR7pmTS-cdEnJHYUmBlvfdshuMDUsGVI4bVonqgswoyCKXUJWX0yyqnDPg12QeYwcAXHIxI9s1JjTJun0WjzpZn_Bw9EH3mQ0B96deB5ssxsy6bLAN-jiGznTG15nxbvD9aYTceK9PyaMzvsFwQ65a3Ue8_ckF-Xh-2q5e8837y9vqcZMbDjzlRjBtCmxqXhojABoNdYEUClYWFXIppDFY0Z2UYqf5zrR13TJKG8YEsEIwviDy_NcEH2PAVhmbphIuBW17RUFNelSnvvWoSY866xlZ_os9BnvQ4fMf6uFM4VhrsBhUNHZsjY0No0bVePsn_wWPZYNP
CitedBy_id crossref_primary_10_1007_s10489_025_06797_4
crossref_primary_10_1007_s11063_022_11120_0
crossref_primary_10_1016_j_jvcir_2021_103201
crossref_primary_10_1016_j_jvcir_2023_103860
crossref_primary_10_3390_electronics13132579
Cites_doi 10.1109/CVPR.2009.5206641
10.1109/CVPR.2016.86
10.5244/C.29.8
10.1109/TPAMI.2013.111
10.1109/CVPR.2018.00678
10.1109/CVPR.2009.5206569
10.1109/CVPR.2018.00572
10.1109/CVPR.2011.5995434
10.1109/CVPR.2018.00684
10.1016/j.cviu.2010.10.008
10.1109/CVPR.2015.7298965
10.1109/TPAMI.2013.137
10.1109/ICPR.2018.8546039
10.1109/TIFS.2013.2272243
10.1007/978-3-642-35289-8_3
10.1109/CVPR.2015.7298878
10.1109/ICCV.2015.510
10.1109/LSP.2015.2410031
10.1109/CVPR.2010.5539872
10.1109/CVPR.2010.5539882
10.1109/CVPR.2009.5206771
10.1145/2647868.2654889
10.1007/978-3-319-24574-4_28
10.1109/ICCV.2013.338
10.1109/CVPR.2018.00145
10.1109/TCSVT.2008.2005599
10.1109/TIP.2017.2670780
ContentType Journal Article
Copyright 2020 Elsevier Inc.
Copyright_xml – notice: 2020 Elsevier Inc.
DBID AAYXX
CITATION
DOI 10.1016/j.jvcir.2019.102747
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Journalism & Communications
Engineering
EISSN 1095-9076
ExternalDocumentID 10_1016_j_jvcir_2019_102747
S1047320319303682
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
29L
4.4
457
4G.
53G
5GY
5VS
7-5
71M
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABFNM
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADFGL
ADJOM
ADMHC
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
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
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG5
LX9
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
WH7
WUQ
XPP
YQT
ZMT
ZU3
~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
~HD
ID FETCH-LOGICAL-c303t-c42ac5ed836cc400da085e1052657e3949cce71b994ba3bcf88f211d224025423
ISICitedReferencesCount 8
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000521653800011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1047-3203
IngestDate Tue Nov 18 22:30:30 EST 2025
Sat Nov 29 07:10:00 EST 2025
Fri Feb 23 02:49:13 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Spatiotemporal irregularity detection
3D convolution
Autoencoder
Real-time
Anomaly detection
Unsupervised learning
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c303t-c42ac5ed836cc400da085e1052657e3949cce71b994ba3bcf88f211d224025423
ORCID 0000-0002-4395-6614
0000-0002-6729-6518
ParticipantIDs crossref_citationtrail_10_1016_j_jvcir_2019_102747
crossref_primary_10_1016_j_jvcir_2019_102747
elsevier_sciencedirect_doi_10_1016_j_jvcir_2019_102747
PublicationCentury 2000
PublicationDate February 2020
2020-02-00
PublicationDateYYYYMMDD 2020-02-01
PublicationDate_xml – month: 02
  year: 2020
  text: February 2020
PublicationDecade 2020
PublicationTitle Journal of visual communication and image representation
PublicationYear 2020
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in: International Conference on Medical image computing and computer-assisted intervention, Springer, 2015, pp. 234–241.
accessed, pp. 11–01, 2015.
