Scene Text Detection Using HRNet and Spatial Attention Mechanism

To better extract the features from text instances with various shapes, a scene text detector using High Resolution Net (HRNet) and spatial attention mechanism is proposed in this paper. Specifically, we use HRNetv2-W18 as the backbone network to extract the text feature in text instances with compl...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Programming and computer software Ročník 49; číslo 8; s. 954 - 965
Hlavní autoři: Tang, Qingsong, Jiang, Zhangyan, Pan, Bolin, Guo, Jinting, Jiang, Wuming
Médium: Journal Article
Jazyk:angličtina
Vydáno: Moscow Pleiades Publishing 01.12.2023
Témata:
ISSN:0361-7688, 1608-3261
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract To better extract the features from text instances with various shapes, a scene text detector using High Resolution Net (HRNet) and spatial attention mechanism is proposed in this paper. Specifically, we use HRNetv2-W18 as the backbone network to extract the text feature in text instances with complex shapes. Considering that the scene text instance is usually small, to avoid too small feature size, we optimize HRNet through deformable convolution and Smooth Maximum Unit (SMU) activation function, so that the network can retain more detail information and location information of the text instance. In addition, a Text Region Attention Module (TRAM) is added after the backbone to make it pay more attention to the text location information and a loss function is used to TRAM, so that the network can learn the features better. The experimental results illustrate that the proposed method can compete with the state-of-the-art methods. Code is available at: https://github.com/zhangyan1005/HR-DBNet .
AbstractList To better extract the features from text instances with various shapes, a scene text detector using High Resolution Net (HRNet) and spatial attention mechanism is proposed in this paper. Specifically, we use HRNetv2-W18 as the backbone network to extract the text feature in text instances with complex shapes. Considering that the scene text instance is usually small, to avoid too small feature size, we optimize HRNet through deformable convolution and Smooth Maximum Unit (SMU) activation function, so that the network can retain more detail information and location information of the text instance. In addition, a Text Region Attention Module (TRAM) is added after the backbone to make it pay more attention to the text location information and a loss function is used to TRAM, so that the network can learn the features better. The experimental results illustrate that the proposed method can compete with the state-of-the-art methods. Code is available at: https://github.com/zhangyan1005/HR-DBNet .
Author Guo, Jinting
Jiang, Wuming
Tang, Qingsong
Pan, Bolin
Jiang, Zhangyan
Author_xml – sequence: 1
  givenname: Qingsong
  surname: Tang
  fullname: Tang, Qingsong
  email: tangqs@mail.neu.edu.cn
  organization: Department of Mathematics, College of Sciences, Northeastern University
– sequence: 2
  givenname: Zhangyan
  surname: Jiang
  fullname: Jiang, Zhangyan
  email: 1714203863@qq.com
  organization: Department of Mathematics, College of Sciences, Northeastern University
– sequence: 3
  givenname: Bolin
  surname: Pan
  fullname: Pan, Bolin
  email: 2100126@stu.neu.edu.cn
  organization: Department of Mathematics, College of Sciences, Northeastern University
– sequence: 4
