Two-stream lightweight sign language transformer

Despite the recent progress of continuous sign language translation-based video, a variety of deep learning models are difficult to apply to the real-time translation in the limit computing resource. We present the two-stream lightweight sign transformer network model for recognizing and translating...

Full description

Saved in:
Bibliographic Details
Published in:Machine vision and applications Vol. 33; no. 5
Main Authors: Chen, Yuming, Mei, Xue, Qin, Xuan
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2022
Springer Nature B.V
Subjects:
ISSN:0932-8092, 1432-1769
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Despite the recent progress of continuous sign language translation-based video, a variety of deep learning models are difficult to apply to the real-time translation in the limit computing resource. We present the two-stream lightweight sign transformer network model for recognizing and translating continuous sign language. This lightweight framework can obtain both static spatial information and all body dynamic features of signer, and the transformer-style decoder architecture to real-time translate sentences from the spatio-temporal context around the signer. Additionally its attention mechanism focus on moving hands and mouth of signer, which is often crucial for semantic understanding of sign language. In this paper, we introduce the Chinese sign language corpus of the business scene which consists of 3080 videos of high quality. The Chinese sign language corpus of the business scene has enormous impetuses for further research on the Chinese sign language translation. Experiments are carried out the PHOENIX-Weather 2014T (Camgoz et al, in: Proceedings of IEEE/CVF conference on computer vision and pattern recognition (CVPR 2018), pp 7784–7793, 2018), Chinese Sign Language dataset Huang et al, in: The thirty-second AAAI conference on artificial intelligence (AAAI-18), pp 2257–2264, 2018) and our CSLBS, the proposed model outperforms the state-of-the-art in inference times and accuracy using only raw RGB and RGB difference frames as input.
AbstractList Despite the recent progress of continuous sign language translation-based video, a variety of deep learning models are difficult to apply to the real-time translation in the limit computing resource. We present the two-stream lightweight sign transformer network model for recognizing and translating continuous sign language. This lightweight framework can obtain both static spatial information and all body dynamic features of signer, and the transformer-style decoder architecture to real-time translate sentences from the spatio-temporal context around the signer. Additionally its attention mechanism focus on moving hands and mouth of signer, which is often crucial for semantic understanding of sign language. In this paper, we introduce the Chinese sign language corpus of the business scene which consists of 3080 videos of high quality. The Chinese sign language corpus of the business scene has enormous impetuses for further research on the Chinese sign language translation. Experiments are carried out the PHOENIX-Weather 2014T (Camgoz et al, in: Proceedings of IEEE/CVF conference on computer vision and pattern recognition (CVPR 2018), pp 7784–7793, 2018), Chinese Sign Language dataset Huang et al, in: The thirty-second AAAI conference on artificial intelligence (AAAI-18), pp 2257–2264, 2018) and our CSLBS, the proposed model outperforms the state-of-the-art in inference times and accuracy using only raw RGB and RGB difference frames as input.