R. Mehran, A. Oyama, M. Shah, Abnormal crowd behavior detection using social force model, in: CVPR, 2009, pp. 935–942.
C. Lu, J. Shi, J. Jia, Abnormal event detection at 150 fps in matlab, in: ICCV, 2013, pp. 2720–2727.
M. Hasan, J. Choi, J. Neumann, A.K. Roy-Chowdhury, L.S. Davis, Learning temporal regularity in video sequences, in: CVPR, 2016, pp. 733–742.
J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in: CVPR, 2015, pp. 3431–3440.
Y.A. LeCun, L. Bottou, G.B. Orr, K.-R. Müller, Efficient backprop, in: Neural networks: Tricks of the trade, Springer, 2012, pp. 9–48.
A. Radford, L. Metz, S. Chintala, Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv preprint arXiv:1511.06434, 2015.
Y. Cong, J. Yuan, J. Liu, Sparse reconstruction cost for abnormal event detection, in: CVPR, 2011, pp. 3449–3456.
L. Kratz, K. Nishino, Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models, in: CVPR, 2009, pp. 1446–1453.
V. Mahadevan, W. Li, V. Bhalodia, N. Vasconcelos, Anomaly detection in crowded scenes, in: CVPR, 2010, pp. 1975–1981.
W. Liu, W. Luo, D. Lian, S. Gao, Future frame prediction for anomaly detection--a new baseline, arXiv preprint arXiv:1712.09867, 2017.
S. Wu, B.E. Moore, M. Shah, Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes, in: CVPR, 2010, pp. 2054–2060.
M. Yan, X. Jiang, J. Yuan, 3d convolutional generative adversarial networks for detecting temporal irregularities in videos, in: ICPR, 2018.
D. Tran, L. Bourdev, R. Fergus, L. Torresani, M. Paluri, Learning spatiotemporal features with 3d convolutional networks, in: ICCV, 2015, pp. 4489–4497.
I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial nets, in: NIPS, 2014, pp. 2672–2680.
Jiang, Wu, Katsaggelos (b0050) 2009; 18
W. Hong, Z. Wang, M. Yang, J. Yuan, Conditional generative adversarial network for structured domain adaptation, in: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2018.
Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, T. Darrell, Caffe: Convolutional architecture for fast feature embedding, in: ACM MM, 2014, pp. 675–678.
Xiao, Zhang, Zha (b0090) 2015; 22
Tran, Yuan, Forsyth (b0150) 2014; 36
M. Sabokrou, M. Fayyaz, M. Fathy, R. Klette, Deep-cascade: Cascading 3d deep neural networks for fast anomaly detection and localization in crowded scenes, TIP, 2017.
S. Li, W. Li, C. Cook, C. Zhu, Y. Gao, Independently recurrent neural network (indrnn): Building a longer and deeper rnn, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 5457–5466.
W. Sultani, C. Chen, M. Shah, Real-world anomaly detection in surveillance videos, in: Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), 2018.
Y. Kozlov, T. Weinkauf, Persistence1d: Extracting and filtering minima and maxima of 1d functions
Li, Mahadevan, Vasconcelos (b0020) 2014; 36
Cong, Yuan, Tang (b0030) 2013; 8
Piciarelli, Micheloni, Foresti (b0045) 2008; 18
J. Donahue, L. Anne Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan, K. Saenko, T. Darrell, Long-term recurrent convolutional networks for visual recognition and description, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 2625–2634.
D. Xu, E. Ricci, Y. Yan, J. Song, N. Sebe, Learning deep representations of appearance and motion for anomalous event detection, in: BMVC, 2015.
Jiang, Yuan, Tsaftaris, Katsaggelos (b0035) 2011; 115
J. Kim, K. Grauman, Observe locally, infer globally: a space-time mrf for detecting abnormal activities with incremental updates, in: CVPR, 2009, pp. 2921–2928.
