Semi‐Supervised 3D Shape Recognition via Multimodal Deep Co‐training

3D shape recognition has been actively investigated in the field of computer graphics. With the rapid development of deep learning, various deep models have been introduced and achieved remarkable results. Most 3D shape recognition methods are supervised and learn only from the large amount of label...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer graphics forum Jg. 39; H. 7; S. 279 - 289
Hauptverfasser: Song, Mofei, Liu, Yu, Liu, Xiao Fan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Oxford Blackwell Publishing Ltd 01.10.2020
Schlagworte:
ISSN:0167-7055, 1467-8659
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract 3D shape recognition has been actively investigated in the field of computer graphics. With the rapid development of deep learning, various deep models have been introduced and achieved remarkable results. Most 3D shape recognition methods are supervised and learn only from the large amount of labeled shapes. However, it is expensive and time consuming to obtain such a large training set. In contrast to these methods, this paper studies a semi‐supervised learning framework to train a deep model for 3D shape recognition by using both labeled and unlabeled shapes. Inspired by the co‐training algorithm, our method iterates between model training and pseudo‐label generation phases. In the model training phase, we train two deep networks based on the point cloud and multi‐view representation simultaneously. In the pseudo‐label generation phase, we generate the pseudo‐labels of the unlabeled shapes using the joint prediction of two networks, which augments the labeled set for the next iteration. To extract more reliable consensus information from multiple representations, we propose an uncertainty‐aware consistency loss function to combine the two networks into a multimodal network. This not only encourages the two networks to give similar predictions on the unlabeled set, but also eliminates the negative influence of the large performance gap between the two networks. Experiments on the benchmark ModelNet40 demonstrate that, with only 10% labeled training data, our approach achieves competitive performance to the results reported by supervised methods.
AbstractList 3D shape recognition has been actively investigated in the field of computer graphics. With the rapid development of deep learning, various deep models have been introduced and achieved remarkable results. Most 3D shape recognition methods are supervised and learn only from the large amount of labeled shapes. However, it is expensive and time consuming to obtain such a large training set. In contrast to these methods, this paper studies a semi‐supervised learning framework to train a deep model for 3D shape recognition by using both labeled and unlabeled shapes. Inspired by the co‐training algorithm, our method iterates between model training and pseudo‐label generation phases. In the model training phase, we train two deep networks based on the point cloud and multi‐view representation simultaneously. In the pseudo‐label generation phase, we generate the pseudo‐labels of the unlabeled shapes using the joint prediction of two networks, which augments the labeled set for the next iteration. To extract more reliable consensus information from multiple representations, we propose an uncertainty‐aware consistency loss function to combine the two networks into a multimodal network. This not only encourages the two networks to give similar predictions on the unlabeled set, but also eliminates the negative influence of the large performance gap between the two networks. Experiments on the benchmark ModelNet40 demonstrate that, with only 10% labeled training data, our approach achieves competitive performance to the results reported by supervised methods.
Author Song, Mofei
Liu, Yu
Liu, Xiao Fan
Author_xml – sequence: 1
  givenname: Mofei
  orcidid: 0000-0002-9912-1560