ArticleNumber 79
Author Chen, Yuming
Qin, Xuan
Mei, Xue
Author_xml – sequence: 1
  givenname: Yuming
  orcidid: 0000-0001-8253-9373
  surname: Chen
  fullname: Chen, Yuming
  email: cym@njtech.edu.cn
  organization: College of Electrical Engineering and Control Science, Nanjing Tech University
– sequence: 2
  givenname: Xue
  surname: Mei
  fullname: Mei, Xue
  organization: College of Electrical Engineering and Control Science, Nanjing Tech University
– sequence: 3
  givenname: Xuan
  surname: Qin
  fullname: Qin, Xuan
  organization: China Electronics Technology Group Corp 28th Research Institute
BookMark eNp9kM1LAzEQxYNUsK3-A54WPEcnH-1mjlL8goKXeg5xN1m3bLM1SVn8701dQfDQy8w7vN_M483IxPfeEnLN4JYBlHcRgAlFgXOahQA6nJEpk4JTVi5xQqaAWStAfkFmMW4BQJalnBLYDD2NKVizK7q2-UiDPc4ito0vOuObg2lskYLx0fVhZ8MlOXemi_bqd8_J2-PDZvVM169PL6v7Na0Ew0QdOGblEhboeK2Ec5wJkGj4u7QolcEKlZMVs4u6BmZQ1pUtRTZbhmhULebkZry7D_3nwcakt_0h-PxS8xIWChkwzC41uqrQxxis01WbTGp7nyO3nWagj_3osR-d-9E__egho_wfug_tzoSv05AYoZjNvrHhL9UJ6hvxjnpG
CitedBy_id crossref_primary_10_1038_s41598_024_78319_0
crossref_primary_10_32604_cmes_2023_045731
Cites_doi 10.1109/TPAMI.2012.59
10.1109/TSMCA.2006.886347
10.1109/ACCESS.2021.3132668
10.1109/TMM.2021.3117124
10.3390/app9132683
10.1016/j.patrec.2016.03.030
10.1109/TCSVT.2020.2999384
10.1145/2632856.2632931
10.1609/aaai.v34i07.7001
10.1109/ICCV.2017.332
10.1145/3341105.3373906
10.1109/CVPR.2009.5206523
10.1609/aaai.v32i1.11903
10.1109/ICCV.2015.512
10.3115/v1/N15-1173
10.1007/978-3-319-11179-7_51
10.1609/aaai.v35i2.16247
10.1109/CVPR.2017.131
10.1109/CVPR.2018.00812
10.5244/C.27.20
10.1109/CVPR.2009.5206848
10.1109/FG47880.2020.00002
10.3115/1073083.1073135
10.1109/CVPR.2017.364
10.1109/TMM.2021.3059098
10.1109/CVPR.2016.90
10.1109/CVPR.2016.497
10.1109/ICCV.2015.515
ContentType Journal Article
Copyright The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Copyright_xml – notice: The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
DBID AAYXX
CITATION
7T9
8FE
8FG
ABJCF
AFKRA
ARAPS
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
L6V
M7S
P5Z
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
DOI 10.1007/s00138-022-01330-w
DatabaseName CrossRef
Linguistics and Language Behavior Abstracts (LLBA)
ProQuest SciTech Collection
ProQuest Technology Collection
Materials Science & Engineering Collection
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central
Technology collection
ProQuest One Community College
ProQuest Central
SciTech Premium Collection
ProQuest Engineering Collection
Engineering Database
ProQuest advanced technologies & aerospace journals
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering collection
DatabaseTitle CrossRef
Advanced Technologies & Aerospace Collection
Engineering Database
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest One Academic Eastern Edition
SciTech Premium Collection
ProQuest One Community College
Linguistics and Language Behavior Abstracts (LLBA)
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
Advanced Technologies & Aerospace Database
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest One Academic UKI Edition
ProQuest Central Korea
Materials Science & Engineering Collection
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
Engineering Collection
DatabaseTitleList Advanced Technologies & Aerospace Collection

Database_xml – sequence: 1
  dbid: P5Z
  name: Advanced Technologies & Aerospace Database
  url: https://search.proquest.com/hightechjournals
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
Computer Science
EISSN 1432-1769
ExternalDocumentID 10_1007_s00138_022_01330_w
GrantInformation_xml – fundername: Research Center of Security Video and Image Processing Engineering Technology of Guizhou (CN)
  grantid: [2020]001]
– fundername: National Natural Science Foundation of China
  grantid: 61973334
  funderid: http://dx.doi.org/10.13039/501100001809
– fundername: Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology
  grantid: 2018IRS20
  funderid: http://dx.doi.org/10.13039/501100012237
GroupedDBID -4Z
-59
-5G
-BR
-EM
-Y2
-~C
.4S
.86
.DC
.VR
06D
0R~
0VY
199
1N0
1SB
203
28-
29M
2J2
2JN
2JY
2KG
2KM
2LR
2P1
2VQ
2~H
30V
4.4
406
408
409
40D
40E
5GY
5QI
5VS
67Z
6NX
78A
8FE
8FG
8UJ
95-
95.