  givenname: Jinting
  surname: Guo
  fullname: Guo, Jinting
  email: 2100107@stu.neu.edu.cn
  organization: Department of Mathematics, College of Sciences, Northeastern University
– sequence: 5
  givenname: Wuming
  surname: Jiang
  fullname: Jiang, Wuming
  email: jiangwuming@eyecool.cn
  organization: Beijing Eyecool Technology Co., Ltd
BookMark eNp9kM1OAjEUhRuDiYA-gLu-wOhtO8x0dhL8wQQ1EVhPOu0tlkCHtDXRt4cRV5qwOotzvpt7zoD0fOuRkGsGN4yJ_HYOomBlISUXIIEzfkb6rACZCV6wHul3dtb5F2QQ4xqAAeR5n9zNNXqkC_xK9B4T6uRaT5fR-RWdvr9iosobOt-p5NSGjlNC_5N4Qf2hvIvbS3Ju1Sbi1a8OyfLxYTGZZrO3p-fJeJZpLmXKqkKbhpdYGavzRiksSgUaLJQCDKsqgYzliLmWfASm5I1Fa5k0phLNyKARQ1Ie7-rQxhjQ1tol1f2SgnKbmkHdDVH_G-JAsj_kLritCt8nGX5k4iHrVxjqdfsZ_KHgCWgPmkRwvw
CitedBy_id crossref_primary_10_3390_f16050783
Cites_doi 10.1016/j.patcog.2021.107980
10.1109/TPAMI.2022.3155612
10.1109/TCSVT.2022.3156390
10.1109/TIP.2014.2353813
10.1016/j.jvcir.2021.103261
10.1007/s11263-020-01369-0
10.1109/TPAMI.2020.2983686
10.1016/j.patcog.2019.02.002
10.1145/129902.129906
10.1109/TIP.2019.2900589
10.1007/s11263-015-0823-z
10.1109/TPAMI.2016.2577031
10.1109/TIP.2018.2825107
10.1007/s10462-020-09930-6
10.1109/CVPR.2019.00956
10.1109/CVPR.2019.00436
10.1109/CVPR.2017.371
10.1007/978-3-319-10602-1_26
10.1109/CVPR52688.2022.00087
10.1109/CVPR.2019.01080
10.1145/3394171.3413565
10.1007/978-3-319-46484-8_4
10.1109/CVPR.2017.283
10.1609/aaai.v31i1.11196
10.1007/978-3-319-46493-0_38
10.1007/978-3-030-01264-9_5
10.1109/ICCV.2017.535
10.1007/978-3-030-01234-2_1
10.1145/3343031.3350988
10.1609/aaai.v32i1.12269
10.1109/ICDAR.2015.7333942
10.1007/978-3-030-01216-8_2
10.1109/CVPR.2018.00725
10.1109/ICDAR.2017.157
10.1109/ICDAR.2017.237
10.1109/CVPR.2019.00959
10.1609/aaai.v34i07.6812
10.1109/CVPR42600.2020.00983
10.1109/CVPR.2018.00788
10.1007/978-3-319-46448-0_2
10.1109/CVPR46437.2021.00731
10.1109/CVPR.2019.00584
10.1109/CVPR46437.2021.00314
10.1109/CVPR.2017.106
ContentType Journal Article
Copyright Pleiades Publishing, Ltd. 2023. ISSN 0361-7688, Programming and Computer Software, 2023, Vol. 49, No. 8, pp. 954–965. © Pleiades Publishing, Ltd., 2023.
Copyright_xml – notice: Pleiades Publishing, Ltd. 2023. ISSN 0361-7688, Programming and Computer Software, 2023, Vol. 49, No. 8, pp. 954–965. © Pleiades Publishing, Ltd., 2023.
DBID AAYXX
CITATION
DOI 10.1134/S0361768823080212
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1608-3261
EndPage 965
ExternalDocumentID 10_1134_S0361768823080212
GroupedDBID -59
-5G
-BR
-EM
-Y2
-~C
.86
.DC
.VR
06D
0R~
0VY
123
1N0
29P
2J2
2JN
2JY
2KG
2KM
2LR
2P1
2VQ
2~H
30V
4.4
406
408
409
40D
40E
5VS
67Z
6NX
8TC
95-
95.
95~
96X
AAAVM
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AARHV
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYTO
AAYZH
ABAKF
ABBBX
ABBXA
ABDZT
ABECU
ABFTD
ABFTV
ABHQN
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABQBU
ABQSL
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABWNU
ABXPI
ACAOD
ACBXY
ACDTI
ACGFS
ACHSB
ACHXU
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPIV
ACSNA
ACZOJ
ADHHG
ADHIR
ADINQ
ADKNI
ADKPE
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEMSY
AENEX
AEOHA
AEPYU
AETLH
AEVLU
AEXYK
AFBBN
AFGCZ
AFKRA
AFLOW
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGJBK
AGMZJ
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHSBF
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJBLW
AJRNO
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
AOCGG
ARAPS
ARMRJ
ASPBG
AVWKF
AXYYD
AZFZN
B-.