  surname: Song
  fullname: Song, Mofei
  organization: Nanjing University
– sequence: 2
  givenname: Yu
  orcidid: 0000-0002-2207-1569
  surname: Liu
  fullname: Liu, Yu
  organization: Southeast University
– sequence: 3
  givenname: Xiao Fan
  orcidid: 0000-0001-8342-4623
  surname: Liu
  fullname: Liu, Xiao Fan
  organization: City University of Hong Kong
BookMark eNp9kLFOwzAQhi1UJNrCwBtEYmJoazu2k4wopS1SERKF2XKSc3GVxsFJirrxCDwjT4JLmZDglrvh--_u_weoV9kKELokeEx8TfK1HhNGGDtBfcJENIoFT3qoj4mfI8z5GRo0zQZjzCLB-2ixgq35fP9YdTW4nWmgCMJpsHpRNQSPkNt1ZVpjq2BnVHDfla3Z2kKVwRSgDlLrha1TpjLV-hydalU2cPHTh-h5dvuULkbLh_lderMc5TSJ2IjHBadFxFlCuX-Agi5EpCHMMq3CJKY605oKlkPOC1pgAZRlUYYTVqgkIxqHQ3R13Fs7-9pB08qN7VzlT0rKRMhiIRLqqesjlTvbNA60rJ3ZKreXBMtDUNIHJb-D8uzkF5ubVh1cH7yV_yneTAn7v1fLdD47Kr4AoJJ80g
CitedBy_id crossref_primary_10_1186_s13677_022_00359_6
crossref_primary_10_1109_ACCESS_2023_3243854
crossref_primary_10_1007_s12046_025_02762_6
crossref_primary_10_32604_cmc_2023_036365
Cites_doi 10.1609/aaai.v33i01.33018279
10.1007/978-3-319-49409-8_20
10.1109/CVPR.2017.238
10.1145/3240508.3240702
10.1109/TMM.2017.2758522
10.1109/CGIV.2013.11
10.1109/TVCG.2018.2866793
10.1109/ACCESS.2020.2982196
10.1109/ICCV.2015.114
10.1109/TMM.2014.2351788
10.1109/TPAMI.2018.2858821
10.1109/CVPR.2019.00521
10.1109/WACV45572.2020.9093608
10.1016/j.neucom.2018.01.080
10.1609/aaai.v33i01.33018376
10.1145/2508363.2508364
10.1007/978-3-031-01548-9_7
10.1007/978-3-030-11015-4_49
10.1109/TIP.2016.2563981
10.1145/3326362
10.1109/CVPR42600.2020.01109
10.1109/ICME.2014.6890145
10.1145/279943.279962
10.1109/TIP.2019.2933724
10.1016/j.patcog.2020.107269
10.1609/aaai.v33i01.33019119
10.1145/3343031.3351009
10.1109/CVPR.2018.00029
10.1109/TPAMI.2014.2299812
10.1109/CVPR.2019.00910
10.1109/CVPR.2019.00997
10.1111/cgf.12790
10.1016/j.patcog.2019.107164
10.1145/3272127.3275050
ContentType Journal Article
Copyright 2020 The Author(s) Computer Graphics Forum © 2020 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.
2020 The Eurographics Association and John Wiley & Sons Ltd.
Copyright_xml – notice: 2020 The Author(s) Computer Graphics Forum © 2020 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.
– notice: 2020 The Eurographics Association and John Wiley & Sons Ltd.
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1111/cgf.14144
DatabaseName CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts
CrossRef

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1467-8659
EndPage 289
ExternalDocumentID 10_1111_cgf_14144
CGF14144
Genre article
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 61906036
– fundername: Open Research Project of State Key Laboratory of Novel Software Technology (Nanjing University)
  funderid: KFKT2019B02
GroupedDBID .3N
.4S
.DC
.GA
.Y3
05W
0R~
10A
15B
1OB
1OC
29F
31~
33P
3SF
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5HH
5LA
5VS
66C
6J9
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
8VB
930
A03
AAESR
AAEVG
AAHHS
AAHQN
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABDPE
ABEML
ABPVW
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACFBH
ACGFS
ACPOU
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADNMO
ADOZA
ADXAS
ADZMN
ADZOD
AEEZP
AEGXH
AEIGN
AEIMD
AEMOZ
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFEBI
AFFNX
AFFPM
AFGKR
AFPWT
AFWVQ
AFZJQ
AHBTC
AHEFC
AHQJS
AITYG
AIURR
AIWBW
AJBDE
AJXKR
AKVCP
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CAG
COF
CS3
CWDTD
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EAD
EAP
EBA
EBO
EBR
EBS
EBU
EDO
EJD
EMK
EST
ESX
F00
F01
F04
F5P
FEDTE
FZ0
G-S
G.N
GODZA
H.T
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
I-F
IHE
IX1
J0M
K1G
K48
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
O66
O9-
OIG
P2W
P2X
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
QWB
R.K
RDJ
RIWAO
RJQFR
ROL
RX1
SAMSI
SUPJJ
TH9
TN5
TUS
UB1
V8K
W8V
W99
WBKPD
WIH
WIK
WOHZO
WQJ
WRC
WXSBR
WYISQ
WZISG
XG1
ZL0
ZZTAW
~IA
~IF
~WT
AAMMB
AAYXX
ADMLS
AEFGJ
AEYWJ