S. Ioffe, C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint arXiv:1502.03167, 2015.
Calderara, Heinemann, Prati, Cucchiara, Tishby (b0055) 2011; 115
Jiang (10.1016/j.jvcir.2019.102747_b0050) 2009; 18
Tran (10.1016/j.jvcir.2019.102747_b0150) 2014; 36
10.1016/j.jvcir.2019.102747_b0080
10.1016/j.jvcir.2019.102747_b0160
10.1016/j.jvcir.2019.102747_b0060
10.1016/j.jvcir.2019.102747_b0155
10.1016/j.jvcir.2019.102747_b0110
10.1016/j.jvcir.2019.102747_b0135
10.1016/j.jvcir.2019.102747_b0095
10.1016/j.jvcir.2019.102747_b0010
10.1016/j.jvcir.2019.102747_b0075
10.1016/j.jvcir.2019.102747_b0130
10.1016/j.jvcir.2019.102747_b0115
10.1016/j.jvcir.2019.102747_b0015
Cong (10.1016/j.jvcir.2019.102747_b0030) 2013; 8
10.1016/j.jvcir.2019.102747_b0070
Xiao (10.1016/j.jvcir.2019.102747_b0090) 2015; 22
Li (10.1016/j.jvcir.2019.102747_b0020) 2014; 36
10.1016/j.jvcir.2019.102747_b0100
10.1016/j.jvcir.2019.102747_b0165
10.1016/j.jvcir.2019.102747_b0025
10.1016/j.jvcir.2019.102747_b0145
10.1016/j.jvcir.2019.102747_b0085
10.1016/j.jvcir.2019.102747_b0140
10.1016/j.jvcir.2019.102747_b0040
Calderara (10.1016/j.jvcir.2019.102747_b0055) 2011; 115
10.1016/j.jvcir.2019.102747_b0065
10.1016/j.jvcir.2019.102747_b0120
Piciarelli (10.1016/j.jvcir.2019.102747_b0045) 2008; 18
10.1016/j.jvcir.2019.102747_b0005
10.1016/j.jvcir.2019.102747_b0125
Jiang (10.1016/j.jvcir.2019.102747_b0035) 2011; 115
10.1016/j.jvcir.2019.102747_b0105
References_xml – reference: W. Hong, Z. Wang, M. Yang, J. Yuan, Conditional generative adversarial network for structured domain adaptation, in: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2018.
– reference: O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in: International Conference on Medical image computing and computer-assisted intervention, Springer, 2015, pp. 234–241.
– reference: Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, T. Darrell, Caffe: Convolutional architecture for fast feature embedding, in: ACM MM, 2014, pp. 675–678.
– reference: R. Mehran, A. Oyama, M. Shah, Abnormal crowd behavior detection using social force model, in: CVPR, 2009, pp. 935–942.
– reference: A. Radford, L. Metz, S. Chintala, Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv preprint arXiv:1511.06434, 2015.
– volume: 22
  start-page: 1477
  year: 2015
  end-page: 1481
  ident: b0090
  article-title: Learning to detect anomalies in surveillance video
  publication-title: IEEE Signal Process. Lett.
– reference: D. Tran, L. Bourdev, R. Fergus, L. Torresani, M. Paluri, Learning spatiotemporal features with 3d convolutional networks, in: ICCV, 2015, pp. 4489–4497.
– reference: S. Ioffe, C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint arXiv:1502.03167, 2015.
– reference: Y.A. LeCun, L. Bottou, G.B. Orr, K.-R. Müller, Efficient backprop, in: Neural networks: Tricks of the trade, Springer, 2012, pp. 9–48.
– reference: I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial nets, in: NIPS, 2014, pp. 2672–2680.
– reference: Y. Cong, J. Yuan, J. Liu, Sparse reconstruction cost for abnormal event detection, in: CVPR, 2011, pp. 3449–3456.