BA0
BDATZ
BENPR
BGLVJ
BGNMA
BSONS
CAG
CCPQU
COF
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
DU5
EBLON
EBS
EIOEI
EJD
ESBYG
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNWQR
GQ6
GQ7
GQ8
GXS
H13
HCIFZ
HF~
HG6
HMJXF
HQYDN
HRMNR
HVGLF
HZ~
IHE
IJ-
IKXTQ
IWAJR
IXC
IXD
IXE
IZIGR
IZQ
I~X
I~Z
J-C
JBSCW
JCJTX
JZLTJ
K7-
KDC
KOV
LAK
LLZTM
M4Y
MA-
N2Q
NB0
NPVJJ
NQJWS
NU0
O9-
O93
O9J
OAM
OVD
P2P
P9O
PF0
PT4
QOS
R89
R9I
RIG
RNI
RNS
ROL
RPX
RSV
RZC
RZE
S16
S1Z
S27
S3B
SAP
SCO
SDH
SHX
SISQX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
TEORI
TN5
TSG
TSK
TSV
TUC
U2A
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WK8
XU3
YLTOR
Z7R
Z7X
Z83
Z88
ZMTXR
~A9
AAPKM
AAYXX
ABDBE
ABFSG
ABRTQ
ACSTC
ADHKG
AEZWR
AFDZB
AFFHD
AFHIU
AFOHR
AGQPQ
AHPBZ
AHWEU
AIXLP
ATHPR
CITATION
PHGZM
PHGZT
PQGLB
ID FETCH-LOGICAL-c288t-96cdb27e9dfc4baae67a0c0f0730d1993e114ee4c8250d72bfeff18dd93b5ded3
IEDL.DBID RSV
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001149823800026&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0361-7688
IngestDate Sat Nov 29 04:55:45 EST 2025
Tue Nov 18 21:29:26 EST 2025
Fri Feb 21 02:41:26 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 8
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c288t-96cdb27e9dfc4baae67a0c0f0730d1993e114ee4c8250d72bfeff18dd93b5ded3
PageCount 12
ParticipantIDs crossref_citationtrail_10_1134_S0361768823080212
crossref_primary_10_1134_S0361768823080212
springer_journals_10_1134_S0361768823080212
PublicationCentury 2000
PublicationDate 20231200
2023-12-00
PublicationDateYYYYMMDD 2023-12-01
PublicationDate_xml – month: 12
  year: 2023
  text: 20231200
PublicationDecade 2020
PublicationPlace Moscow
PublicationPlace_xml – name: Moscow
PublicationTitle Programming and computer software
PublicationTitleAbbrev Program Comput Soft
PublicationYear 2023
Publisher Pleiades Publishing
Publisher_xml – name: Pleiades Publishing
References Khan, Sarkar, Mollah (CR1) 2021; 54
Jaderberg, Simonyan, Vedaldi, Zisserman (CR8) 2018; 116
Liao, Shi, Bai (CR7) 2018; 27
Powers (CR37) 2011; 2
CR39
CR38
Long, He, Yao (CR2) 2021; 129
CR35
CR34
Wang, Sun, Cheng, Jiang, Deng, Zhao, Xiao (CR22) 2020; 43
Liu, Zhou, Li (CR32) 2019; 15
Wu, Liu, Wan (CR33) 2021; 80
CR4
CR6
CR5
CR9
CR49
Ren, He, Girshick, Sun, Faster (CR3) 2017; 39
CR48
Liao, Zou, Wan, Yao, Bai (CR14) 2023; 45
CR47
CR45
CR44
CR43
CR42
Zhang, Zhu, Chen, Hou, Yin (CR16) 2022; 45
CR41
CR40
CR19
CR18
CR17
CR15
CR13
CR12
CR11
CR10
Vatti (CR29) 1992; 35
Xu, Wang, Zhou, Wang, Yang, Bai (CR46) 2019; 28
CR28
Lu, Yu, Qi, Chen, Gong, Xiao, Bai (CR31) 2021; 117
CR26
Liu, Jin, Zhang, Luo, Zhang (CR27) 2019; 90
CR25
CR24
CR23
Guan, Gu, Lu (CR30) 2022; 32
CR21
CR20
Yao, Bai, Liu (CR36) 2014; 23
S. Ren (3800_CR3) 2017; 39
S.X. Zhang (3800_CR16) 2022; 45
Y. Wu (3800_CR33) 2021; 80
3800_CR20
3800_CR23
3800_CR24
3800_CR21
D.M. Powers (3800_CR37) 2011; 2
M. Liao (3800_CR7) 2018; 27
3800_CR28
B.R. Vatti (3800_CR29) 1992; 35
3800_CR25
3800_CR26
T. Khan (3800_CR1) 2021; 54
3800_CR34
3800_CR35
M. Jaderberg (3800_CR8) 2018; 116
3800_CR38
3800_CR39
C. Yao (3800_CR36) 2014; 23
Y. Xu (3800_CR46) 2019; 28
S. Long (3800_CR2) 2021; 129
T. Guan (3800_CR30) 2022; 32
J. Wang (3800_CR22) 2020; 43
Z. Liu (3800_CR32) 2019; 15
3800_CR41
3800_CR42
3800_CR40
3800_CR45