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
O8X
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c2974-58d52d7549257652efd67fe3bbfa3982fbff264cec5d2d06e24b7b094da9b1f03
IEDL.DBID DRFUL
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000594502700024&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0167-7055
IngestDate Wed Aug 13 03:40:14 EDT 2025
Tue Nov 18 21:12:42 EST 2025
Sat Nov 29 03:41:19 EST 2025
Wed Jan 22 16:31:23 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2974-58d52d7549257652efd67fe3bbfa3982fbff264cec5d2d06e24b7b094da9b1f03
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-9912-1560
0000-0001-8342-4623
0000-0002-2207-1569
PQID 2463486692
PQPubID 30877
PageCount 11
ParticipantIDs proquest_journals_2463486692
crossref_primary_10_1111_cgf_14144
crossref_citationtrail_10_1111_cgf_14144
wiley_primary_10_1111_cgf_14144_CGF14144
PublicationCentury 2000
PublicationDate October 2020
2020-10-00
20201001
PublicationDateYYYYMMDD 2020-10-01
PublicationDate_xml – month: 10
  year: 2020
  text: October 2020
PublicationDecade 2020
PublicationPlace Oxford
PublicationPlace_xml – name: Oxford
PublicationTitle Computer graphics forum
PublicationYear 2020
Publisher Blackwell Publishing Ltd
Publisher_xml – name: Blackwell Publishing Ltd
References 2015; 37
2017; 20
2009
2019; 38
2020; 100
2004
2019; 109
2018; 25
2020; 8
2018; 297
2013; 32
2019; 41
2017; 36
2020
2014; 16
2019
2018
2017
2016
2015
2014
2013
1998; 98
2016; 25
2018; 37
2020; 29
e_1_2_10_23_2
e_1_2_10_21_2
Wu S. (e_1_2_10_41_2) 2017; 20
Wang Y. (e_1_2_10_44_2) 2019; 38
Blum A. (e_1_2_10_6_2) 1998; 98
e_1_2_10_2_2
e_1_2_10_18_2
e_1_2_10_53_2
e_1_2_10_4_2
e_1_2_10_16_2
e_1_2_10_37_2
e_1_2_10_14_2
e_1_2_10_35_2
e_1_2_10_11_2
e_1_2_10_34_2
e_1_2_10_8_2
e_1_2_10_32_2
e_1_2_10_30_2
e_1_2_10_51_2
Gong C. (e_1_2_10_12_2) 2016; 25
Wang P.‐S. (e_1_2_10_42_2) 2017; 36
e_1_2_10_29_2
e_1_2_10_27_2
e_1_2_10_48_2
e_1_2_10_25_2
e_1_2_10_46_2
e_1_2_10_22_2
e_1_2_10_45_2
e_1_2_10_20_2
e_1_2_10_43_2
e_1_2_10_19_2
e_1_2_10_3_2
e_1_2_10_17_2
e_1_2_10_52_2
e_1_2_10_5_2
Chen S.‐L. (e_1_2_10_10_2) 2018; 25
e_1_2_10_15_2
e_1_2_10_38_2
e_1_2_10_13_2
e_1_2_10_36_2
e_1_2_10_9_2
Engelen J. E. (e_1_2_10_40_2) 2019; 109
e_1_2_10_33_2
e_1_2_10_31_2
e_1_2_10_50_2
Li J. (e_1_2_10_26_2) 2020; 29
Tang X. (e_1_2_10_39_2) 2018; 297
Cevikalp H. (e_1_2_10_7_2) 2020; 100
e_1_2_10_28_2
e_1_2_10_49_2
e_1_2_10_24_2
e_1_2_10_47_2
References_xml – volume: 36
  start-page: 101
  issue: 1
  year: 2017
  end-page: 132
  article-title: Data‐driven shape analysis and processing
  publication-title: Computer Graphics Forum
– year: 2009
– start-page: 945
  year: 2015
  end-page: 953
– volume: 98
  year: 1998
  article-title: Combining labeled and unlabeled data with co‐training
  publication-title: COLT'
– volume: 32
  start-page: 1
  issue: 6
  year: 2013
  end-page: 10
  article-title: Fine‐grained semi‐supervised labeling of large shape collections
  publication-title: ACM Transactions on Graphics (TOG)
– start-page: 107269
  year: 2020
– start-page: 77
  year: 2016
  end-page: 85
– start-page: 206
  year: 2018
  end-page: 215
– start-page: 135
  year: 2018
  end-page: 152
– volume: 25
  start-page: 3244
  year: 2018
  end-page: 3257
  article-title: Veram: View‐enhanced recurrent attention model for 3d shape classification
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– volume: 25
  start-page: 3249
  year: 2016
  end-page: 3260
  article-title: Multi‐modal curriculum learning for semi‐supervised image classification
  publication-title: IEEE Transactions on Image Processing
– volume: 29
  start-page: 538
  year: 2020
  end-page: 550
  article-title: Semi‐supervised deep coupled ensemble learning with classification landmark exploration
  publication-title: IEEE Transactions on Image Processing
– start-page: 1
  year: 2013
  end-page: 10
– volume: 36
  issue: 4
  year: 2017
  article-title: O‐cnn: octree‐based convolutional neural networks for 3d shape analysis
  publication-title: ACM Trans. Graph.