95~
96X
AAAVM
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AAOBN
AARHV
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYTO
AAYZH
ABAKF
ABBBX
ABBXA
ABDBF
ABDZT
ABECU
ABFTD
ABFTV
ABHLI
ABHQN
ABJCF
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABQBU
ABQSL
ABSXP
ABTAH
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABWNU
ABXPI
ACAOD
ACBXY
ACDTI
ACGFS
ACHSB
ACHXU
ACIWK
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPIV
ACUHS
ACZOJ
ADHHG
ADHIR
ADIMF
ADINQ
ADKNI
ADKPE
ADMLS
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFIE
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AEMSY
AENEX
AEOHA
AEPYU
AESKC
AETLH
AEVLU
AEXYK
AFBBN
AFEXP
AFGCZ
AFKRA
AFLOW
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGGDS
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHSBF
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJBLW
AJRNO
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
AOCGG
ARAPS
ARCSS
ARMRJ
ASPBG
AVWKF
AXYYD
AYJHY
AZFZN
B-.
B0M
BA0
BBWZM
BDATZ
BENPR
BGLVJ
BGNMA
BSONS
CAG
CCPQU
COF
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
DU5
EAD
EAP
EBLON
EBS
EDO
EIOEI
EJD
EMK
EPL
ESBYG
ESX
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNWQR
GQ6
GQ7
GQ8
GXS
H13
HCIFZ
HF~
HG5
HG6
HMJXF
HQYDN
HRMNR
HVGLF
HZ~
I-F
I09
IHE
IJ-
IKXTQ
ITM
IWAJR
IXC
IZIGR
IZQ
I~X
I~Z
J-C
J0Z
JBSCW
JCJTX
JZLTJ
KDC
KOV
KOW
L6V
LAS
LLZTM
M4Y
M7S
MA-
N2Q
N9A
NB0
NDZJH
NPVJJ
NQJWS
NU0
O9-
O93
O9G
O9I
O9J
OAM
P19
P62
P9O
PF0
PT4
PT5
PTHSS
QOK
QOS
R4E
R89
R9I
RHV
RIG
RNI
RNS
ROL
RPX
RSV
RZK
S16
S1Z
S26
S27
S28
S3B
SAP
SCJ
SCLPG
SCO
SDH
SDM
SHX
SISQX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
T16
TSG
TSK
TSV
TUC
TUS
U2A
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WK8
YLTOR
YOT
Z45
Z7R
Z7S
Z7X
Z7Z
Z83
Z88
Z8M
Z8N
Z8R
Z8T
Z8W
Z92
ZMTXR
ZY4
~8M
~EX
AAPKM
AAYXX
ABBRH
ABDBE
ABFSG
ABRTQ
ACSTC
ADHKG
AEZWR
AFDZB
AFFHD
AFHIU
AFOHR
AGQPQ
AHPBZ
AHWEU
AIXLP
ATHPR
AYFIA
CITATION
PHGZM
PHGZT
PQGLB
7T9
DWQXO
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c319t-f0f1e46059f2d83ff213049a2b4e948a9c98f4c1e5dd01a94dce739f2e199a8d3
IEDL.DBID RSV
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000844262100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0932-8092
IngestDate Sun Nov 09 06:42:19 EST 2025
Sat Nov 29 03:17:33 EST 2025
Tue Nov 18 21:08:11 EST 2025
Fri Feb 21 02:44:40 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 5
Keywords Sign language translation
Transformer
Multimodal fusion
Lightweight networks
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c319t-f0f1e46059f2d83ff213049a2b4e948a9c98f4c1e5dd01a94dce739f2e199a8d3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-8253-9373
PQID 2705891019
PQPubID 2043753
ParticipantIDs proquest_journals_2705891019
crossref_citationtrail_10_1007_s00138_022_01330_w
crossref_primary_10_1007_s00138_022_01330_w
springer_journals_10_1007_s00138_022_01330_w
PublicationCentury 2000
PublicationDate 20220900
2022-09-00
20220901
PublicationDateYYYYMMDD 2022-09-01
PublicationDate_xml – month: 9
  year: 2022
  text: 20220900
PublicationDecade 2020
PublicationPlace Berlin/Heidelberg
PublicationPlace_xml – name: Berlin/Heidelberg
– name: New York
PublicationTitle Machine vision and applications
PublicationTitleAbbrev Machine Vision and Applications
PublicationYear 2022