3800_CR43
3800_CR44
M. Liao (3800_CR14) 2023; 45
3800_CR49
3800_CR47
3800_CR48
3800_CR9
3800_CR18
3800_CR19
Y. Liu (3800_CR27) 2019; 90
N. Lu (3800_CR31) 2021; 117
3800_CR12
3800_CR4
3800_CR13
3800_CR10
3800_CR11
3800_CR17
3800_CR5
3800_CR6
3800_CR15
References_xml – ident: CR45
– volume: 117
  start-page: 107980
  year: 2021
  ident: CR31
  article-title: Master: multi-aspect non-local network for scene text recognition
  publication-title: Pattern Recogn.
  doi: 10.1016/j.patcog.2021.107980
– ident: CR49
– ident: CR4
– ident: CR39
– volume: 45
  start-page: 919
  year: 2023
  end-page: 931
  ident: CR14
  article-title: Real-time scene text detection with differentiable binarization and adaptive scale fusion
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2022.3155612
– volume: 32
  start-page: 6073
  year: 2022
  end-page: 6085
  ident: CR30
  article-title: Industrial scene text detection with refined feature-attentive network
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2022.3156390
– ident: CR12
– ident: CR35
– volume: 23
  start-page: 4737
  year: 2014
  end-page: 4749
  ident: CR36
  article-title: A unified framework for multioriented text detection and recognition
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2014.2353813
– ident: CR25
– ident: CR42
– volume: 80
  start-page: 103261
  year: 2021
  ident: CR33
  article-title: Multiple attention encoded cascade R-CNN for scene text detection
  publication-title: J. Vis. Commun. Image Represent.
  doi: 10.1016/j.jvcir.2021.103261
– ident: CR21
– ident: CR19
– ident: CR15
– ident: CR11
– ident: CR9
– volume: 129
  start-page: 161
  year: 2021
  end-page: 184
  ident: CR2
  article-title: Scene text detection and recognition: the deep learning era
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-020-01369-0
– ident: CR5
– ident: CR26
– volume: 43
  start-page: 3349
  year: 2020
  end-page: 3364
  ident: CR22
  article-title: Deep high-resolution representation learning for visual recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2020.2983686
– volume: 90
  start-page: 337
  year: 2019
  end-page: 345
  ident: CR27
  article-title: Curved scene text detection via transverse and longitudinal sequence connection
  publication-title: Pattern Recogn.
  doi: 10.1016/j.patcog.2019.02.002
– ident: CR18
– ident: CR43
– ident: CR47
– volume: 35
  start-page: 56
  year: 1992
  end-page: 63
  ident: CR29
  article-title: A generic solution to polygon clipping
  publication-title: Commun. ACM
  doi: 10.1145/129902.129906
– ident: CR10
– ident: CR6
– ident: CR40
– volume: 45
  start-page: 2736
  year: 2022
  end-page: 2750
  ident: CR16
  article-title: Arbitrary shape text detection via segmentation with probability maps
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– ident: CR23
– volume: 28
  start-page: 5566
  year: 2019
  end-page: 5579
  ident: CR46
  article-title: Textfield: learning a deep direction field for irregular scene text detection
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2019.2900589
– volume: 15
  start-page: 1
  year: 2019
  end-page: 23
  ident: CR32
  article-title: AB-LSTM: attention-based bidirectional LSTM model for scene text detection
  publication-title: ACM Trans. Multimed. Comput. Commun. Appl.