– start-page: 40
  year: 2018
  end-page: 49
– volume: 20
  start-page: 851
  issue: 4
  year: 2017
  end-page: 865
  article-title: Semi‐supervised image classification with self‐paced cross‐task networks
  publication-title: IEEE Transactions on Multimedia
– year: 2016
– year: 2018
– start-page: 1
  year: 2014
  end-page: 6
– volume: 38
  start-page: 146:1
  year: 2019
  end-page: 146:12
  article-title: Dynamic graph cnn for learning on point clouds
  publication-title: ACM Trans. Graph.
– volume: 37
  start-page: 175
  issue: 1
  year: 2015
  end-page: 188
  article-title: Towards making unlabeled data never hurt
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– volume: 100
  start-page: 107164
  year: 2020
  article-title: Semi‐supervised robust deep neural networks for multi‐label image classification
  publication-title: Pattern Recognition
– volume: 16
  start-page: 2154
  year: 2014
  end-page: 2167
  article-title: Learning high‐level feature by deep belief networks for 3‐d model retrieval and recognition
  publication-title: IEEE Transactions on Multimedia
– start-page: 8887
  year: 2019
  end-page: 8896
– volume: 37
  issue: 6
  year: 2018
  article-title: Adaptive o‐cnn: A patch‐based deep representation of 3d shapes
  publication-title: ACM Trans. Graph.
– volume: 8
  start-page: 57566
  year: 2020
  end-page: 57593
  article-title: Areview on deep learning approaches for 3d data representations in retrieval and classifications
  publication-title: IEEE Access
– volume: 109
  year: 2019
  article-title: A survey on semi‐supervised learning
  publication-title: Machine Learning
– start-page: 2215
  year: 2017
  end-page: 2223
– year: 2004
– volume: 297
  start-page: 22
  year: 2018
  end-page: 32
  article-title: Facial landmark detection by semi‐supervised deep learning
  publication-title: Neurocomputing
– year: 2020
– start-page: 5065
  year: 2019
  end-page: 5074
– volume: 41
  start-page: 1979
  year: 2019
  end-page: 1993
  article-title: Virtual adversarial training: A regularization method for supervised and semi‐supervised learning
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– year: 2017
– year: 2019
– start-page: 1912
  year: 2015
  end-page: 1920
– year: 2015
– year: 2013
– start-page: 11079
  year: 2020
  end-page: 11087
– ident: e_1_2_10_11_2
  doi: 10.1609/aaai.v33i01.33018279
– ident: e_1_2_10_35_2
  doi: 10.1007/978-3-319-49409-8_20
– ident: e_1_2_10_34_2
– ident: e_1_2_10_9_2
– ident: e_1_2_10_18_2
– ident: e_1_2_10_21_2
  doi: 10.1109/CVPR.2017.238
– ident: e_1_2_10_4_2
– ident: e_1_2_10_3_2
– ident: e_1_2_10_49_2
  doi: 10.1145/3240508.3240702
– volume: 20
  start-page: 851
  issue: 4
  year: 2017
  ident: e_1_2_10_41_2
  article-title: Semi‐supervised image classification with self‐paced cross‐task networks
  publication-title: IEEE Transactions on Multimedia
  doi: 10.1109/TMM.2017.2758522
– ident: e_1_2_10_30_2
– ident: e_1_2_10_22_2
  doi: 10.1109/CGIV.2013.11
– volume: 25
  start-page: 3244
  year: 2018
  ident: e_1_2_10_10_2
  article-title: Veram: View‐enhanced recurrent attention model for 3d shape classification
  publication-title: IEEE Transactions on Visualization and Computer Graphics