– volume: 115
  start-page: 323
  year: 2011
  end-page: 333
  ident: b0035
  article-title: Anomalous video event detection using spatiotemporal context
  publication-title: Comput. Vision Image Underst.
– volume: 18
  start-page: 907
  year: 2009
  end-page: 913
  ident: b0050
  article-title: A dynamic hierarchical clustering method for trajectory-based unusual video event detection
  publication-title: TIP
– reference: M. Sabokrou, M. Fayyaz, M. Fathy, R. Klette, Deep-cascade: Cascading 3d deep neural networks for fast anomaly detection and localization in crowded scenes, TIP, 2017.
– reference: Y. Kozlov, T. Weinkauf, Persistence1d: Extracting and filtering minima and maxima of 1d functions,
– reference: J. Donahue, L. Anne Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan, K. Saenko, T. Darrell, Long-term recurrent convolutional networks for visual recognition and description, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 2625–2634.
– volume: 36
  start-page: 404
  year: 2014
  end-page: 416
  ident: b0150
  article-title: Video event detection: From subvolume localization to spatiotemporal path search
  publication-title: TPAMI
– volume: 36
  start-page: 18
  year: 2014
  end-page: 32
  ident: b0020
  article-title: Anomaly detection and localization in crowded scenes
  publication-title: TPAMI
– reference: J. Kim, K. Grauman, Observe locally, infer globally: a space-time mrf for detecting abnormal activities with incremental updates, in: CVPR, 2009, pp. 2921–2928.
– reference: M. Yan, X. Jiang, J. Yuan, 3d convolutional generative adversarial networks for detecting temporal irregularities in videos, in: ICPR, 2018.
– reference: , accessed, pp. 11–01, 2015.
– volume: 8
  start-page: 1590
  year: 2013
  end-page: 1599
  ident: b0030
  article-title: Video anomaly search in crowded scenes via spatio-temporal motion context
  publication-title: IEEE Trans. Inform. Forensics Sec.
– reference: M. Hasan, J. Choi, J. Neumann, A.K. Roy-Chowdhury, L.S. Davis, Learning temporal regularity in video sequences, in: CVPR, 2016, pp. 733–742.
– volume: 115
  start-page: 1099
  year: 2011
  end-page: 1111
  ident: b0055
  article-title: Detecting anomalies in people’s trajectories using spectral graph analysis
  publication-title: CVIU
– reference: C. Lu, J. Shi, J. Jia, Abnormal event detection at 150 fps in matlab, in: ICCV, 2013, pp. 2720–2727.
– reference: S. Li, W. Li, C. Cook, C. Zhu, Y. Gao, Independently recurrent neural network (indrnn): Building a longer and deeper rnn, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 5457–5466.
– reference: V. Mahadevan, W. Li, V. Bhalodia, N. Vasconcelos, Anomaly detection in crowded scenes, in: CVPR, 2010, pp. 1975–1981.
– reference: D. Xu, E. Ricci, Y. Yan, J. Song, N. Sebe, Learning deep representations of appearance and motion for anomalous event detection, in: BMVC, 2015.
– reference: W. Sultani, C. Chen, M. Shah, Real-world anomaly detection in surveillance videos, in: Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), 2018.
– reference: J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in: CVPR, 2015, pp. 3431–3440.
– reference: W. Liu, W. Luo, D. Lian, S. Gao, Future frame prediction for anomaly detection--a new baseline, arXiv preprint arXiv:1712.09867, 2017.
– reference: L. Kratz, K. Nishino, Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models, in: CVPR, 2009, pp. 1446–1453.
– volume: 18
  start-page: 1544
  year: 2008
  end-page: 1554
  ident: b0045
  article-title: Trajectory-based anomalous event detection
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– reference: S. Wu, B.E. Moore, M. Shah, Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes, in: CVPR, 2010, pp. 2054–2060.