– ident: CR44
– volume: 116
  start-page: 1
  year: 2018
  end-page: 20
  ident: CR8
  article-title: Reading text in the wild with convolutional neural networks
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-015-0823-z
– ident: CR48
– ident: CR38
– ident: CR17
– ident: CR13
– volume: 39
  start-page: 1137
  year: 2017
  end-page: 1149
  ident: CR3
  article-title: towards real-time object detection with region proposal networks
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2016.2577031
– volume: 27
  start-page: 3676
  year: 2018
  end-page: 3690
  ident: CR7
  article-title: Textboxes++: a single-shot oriented scene text detector
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2018.2825107
– ident: CR34
– volume: 54
  start-page: 3239
  year: 2021
  end-page: 3298
  ident: CR1
  article-title: Deep learning approaches to scene text detection: a comprehensive review
  publication-title: Artif. Intell. Rev.
  doi: 10.1007/s10462-020-09930-6
– ident: CR28
– ident: CR41
– ident: CR24
– ident: CR20
– volume: 2
  start-page: 47
  year: 2011
  end-page: 63
  ident: CR37
  article-title: Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
  publication-title: Int. J. Mach. Learn.
– ident: 3800_CR11
  doi: 10.1109/CVPR.2019.00956
– ident: 3800_CR17
  doi: 10.1109/CVPR.2019.00436
– volume: 35
  start-page: 56
  year: 1992
  ident: 3800_CR29
  publication-title: Commun. ACM
  doi: 10.1145/129902.129906
– ident: 3800_CR41
  doi: 10.1109/CVPR.2017.371
– ident: 3800_CR9
  doi: 10.1007/978-3-319-10602-1_26
– ident: 3800_CR35
  doi: 10.1109/CVPR52688.2022.00087
– ident: 3800_CR43
  doi: 10.1109/CVPR.2019.01080
– ident: 3800_CR44
  doi: 10.1145/3394171.3413565
– ident: 3800_CR5
  doi: 10.1007/978-3-319-46484-8_4
– volume: 2
  start-page: 47
  year: 2011
  ident: 3800_CR37
  publication-title: Int. J. Mach. Learn.
– volume: 90
  start-page: 337
  year: 2019
  ident: 3800_CR27
  publication-title: Pattern Recogn.
  doi: 10.1016/j.patcog.2019.02.002
– ident: 3800_CR38
  doi: 10.1109/CVPR.2017.283
– volume: 15
  start-page: 1
  year: 2019
  ident: 3800_CR32
  publication-title: ACM Trans. Multimed. Comput. Commun. Appl.
– ident: 3800_CR6
  doi: 10.1609/aaai.v31i1.11196
– volume: 80
  start-page: 103261
  year: 2021
  ident: 3800_CR33
  publication-title: J. Vis. Commun. Image Represent.