  doi: 10.1109/TVCG.2018.2866793
– ident: e_1_2_10_33_2
– volume: 109
  year: 2019
  ident: e_1_2_10_40_2
  article-title: A survey on semi‐supervised learning
  publication-title: Machine Learning
– ident: e_1_2_10_13_2
  doi: 10.1109/ACCESS.2020.2982196
– ident: e_1_2_10_37_2
  doi: 10.1109/ICCV.2015.114
– ident: e_1_2_10_5_2
  doi: 10.1109/TMM.2014.2351788
– ident: e_1_2_10_28_2
  doi: 10.1109/TPAMI.2018.2858821
– ident: e_1_2_10_17_2
  doi: 10.1109/CVPR.2019.00521
– ident: e_1_2_10_48_2
  doi: 10.1109/WACV45572.2020.9093608
– volume: 297
  start-page: 22
  year: 2018
  ident: e_1_2_10_39_2
  article-title: Facial landmark detection by semi‐supervised deep learning
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.01.080
– ident: e_1_2_10_15_2
  doi: 10.1609/aaai.v33i01.33018376
– ident: e_1_2_10_14_2
  doi: 10.1145/2508363.2508364
– ident: e_1_2_10_23_2
– ident: e_1_2_10_53_2
  doi: 10.1007/978-3-031-01548-9_7
– ident: e_1_2_10_36_2
  doi: 10.1007/978-3-030-11015-4_49
– volume: 25
  start-page: 3249
  year: 2016
  ident: e_1_2_10_12_2
  article-title: Multi‐modal curriculum learning for semi‐supervised image classification
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2016.2563981
– volume: 38
  start-page: 146:1
  year: 2019
  ident: e_1_2_10_44_2
  article-title: Dynamic graph cnn for learning on point clouds
  publication-title: ACM Trans. Graph.
  doi: 10.1145/3326362
– ident: e_1_2_10_52_2
  doi: 10.1109/CVPR42600.2020.01109
– ident: e_1_2_10_24_2
  doi: 10.1109/ICME.2014.6890145
– ident: e_1_2_10_2_2
– ident: e_1_2_10_19_2
– volume: 98
  year: 1998
  ident: e_1_2_10_6_2
  article-title: Combining labeled and unlabeled data with co‐training
  publication-title: COLT'
  doi: 10.1145/279943.279962
– volume: 29
  start-page: 538
  year: 2020
  ident: e_1_2_10_26_2
  article-title: Semi‐supervised deep coupled ensemble learning with classification landmark exploration
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2019.2933724
– ident: e_1_2_10_31_2
  doi: 10.1016/j.patcog.2020.107269
– ident: e_1_2_10_51_2
  doi: 10.1609/aaai.v33i01.33019119
– ident: e_1_2_10_32_2
– ident: e_1_2_10_29_2
  doi: 10.1145/3343031.3351009
– ident: e_1_2_10_50_2
  doi: 10.1109/CVPR.2018.00029
– ident: e_1_2_10_27_2
  doi: 10.1109/TPAMI.2014.2299812
– ident: e_1_2_10_38_2
– ident: e_1_2_10_46_2
– ident: e_1_2_10_25_2
  doi: 10.1109/CVPR.2019.00910
– volume: 36
  issue: 4
  year: 2017
  ident: e_1_2_10_42_2
  article-title: O‐cnn: octree‐based convolutional neural networks for 3d shape analysis
  publication-title: ACM Trans. Graph.
– ident: e_1_2_10_20_2
  doi: 10.1109/CVPR.2019.00997
– ident: e_1_2_10_43_2
– ident: e_1_2_10_47_2
  doi: 10.1111/cgf.12790
– ident: e_1_2_10_8_2
– volume: 100
  start-page: 107164
  year: 2020
  ident: e_1_2_10_7_2
  article-title: Semi‐supervised robust deep neural networks for multi‐label image classification
  publication-title: Pattern Recognition
  doi: 10.1016/j.patcog.2019.107164
– ident: e_1_2_10_16_2
– ident: e_1_2_10_45_2
  doi: 10.1145/3272127.3275050
SSID ssj0004765
Score 2.3301907