– ident: 10.1016/j.jvcir.2019.102747_b0025
  doi: 10.1109/CVPR.2009.5206641
– ident: 10.1016/j.jvcir.2019.102747_b0075
  doi: 10.1109/CVPR.2016.86
– ident: 10.1016/j.jvcir.2019.102747_b0065
  doi: 10.5244/C.29.8
– volume: 36
  start-page: 18
  issue: 1
  year: 2014
  ident: 10.1016/j.jvcir.2019.102747_b0020
  article-title: Anomaly detection and localization in crowded scenes
  publication-title: TPAMI
  doi: 10.1109/TPAMI.2013.111
– ident: 10.1016/j.jvcir.2019.102747_b0095
  doi: 10.1109/CVPR.2018.00678
– volume: 115
  start-page: 1099
  issue: 8
  year: 2011
  ident: 10.1016/j.jvcir.2019.102747_b0055
  article-title: Detecting anomalies in people’s trajectories using spectral graph analysis
  publication-title: CVIU
– ident: 10.1016/j.jvcir.2019.102747_b0105
– ident: 10.1016/j.jvcir.2019.102747_b0085
  doi: 10.1109/CVPR.2009.5206569
– ident: 10.1016/j.jvcir.2019.102747_b0130
  doi: 10.1109/CVPR.2018.00572
– ident: 10.1016/j.jvcir.2019.102747_b0140
– ident: 10.1016/j.jvcir.2019.102747_b0005
  doi: 10.1109/CVPR.2011.5995434
– ident: 10.1016/j.jvcir.2019.102747_b0100
  doi: 10.1109/CVPR.2018.00684
– volume: 115
  start-page: 323
  issue: 3
  year: 2011
  ident: 10.1016/j.jvcir.2019.102747_b0035
  article-title: Anomalous video event detection using spatiotemporal context
  publication-title: Comput. Vision Image Underst.
  doi: 10.1016/j.cviu.2010.10.008
– ident: 10.1016/j.jvcir.2019.102747_b0135
  doi: 10.1109/CVPR.2015.7298965
– volume: 36
  start-page: 404
  issue: 2
  year: 2014
  ident: 10.1016/j.jvcir.2019.102747_b0150
  article-title: Video event detection: From subvolume localization to spatiotemporal path search
  publication-title: TPAMI
  doi: 10.1109/TPAMI.2013.137
– ident: 10.1016/j.jvcir.2019.102747_b0115
  doi: 10.1109/ICPR.2018.8546039
– ident: 10.1016/j.jvcir.2019.102747_b0155
– volume: 8
  start-page: 1590
  issue: 10
  year: 2013
  ident: 10.1016/j.jvcir.2019.102747_b0030
  article-title: Video anomaly search in crowded scenes via spatio-temporal motion context
  publication-title: IEEE Trans. Inform. Forensics Sec.
  doi: 10.1109/TIFS.2013.2272243
– ident: 10.1016/j.jvcir.2019.102747_b0165
  doi: 10.1007/978-3-642-35289-8_3
– ident: 10.1016/j.jvcir.2019.102747_b0125
  doi: 10.1109/CVPR.2015.7298878
– ident: 10.1016/j.jvcir.2019.102747_b0080
  doi: 10.1109/ICCV.2015.510
– volume: 22
  start-page: 1477
  issue: 9
  year: 2015
  ident: 10.1016/j.jvcir.2019.102747_b0090
  article-title: Learning to detect anomalies in surveillance video
  publication-title: IEEE Signal Process. Lett.