  doi: 10.1016/j.jvcir.2021.103261
– ident: 3800_CR26
– volume: 28
  start-page: 5566
  year: 2019
  ident: 3800_CR46
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2019.2900589
– ident: 3800_CR19
  doi: 10.1007/978-3-319-46493-0_38
– volume: 23
  start-page: 4737
  year: 2014
  ident: 3800_CR36
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2014.2353813
– ident: 3800_CR18
  doi: 10.1007/978-3-030-01264-9_5
– ident: 3800_CR15
  doi: 10.1109/ICCV.2017.535
– volume: 27
  start-page: 3676
  year: 2018
  ident: 3800_CR7
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2018.2825107
– volume: 129
  start-page: 161
  year: 2021
  ident: 3800_CR2
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-020-01369-0
– volume: 45
  start-page: 919
  year: 2023
  ident: 3800_CR14
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2022.3155612
– ident: 3800_CR34
  doi: 10.1007/978-3-030-01234-2_1
– ident: 3800_CR42
  doi: 10.1145/3343031.3350988
– ident: 3800_CR12
  doi: 10.1609/aaai.v32i1.12269
– ident: 3800_CR23
  doi: 10.1109/ICDAR.2015.7333942
– volume: 39
  start-page: 1137
  year: 2017
  ident: 3800_CR3
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2016.2577031
– volume: 43
  start-page: 3349
  year: 2020
  ident: 3800_CR22
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2020.2983686
– ident: 3800_CR40
  doi: 10.1007/978-3-030-01216-8_2
– ident: 3800_CR20
– volume: 116
  start-page: 1
  year: 2018
  ident: 3800_CR8
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-015-0823-z
– ident: 3800_CR48
  doi: 10.1109/CVPR.2018.00725
– ident: 3800_CR24
  doi: 10.1109/ICDAR.2017.157
– ident: 3800_CR25
  doi: 10.1109/ICDAR.2017.237
– volume: 45
  start-page: 2736
  year: 2022
  ident: 3800_CR16
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– ident: 3800_CR47
  doi: 10.1109/CVPR.2019.00959
– ident: 3800_CR13
  doi: 10.1609/aaai.v34i07.6812
– ident: 3800_CR45
  doi: 10.1109/CVPR42600.2020.00983
– ident: 3800_CR49
  doi: 10.1109/CVPR.2018.00788
– ident: 3800_CR4
  doi: 10.1007/978-3-319-46448-0_2
– ident: 3800_CR10
  doi: 10.1109/CVPR46437.2021.00731
– ident: 3800_CR28
  doi: 10.1109/CVPR.2019.00584
– ident: 3800_CR39
  doi: 10.1109/CVPR46437.2021.00314
– volume: 32
  start-page: 6073
  year: 2022
  ident: 3800_CR30
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2022.3156390
– ident: 3800_CR21
  doi: 10.1109/CVPR.2017.106
– volume: 54
  start-page: 3239
  year: 2021
  ident: 3800_CR1
  publication-title: Artif. Intell. Rev.
  doi: 10.1007/s10462-020-09930-6
– volume: 117
  start-page: 107980
  year: 2021
  ident: 3800_CR31
  publication-title: Pattern Recogn.
  doi: 10.1016/j.patcog.2021.107980
SSID ssj0010044
Score 2.2883604
Snippet To better extract the features from text instances with various shapes, a scene text detector using High Resolution Net (HRNet) and spatial attention mechanism...
SourceID crossref
springer
SourceType Enrichment Source
Index Database
Publisher
StartPage 954
SubjectTerms Artificial Intelligence
Computer Science
Operating Systems
Software Engineering
Software Engineering/Programming and Operating Systems
Title Scene Text Detection Using HRNet and Spatial Attention Mechanism
URI https://link.springer.com/article/10.1134/S0361768823080212
Volume 49