Snippet 3D shape recognition has been actively investigated in the field of computer graphics. With the rapid development of deep learning, various deep models have...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 279
SubjectTerms Algorithms
CCS Concepts
Cloud computing
Computer graphics
Computing methodologies → Shape analysis
Iterative methods
Machine learning
Networks
Representations
Shape recognition
Three dimensional models
Title Semi‐Supervised 3D Shape Recognition via Multimodal Deep Co‐training
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.14144
https://www.proquest.com/docview/2463486692
Volume 39
WOSCitedRecordID wos000594502700024&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1467-8659
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004765
  issn: 0167-7055
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NSsNAEB5q9aAH_8VqlSAevATSTTY_eJLW2EMp0lrpLWSzu1qwSWjann0En9EncTZN2goKgpBDDrOTZXZmd74w8y3AdeSGhBiO0CWRlm5hQqt7gjZ0botIOpxxktM1PXecbtcdDr3HCtyWvTALfojlDzcVGfl-rQI8ZNlakEcvEsMc8cAGbBL0W6sKm62eP-is2iIdm5bU3oo0piAWUoU8y8Hfj6NVjrmeqeZHjb_3r0nuw26RYWp3C5c4gIqID2FnjXfwCNp9MR59vn_0Z6naKjLBNbOl9V_DVGi9sqIoibX5KNTyDt1xwlFlS4hUayY4sLxY4hgG_v1Ts60XVyroEUHkoFOXU8IdRcuGQIMSIbntSGEyJkPTc4lkUmKKFImIcsINWxCLOQwhIA891pCGeQLVOInFKWiqKVcgmjIJRSF8MBVxDaZUoh7q1OCmtGwQFXzjanZvQYk70DhBbpwaXC1F0wXJxk9C9XJ5giLOsoBYtmm5tu0R_Fy-EL8rCJoPfv5y9nfRc9gmCmDn1Xt1qE4nM3EBW9F8Osoml4XDfQGYt9j6
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5qFdSDb7FaNYgHL4F2k80DvEhrrBiL9CG9hSS7qwWbhL7O_gR_o7_E2TRpKygIQg57mJ0sszO78y073wJchpZPSMXkqiBCV3VMaFWb06rKDB4KkwWMpHRNz67ZbFq9nv1UgOu8FmbGDzE_cJORka7XMsDlgfRSlIcvAuMcAcEKrOroRrQIq_WW03UXdZGmQXNub8kakzELyZs8887f96NFkrmcqqZ7jbP9v1HuwFaWYyo3M6fYhQKP9mBziXlwHxptPuh_vn-0J4lcLEacKVpdab_6CVda-Z2iOFKmfV9Ja3QHMUOVdc4TpRZjx_xpiQPoOredWkPNHlVQQ4LYQaUWo4SZkpgNoQYlXDDDFFwLAuFrtkVEIAQmSSEPKSOsYnCiB2aAIJD5dlAVFe0QilEc8SNQZFkuRzylEYpC-GEyYlUCqRL1ULMEV7lpvTBjHJeje_Ny5IHG8VLjlOBiLprMaDZ-Eirn8-NlkTbyCE69bhmGTfB36Uz8rsCr3Tlp4_jvouew3ug8up5733w4gQ0i4XZ6l68MxfFwwk9hLZyO-6PhWeZ9X57e3Oo
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5qFdGDb_FtEA9eAu0mmwd4kcaoWIpYld5Ckp3Vgk1CX2d_gr_RX-JsmtQKCoKQQw6zk2V2v935ws63AKexEzJWs1GXTJq6SQmt7iKv68LCWNoiEiyXa3pq2q2W0-m4dxU4L2thJvoQ0x9uChn5eq0AjpmQMyiPnyXhnAjBHMyb3LUIlvPevf_Y_KqLtC1eansr1ZhCWUid5Jk2_r4ffSWZs6lqvtf4q__r5RqsFDmmdjGZFOtQwWQDlmeUBzfhuo297sfbe3uUqcVigEIzPK39Emao3ZdnitJEG3dDLa_R7aWCXHqImdZIqWF5tcQWPPqXD41rvbhUQY8ZcQedO4IzYSthNqIanKEUli3RiCIZGq7DZCQlJUkxxlwwUbOQmZEdEQkUoRvVZc3YhmqSJrgDmirLReJTBuNkRA8lI04tUi7JD7d34awMbRAXiuOqd69ByTwoOEEenF04mZpmE5mNn4wOyvEJCqQNAmZahulYlsvoc_lI_O4gaFz5-cve302PYfHO84PmTet2H5aYYtv5Ub4DqA77IzyEhXg87A76R8Xk-wRdidxl
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=Semi%E2%80%90Supervised+3D+Shape+Recognition+via+Multimodal+Deep+Co%E2%80%90training&rft.jtitle=Computer+graphics+forum&rft.au=Song%2C+Mofei&rft.au=Liu%2C+Yu&rft.au=Xiao+Fan+Liu&rft.date=2020-10-01&rft.pub=Blackwell+Publishing+Ltd&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=39&rft.issue=7&rft.spage=279&rft.epage=289&rft_id=info:doi/10.1111%2Fcgf.14144&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-7055&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-7055&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-7055&client=summon