  doi: 10.1109/LSP.2015.2410031
– volume: 18
  start-page: 907
  issue: 4
  year: 2009
  ident: 10.1016/j.jvcir.2019.102747_b0050
  article-title: A dynamic hierarchical clustering method for trajectory-based unusual video event detection
  publication-title: TIP
– ident: 10.1016/j.jvcir.2019.102747_b0015
  doi: 10.1109/CVPR.2010.5539872
– ident: 10.1016/j.jvcir.2019.102747_b0060
  doi: 10.1109/CVPR.2010.5539882
– ident: 10.1016/j.jvcir.2019.102747_b0040
  doi: 10.1109/CVPR.2009.5206771
– ident: 10.1016/j.jvcir.2019.102747_b0160
  doi: 10.1145/2647868.2654889
– ident: 10.1016/j.jvcir.2019.102747_b0120
  doi: 10.1007/978-3-319-24574-4_28
– ident: 10.1016/j.jvcir.2019.102747_b0145
– ident: 10.1016/j.jvcir.2019.102747_b0010
  doi: 10.1109/ICCV.2013.338
– ident: 10.1016/j.jvcir.2019.102747_b0110
  doi: 10.1109/CVPR.2018.00145
– volume: 18
  start-page: 1544
  issue: 11
  year: 2008
  ident: 10.1016/j.jvcir.2019.102747_b0045
  article-title: Trajectory-based anomalous event detection
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2008.2005599
– ident: 10.1016/j.jvcir.2019.102747_b0070
  doi: 10.1109/TIP.2017.2670780
SSID ssj0003934
Score 2.334182
Snippet Spatiotemporal irregularities (i.e., the uncommon appearance and motion patterns) in videos are difficult to detect, as they are usually not well defined and...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 102747
SubjectTerms 3D convolution
Anomaly detection
Autoencoder
Real-time
Spatiotemporal irregularity detection
Unsupervised learning
Title Detecting spatiotemporal irregularities in videos via a 3D convolutional autoencoder
URI https://dx.doi.org/10.1016/j.jvcir.2019.102747
Volume 67
WOSCitedRecordID wos000521653800011&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: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1095-9076
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003934
  issn: 1047-3203
  databaseCode: AIEXJ
  dateStart: 19950301
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Nb9NAEF2FlgMcEC0gSqHaA-ISXNleO_YeK1IEPVQcghS4WOvxGhylTmXHUX8GP5nZDzs2raL2wMVOVuvNKvO88zyeeUvIe8GiNHYBHDeLcicAjrcUEmXHn0gIuQtcQKo3m4guL-P5nH8bjf60tTCbZVSW8c0Nv_6vpsY2NLYqnX2AubtBsQE_o9HxiGbH470MP5XqvYAOE-hsaSs-tRwXVaU3nq-0iKoKdKgavFWNJzEWYzbVKeh2bkpCoFmvlMxlZhN4b1PYTVE3Wl-kV2Ri3kZcqVQgLZjZFjd1IPxhQq4qnXZRdE5BfdWIKlSzdac6oL1qTFpAUy6bLZRnuvXn7-KXsJ1t6AKfU90uDcSstkomgvku6y_HZncOu556-qn5zqXeRB0Wp4sNFErY1eOn295DYe1_HF6XhthmuC0SPUiiBknMII_Ivh-FHNfJ_bOv5_OLzrszbjIV2qm3SlY6Z_DWXO5mOz0GM3tOnlm70TMDmQMykuUhedoTpDwkx7ZTUV_RD3RQPFS_ILMOWnQILTqEFi1KaqCFJ0EFZVM6gBbtQesl-f75fPbpi2N35XAA6c7agcAXEMosZhMA9ACZQNYuPaUbFEaS8YADyMhLOQ9SwVLI4zj3PS9T3NEPkb2_InvlqpSvCZUTHsucZ2kQQIBdODARZcixg1TmgkdHxG__vQSsZL3aOWWZ7LDcEfnYXXRtFFt2d5-0Zkks6TRkMkGg7brwzcN-55g82d4Cb8neumrkO_IYNuuirk4syv4CpF-pWQ
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=Detecting+spatiotemporal+irregularities+in+videos+via+a+3D+convolutional+autoencoder&rft.jtitle=Journal+of+visual+communication+and+image+representation&rft.au=Yan%2C+Mengjia&rft.au=Meng%2C+Jingjing&rft.au=Zhou%2C+Chunluan&rft.au=Tu%2C+Zhigang&rft.date=2020-02-01&rft.issn=1047-3203&rft.volume=67&rft.spage=102747&rft_id=info:doi/10.1016%2Fj.jvcir.2019.102747&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_jvcir_2019_102747
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1047-3203&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1047-3203&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1047-3203&client=summon