WOSCitedRecordID wos001149823800026&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: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1608-3261
  dateEnd: 20241214
  omitProxy: false
  ssIdentifier: ssj0010044
  issn: 0361-7688
  databaseCode: K7-
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest advanced technologies & aerospace journals
  customDbUrl:
  eissn: 1608-3261
  dateEnd: 20241214
  omitProxy: false
  ssIdentifier: ssj0010044
  issn: 0361-7688
  databaseCode: P5Z
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1608-3261
  dateEnd: 20241214
  omitProxy: false
  ssIdentifier: ssj0010044
  issn: 0361-7688
  databaseCode: BENPR
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerLink Contemporary
  customDbUrl:
  eissn: 1608-3261
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0010044
  issn: 0361-7688
  databaseCode: RSV
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB5s9eDF-sT6KHvwpAST7Cab3BS1FNQitpbewmZ3FgoapYn-fnfzKBQfoPfZJUx2Zmf4vp0P4ERzSgNPmO6EBYHDpB85qTI_hFMtXK5YFJZwweSOD4fRdBo_1O-484bt3kCSZaaudEfY-cjkWs8UxxYZiuxg8hasBnbYjG3RR5MFdGAhygqg9BxrXkOZ326xfBktI6HlBdPv_OvTNmGjrifJZXUAtmAFs23oNFoNpA7dHbgYSZPVyNjkYnKNRUnAykhJGCCDxyEWRGSKWIHimd2uKCoaJLlH-zR4lr_swlP_Znw1cGr1BMc4PCqcOJQq9TnGSkuWCoEhF650tY1pZWl7aFohRCZNj-gq7qcatfYipWKaBgoV3YN29prhPhAuU5d5aColSZmv_SgNYyqkRmFWeBK74DZuTGQ9WtwqXDwnZYtBWfLFQ104XSx5q-Zq_GZ81vg9qUMs_9n64E_Wh7BuFeQrhsoRtIv5Ox7DmvwoZvm8B61b7vTKA_YJd1jFtw
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8QwEB50FfTi-sT1mYMnpdg2adPeFB-suFvEXZe9lTaZwIJW2VZ_v0kfC4sP0PsklGlmMsP3ZT6AE8Up9ZxEdyfM8ywm3MBKpf4hnKrE5pIFfgkXjHo8ioLxOHyo33HnDdu9gSTLTF3pjrDzgc61ji6ODTIUmMHki7DEjMqOadEHoxl0YCDKCqB0LGNeQ5nfbjF_Gc0joeUFc9v-16etw1pdT5LL6gBswAJmm9ButBpIHbpbcDEQOquRoc7F5BqLkoCVkZIwQLqPERYkySQxAsUTs11RVDRI0kfzNHiSv2zD0-3N8Kpr1eoJlnZ4UFihL2TqcgylEixNEvR5YgtbmZiWhraHuhVCZEL3iLbkbqpQKSeQMqSpJ1HSHWhlrxnuAuEitZmDulISlLnKDVI_pIlQmOgVjsAO2I0bY1GPFjcKF89x2WJQFn_xUAdOZ0veqrkavxmfNX6P6xDLf7be-5P1Max0h_1e3LuL7vdh1ajJV2yVA2gV03c8hGXxUUzy6VF5zD4BHmjHyw
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFA46RXxxXnFe8-CTUmybtGnfFOeYOMvY5thbSXOBgdaxRn-_SZsOhhcQ309CSHJOzuH7cj4ALiRBKPCork5wEDiY-ZGTcX0gBEnqEo6jsIQLxj2SJNFkEvetzmlRs91rSLL602C6NOXqesal1SDB10Mddz2dKBuUKDJNylfBGtaFjOF0DYbjBYxg4MoKrPQcY25hzW-nWH6YllHR8rHpNP-9zG2wZfNMeFtdjB2wIvJd0Kw1HKB16T1wM2Q62sGRjtGwLVRJzMphSSSA3UEiFKQ5h0a4eGqmU6qiR8InYb4MT4vXffDcuR_ddR2rquDog4iUE4eMZz4RMZcMZ5SKkFCXudL4Ojd0PqFLJCEw07Wjy4mfSSGlF3EeoyzggqMD0MjfcnEIIGGZiz2hMyiGsC_9KAtjRJkUVI_wmGgBt97SlNmW40b54iUtSw-E0y871AKXiyGzqt_Gb8ZX9Rmk1vWKn62P_mR9Djb67U7ae0gej8GmEZmvSCwnoKHm7-IUrLMPNS3mZ-WN-wRCqtCv
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=Scene+Text+Detection+Using+HRNet+and+Spatial+Attention+Mechanism&rft.jtitle=Programming+and+computer+software&rft.au=Tang%2C+Qingsong&rft.au=Jiang%2C+Zhangyan&rft.au=Pan%2C+Bolin&rft.au=Guo%2C+Jinting&rft.date=2023-12-01&rft.issn=0361-7688&rft.eissn=1608-3261&rft.volume=49&rft.issue=8&rft.spage=954&rft.epage=965&rft_id=info:doi/10.1134%2FS0361768823080212&rft.externalDBID=n%2Fa&rft.externalDocID=10_1134_S0361768823080212
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0361-7688&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0361-7688&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0361-7688&client=summon