Publisher Springer Berlin Heidelberg
Springer Nature B.V
Publisher_xml – name: Springer Berlin Heidelberg
– name: Springer Nature B.V
References Yang, Tao, Ye (CR36) 2016; 78
Wei, Zhao, Zhou, Li (CR19) 2021; 31
CR15
CR37
CR14
CR13
CR35
CR34
CR11
CR33
CR10
CR32
CR31
CR30
Zhou, Tam, Lam (CR18) 2021; 9
Fang, Gao, Zhao (CR28) 2007; 37
Koller, Forster, Ney (CR9) 2015; 141
Ko, Kim, Jung (CR12) 2019; 9
CR2
CR4
CR3
Cui, Liu, Zhang (CR6) 2019; 21
CR8
CR7
Tang, Guo, Richang, Wang (CR17) 2021
CR29
CR27
CR26
CR25
CR24
Ji, Xu, Yang (CR1) 2013; 35
CR23
CR22
CR21
CR20
HU, ZHOU, PU, LI (CR16) 2021; 17
Huang, Zhou, Li (CR5) 2018; 32
1330_CR14
G Fang (1330_CR28) 2007; 37
1330_CR15
1330_CR37
1330_CR34
1330_CR13
ZX Zhou (1330_CR18) 2021; 9
1330_CR35
W Yang (1330_CR36) 2016; 78
R Cui (1330_CR6) 2019; 21
1330_CR10
1330_CR32
1330_CR11
1330_CR33
J Huang (1330_CR5) 2018; 32
1330_CR30
1330_CR31
1330_CR29
1330_CR27
1330_CR25
1330_CR26
1330_CR8
CC Wei (1330_CR19) 2021; 31
1330_CR23
1330_CR7
1330_CR24
SG Tang (1330_CR17) 2021
1330_CR4
H HU (1330_CR16) 2021; 17
1330_CR3
1330_CR2
SK Ko (1330_CR12) 2019; 9
O Koller (1330_CR9) 2015; 141
1330_CR21
S Ji (1330_CR1) 2013; 35
1330_CR22
1330_CR20
References_xml – ident: CR22
– ident: CR4
– ident: CR14
– volume: 35
  start-page: 221
  issue: 1
  year: 2013
  end-page: 231
  ident: CR1
  article-title: 3D convolutional neural networks for human action recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2012.59
– ident: CR2
– ident: CR37
– ident: CR30
– ident: CR10
– ident: CR33
– volume: 37
  start-page: 1
  issue: 1
  year: 2007
  end-page: 9
  ident: CR28
  article-title: Large-vocabulary continuous sign language recognition based on transition-movement models
  publication-title: IEEE Trans. Syst. Man Cybern.
  doi: 10.1109/TSMCA.2006.886347
– ident: CR35
– ident: CR29
– volume: 21
  start-page: 1880
  issue: 7
  year: 2019
  end-page: 1891
  ident: CR6
  article-title: A deep neural framework for continuous sign language recognition by iterative training
  publication-title: TMM
– ident: CR8
– volume: 17
  start-page: 80:1
  issue: 3
  year: 2021
  end-page: 80:19
  ident: CR16
  article-title: Global-local enhancement network for NMF-aware sign language recognition
  publication-title: ACM Trans. Multimedia Comput. Commun. Appl. TOMM
– ident: CR25
– ident: CR27
– ident: CR23
– ident: CR21
– volume: 141
  start-page: 108
  year: 2015
  end-page: 125
  ident: CR9
  article-title: Continuous sign language recognition: towards large vocabulary statistical recognition systems handling multiple signers
  publication-title: CVIU
– volume: 9
  start-page: 10
  year: 2021
  ident: CR18
  article-title: SignBERT: a BERT-based deep learning framework for continuous sign language recognition
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3132668
– ident: CR3
– ident: CR15
– ident: CR31
– ident: CR13
– ident: CR11
– year: 2021
  ident: CR17
  article-title: Graph-based multimodal sequential embedding for sign language translation
  publication-title: IEEE Trans. Multimedia
  doi: 10.1109/TMM.2021.3117124
– ident: CR32
– ident: CR34
– ident: CR7
– volume: 9
  start-page: 2683
  issue: 13
  year: 2019
  ident: CR12
  article-title: Neural sign language translation based on human key-point estimation
  publication-title: Appl. Sci.
  doi: 10.3390/app9132683
– ident: CR26
– volume: 32
  start-page: 1
  year: 2018
  ident: CR5
  article-title: Attention-based 3D-CNNs for large-vocabulary sign language recognition
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– ident: CR24
– volume: 78
  start-page: 28
  year: 2016
  end-page: 35
  ident: CR36
  article-title: Continuous sign language recognition using level building based on fast hidden Markov model
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2016.03.030
– volume: 31
  start-page: 1138
  issue: 3
  year: 2021
  end-page: 1149
  ident: CR19
  article-title: Semantic boundary detection with reinforcement learning for continuous sign language recognition
  publication-title: IEEE Trans. Circuits Syst. Video Technol. TCSVT
  doi: 10.1109/TCSVT.2020.2999384
– ident: CR20
– ident: 1330_CR3
  doi: 10.1145/2632856.2632931
– year: 2021
  ident: 1330_CR17
  publication-title: IEEE Trans. Multimedia
  doi: 10.1109/TMM.2021.3117124
– ident: 1330_CR14
  doi: 10.1609/aaai.v34i07.7001
– ident: 1330_CR10
  doi: 10.1109/ICCV.2017.332
– ident: 1330_CR24
  doi: 10.1145/3341105.3373906
– volume: 9
  start-page: 10
  year: 2021
  ident: 1330_CR18
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3132668
– ident: 1330_CR7
  doi: 10.1109/CVPR.2009.5206523
– volume: 78
  start-page: 28
  year: 2016
  ident: 1330_CR36
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2016.03.030
– ident: 1330_CR30
  doi: 10.1609/aaai.v32i1.11903
– ident: 1330_CR34
  doi: 10.1109/ICCV.2015.512
– volume: 21
  start-page: 1880
  issue: 7
  year: 2019
  ident: 1330_CR6
  publication-title: TMM
– volume: 9
  start-page: 2683
  issue: 13
  year: 2019
  ident: 1330_CR12
  publication-title: Appl. Sci.
  doi: 10.3390/app9132683
– ident: 1330_CR13
– ident: 1330_CR37
  doi: 10.1145/2632856.2632931
– volume: 17
  start-page: 80:1
  issue: 3
  year: 2021
  ident: 1330_CR16
  publication-title: ACM Trans. Multimedia Comput. Commun. Appl. TOMM
– ident: 1330_CR32
  doi: 10.3115/v1/N15-1173
– volume: 35
  start-page: 221
  issue: 1
  year: 2013
  ident: 1330_CR1
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2012.59
– ident: 1330_CR25
– volume: 37
  start-page: 1
  issue: 1
  year: 2007
  ident: 1330_CR28
  publication-title: IEEE Trans. Syst. Man Cybern.
  doi: 10.1109/TSMCA.2006.886347
– ident: 1330_CR27
– ident: 1330_CR2
  doi: 10.1007/978-3-319-11179-7_51
– ident: 1330_CR31
– ident: 1330_CR21
  doi: 10.1609/aaai.v35i2.16247
– ident: 1330_CR29
  doi: 10.1109/CVPR.2017.131
– ident: 1330_CR11
  doi: 10.1109/CVPR.2018.00812
– ident: 1330_CR8
  doi: 10.5244/C.27.20
– volume: 141
  start-page: 108
  year: 2015
  ident: 1330_CR9
  publication-title: CVIU
– ident: 1330_CR23
  doi: 10.1109/CVPR.2009.5206848
– volume: 31
  start-page: 1138
  issue: 3
  year: 2021
  ident: 1330_CR19
  publication-title: IEEE Trans. Circuits Syst. Video Technol. TCSVT
  doi: 10.1109/TCSVT.2020.2999384
– ident: 1330_CR15
  doi: 10.1109/FG47880.2020.00002
– ident: 1330_CR26
  doi: 10.3115/1073083.1073135
– ident: 1330_CR4
  doi: 10.1109/CVPR.2017.364
– ident: 1330_CR20
  doi: 10.1109/TMM.2021.3059098
– volume: 32
  start-page: 1
  year: 2018
  ident: 1330_CR5
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– ident: 1330_CR22
  doi: 10.1109/CVPR.2016.90
– ident: 1330_CR35
  doi: 10.1109/CVPR.2016.497
– ident: 1330_CR33
  doi: 10.1109/ICCV.2015.515
SSID ssj0004774
Score 2.3156176
Snippet Despite the recent progress of continuous sign language translation-based video, a variety of deep learning models are difficult to apply to the real-time...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
SubjectTerms Artificial intelligence
Chinese languages
Communications Engineering
Computer Science
Computer vision
Computerized corpora
Conferences
Corpus linguistics
Deep learning
Experiments
Image Processing and Computer Vision
Inference
Language translation
Lightweight
Machine learning
Networks
Original Paper
Pattern Recognition
Real time
Semantics
Sentences
Sign language
Spatial data
Transformers
Translating
Translation
Vision systems
Weather
SummonAdditionalLinks – databaseName: ProQuest Central
  dbid: BENPR
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NS8MwFH_o5kEPTqfidEoP3jTYpunanERlw9MYMmG3kuYDhLnNtdp_3yRLVxXcxVuhaWjzy3v59X0CXBEmWBT2OGIYc0QY1SJFGUEijImMsRJJltlmE_FwmEwmdOQMbrkLq6x0olXUYs6NjfwWx7YBnmYkd4t3ZLpGGe-qa6GxDU1TqYw0oPnQH46e68zIeFWHWbMUrYspdmkzNnnOOumQiWbXF6GPyp9HU803f7lI7ckzaP33nQ9g33FO7361SQ5hS87a0HL803PSnbdh71txwiPwx-UcmVQS9uZNzS98aa2onon48Cozp1dUxFcuj-Fl0B8_PiHXXwFxLXgFUr4KpPGLUoVFEiqFA-N0YzgjkpKEUU4TRXggIyH8gFEiuIxDPVgGGs9EhCfQmM1n8hQ8rlWmYDhKMkUJl_qjI5XxIOkJ1RMk8zsQVEubcld83PTAmKbrsskWjlTDkVo40rID1-tnFqvSGxtHdysMUieGeVoD0IGbCsX69t-znW2e7Rx2sd04JtasC41i-SEvYId_Fq_58tJtwi94YeIw
  priority: 102
  providerName: ProQuest
Title Two-stream lightweight sign language transformer
URI https://link.springer.com/article/10.1007/s00138-022-01330-w
https://www.proquest.com/docview/2705891019
Volume 33
WOSCitedRecordID wos000844262100001&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: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1432-1769
  dateEnd: 20241209
  omitProxy: false
  ssIdentifier: ssj0004774
  issn: 0932-8092
  databaseCode: P5Z
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Engineering Database
  customDbUrl:
  eissn: 1432-1769
  dateEnd: 20241209
  omitProxy: false
  ssIdentifier: ssj0004774
  issn: 0932-8092
  databaseCode: M7S
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1432-1769
  dateEnd: 20241209
  omitProxy: false
  ssIdentifier: ssj0004774
  issn: 0932-8092
  databaseCode: BENPR
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 1432-1769
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004774
  issn: 0932-8092
  databaseCode: RSV
  dateStart: 19970101
  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/eLvHCXMwnV3NT8IwFH9R8KAHUdSIItnBmzbZuo61RzUYT4QAGuJl6fqRmCAYmPLv25YV1KiJXpale2uW9_pef-v7AjgnXPIkbgvEMRaIcGZUinGCZJwSlWItaZ67ZhNpt0tHI9Yrk8LmPtrduySdpV4luzmnGrLR5-YmDtFiE6pmu6NWHfuDh3U2ZLqsvWyQibG_DJepMt_P8Xk7WmPML25Rt9vc1v73nXuwW6LL4Gq5HPZhQ03qUCuRZlDq8dwM-WYOfqwOOx8qEx5AOFxMkc0j4c_B2P6_L9wRamDDPQJ_xhkUHvWq2SHc33aGN3eobK6AhNG6AulQR8o6RZnGksZa48h63DjOiWKEciYY1UREKpEyjDgjUqg0NsQqMsKkMj6CymQ6UccQCGMvJccJzTUjQlEWJToXEW1L3ZYkDxsQeR5noqw8bhtgjLNVzWTHs8zwLHM8yxYNuFi987Ksu_ErddOLLit1cJ7h1LVMNBi2AZdeVOvHP8928jfyU9jGTto28KwJlWL2qs5gS7wVT_NZC6rXnW6v37JBpQNz7SWPLbde3wGJaOFQ
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LS8NAEB7qA9SDj6pYnznoSReTzbbJHkRELS2tRbBCb3GzDxBqq200-Kf8je5uE6uCvfXgLZDNwO43OzOZJ8AhYYKV_QpHDGOOCKP6SlFGkPADIgOsRBjHdthE0GqFnQ69LcBHXgtj0ipzmWgFtehz4yM_xYEdgKctkvPnF2SmRpnoaj5CY8QWDfme6l-24Vn9SuN7hHH1un1ZQ9lUAcQ1uyVIucqTJhpIFRahrxT2TKiJ4ZhISkJGOQ0V4Z4sC-F6jBLBZeDrxdLTuwiFr-nOwBwx0t-mCt6N6zCDUddnbRNpyU9xVqRjS_VsSBCZ3Hn94Lso_akIx9btr4Cs1XPVlf92QquwnFnUzsXoCqxBQfaKsJJZ104mu4ZFWPrWenEd3HbaR6ZQhj05XeOgSK2P2DH5LE7uxHWS3KyXgw24n8ouNmG21-_JLXC4VgiC4XIYK0q41IdcVjH3wopQFUFitwReDmXEs9bqZsJHN_pqCm3hjzT8kYU_Sktw_PXN86ixyMTVuznmUSZkhtEY8BKc5Fwzfv03te3J1A5goda-aUbNequxA4vYMq3JqtuF2WTwKvdgnr8lj8PBvmV_Bx6mzU2f2z8-Zw
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dS8MwED90iuiD06k4P_vgm4a1abYmj6IORRkDp-ytpPkAYXZjq-7fN0nbbYoK4ltJ01Ducskld_f7AZwRLnkzbAnEMRaIcGZMinGCZBgRFWEtaZI4somo06H9PusuVPG7bPcyJJnXNFiUpjRrjKRuzArfXIAN2Ux08xD6aLoMK8SSBtnz-uPzvDIyynGYjZdi1mKGi7KZ78f4vDXN_c0vIVK387Sr___nLdgsvE7vMp8m27Ck0hpUCw_UK-x7YppKkoeyrQYbC4iFO-D3pkNk60v4qzew5_qpu1r1bBqIV959elnpDavxLjy1b3pXt6ggXUDCWGOGtK8DZYOlTGNJQ61xYCNxHCdEMUI5E4xqIgLVlNIPOCNSqCg0nVVglExluAeVdJiqffCEWUclx02aaEaEoixo6kQEtCV1S5LEr0NQyjsWBSK5JcYYxDMsZSez2MgsdjKLp3U4n30zyvE4fu19VKoxLmxzEuPIUSka37YOF6Xa5q9_Hu3gb91PYa173Y4f7jr3h7COneJtbtoRVLLxmzqGVfGevUzGJ27KfgAB9OmG
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=Two-stream+lightweight+sign+language+transformer&rft.jtitle=Machine+vision+and+applications&rft.au=Chen%2C+Yuming&rft.au=Mei%2C+Xue&rft.au=Qin%2C+Xuan&rft.date=2022-09-01&rft.pub=Springer+Berlin+Heidelberg&rft.issn=0932-8092&rft.eissn=1432-1769&rft.volume=33&rft.issue=5&rft_id=info:doi/10.1007%2Fs00138-022-01330-w&rft.externalDocID=10_1007_s00138_022_01330_w
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0932-8092&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0932-8092&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0932-8092&client=summon