Real-Time 3D Face Alignment Using an Encoder-Decoder Network With an Efficient Deconvolution Layer

In the field of 3D face alignment, most researchers have focused on improving the prediction accuracy of algorithms and ignored the portability for practical applications. To this end, this study presents a real-time 3D face-alignment method that uses an encoder-decoder network with an efficient dec...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE signal processing letters Ročník 27; s. 1944 - 1948
Hlavní autoři:	Ning, Xin, Duan, Pengfei, Li, Weijun, Zhang, Shaolin
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	3D face alignment Algorithms Alignment Coders Decoding Deconvolution encoder decoder network Encoders-Decoders Encoding Face recognition Faces Real time real time application Real-time systems Three-dimensional displays
ISSN:	1070-9908, 1558-2361
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	In the field of 3D face alignment, most researchers have focused on improving the prediction accuracy of algorithms and ignored the portability for practical applications. To this end, this study presents a real-time 3D face-alignment method that uses an encoder-decoder network with an efficient deconvolution layer. The fusion of the encoding and decoding feature adds more abundant features to this network. An efficient deconvolution layer at the decoding stage applies the L1 norm to select useful features and generate abundant ones through linear operations. Experimental results using the standard AFLW2000-3D and AFLW-LFPA datasets show that our algorithm has low prediction errors with real-time applicability.
AbstractList	In the field of 3D face alignment, most researchers have focused on improving the prediction accuracy of algorithms and ignored the portability for practical applications. To this end, this study presents a real-time 3D face-alignment method that uses an encoder-decoder network with an efficient deconvolution layer. The fusion of the encoding and decoding feature adds more abundant features to this network. An efficient deconvolution layer at the decoding stage applies the L1 norm to select useful features and generate abundant ones through linear operations. Experimental results using the standard AFLW2000-3D and AFLW-LFPA datasets show that our algorithm has low prediction errors with real-time applicability.
Author	Li, Weijun Zhang, Shaolin Ning, Xin Duan, Pengfei
Author_xml	– sequence: 1 givenname: Xin orcidid: 0000-0001-7897-1673 surname: Ning fullname: Ning, Xin email: ningxin@semi.ac.cn organization: Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China – sequence: 2 givenname: Pengfei surname: Duan fullname: Duan, Pengfei email: duanpengfei@wavewisdom-bj.com organization: Cognitive Computing Technology Joint Laboratory, Wave Group, Beijing, China – sequence: 3 givenname: Weijun orcidid: 0000-0001-9668-2883 surname: Li fullname: Li, Weijun email: wjli@semi.ac.cn organization: Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China – sequence: 4 givenname: Shaolin surname: Zhang fullname: Zhang, Shaolin email: zsl1830@163.com organization: Cognitive Computing Technology Joint Laboratory, Wave Group, Beijing, China
BookMark	eNp9kM9LwzAUx4NMcE7vgpeA586XpOma49gPFYqKbngsafY6M7t0pp2y_952Gx48ePo-yOfz8viek44rHRJyxaDPGKjb5PW5z4FDX4DgfDA4IV0mZRxwEbFOM8MAAqUgPiPnVbUCgJjFskuyF9RFMLNrpGJMp9ogHRZ26dboajqvrFtS7ejEmXKBPhjjPukj1t-l_6Bvtn7fv-e5NbZVWsJ9lcW2tqWjid6hvyCnuS4qvDxmj8ynk9noPkie7h5GwyQwXLE6QJVnMQo0XEvDAWMemgwUx9DkUkm9aBJMpAcxy7VRmsUGQpFJEBnTJo9Ej9wc9m58-bnFqk5X5da75suUhxGwSAHIhooOlPFlVXnMU2Nr3V5be22LlEHa9pk2faZtn-mxz0aEP-LG27X2u_-U64NiEfEXV1xIySPxA1Iqgj0
CODEN	ISPLEM
CitedBy_id	crossref_primary_10_1007_s11042_022_12155_0 crossref_primary_10_1080_09540091_2021_2025340 crossref_primary_10_1016_j_cag_2022_03_011 crossref_primary_10_1155_2022_3606469 crossref_primary_10_1007_s00371_024_03316_3 crossref_primary_10_1016_j_displa_2021_102094 crossref_primary_10_1080_09540091_2021_2012423 crossref_primary_10_3389_fnbot_2023_1148545 crossref_primary_10_1016_j_displa_2021_102135 crossref_primary_10_3390_electronics11060875 crossref_primary_10_1007_s11263_022_01742_1 crossref_primary_10_1007_s11042_023_14519_6 crossref_primary_10_3390_app13137611 crossref_primary_10_1155_2021_1865538 crossref_primary_10_1109_ACCESS_2021_3056671 crossref_primary_10_1007_s11042_022_12856_6 crossref_primary_10_1016_j_bspc_2023_105906 crossref_primary_10_1016_j_displa_2021_102028 crossref_primary_10_1007_s11042_022_12849_5 crossref_primary_10_1155_2022_7104750 crossref_primary_10_1080_09540091_2021_2024510 crossref_primary_10_1007_s11277_022_09790_z crossref_primary_10_1155_2022_3076432 crossref_primary_10_1155_2022_3306661 crossref_primary_10_1155_2022_3902107 crossref_primary_10_1016_j_displa_2022_102192 crossref_primary_10_1109_TCSVT_2025_3526960 crossref_primary_10_1109_ACCESS_2021_3120419 crossref_primary_10_1016_j_neucom_2023_126941 crossref_primary_10_1002_cpe_6714 crossref_primary_10_1109_TCSVT_2022_3192422 crossref_primary_10_1155_2022_7628124 crossref_primary_10_1109_MMUL_2022_3195091 crossref_primary_10_1002_cpe_7234 crossref_primary_10_4018_JOEUC_347217 crossref_primary_10_1007_s11042_022_12166_x crossref_primary_10_1007_s11042_021_11866_0 crossref_primary_10_1016_j_displa_2021_102042 crossref_primary_10_1016_j_displa_2021_102043 crossref_primary_10_1155_2022_9401001 crossref_primary_10_1016_j_displa_2021_102044 crossref_primary_10_1016_j_displa_2022_102225 crossref_primary_10_1002_cpe_6704 crossref_primary_10_1007_s11042_022_12963_4 crossref_primary_10_1109_ACCESS_2021_3090215 crossref_primary_10_1016_j_compbiomed_2025_110437 crossref_primary_10_1002_cpe_6331 crossref_primary_10_1007_s11042_021_11667_5 crossref_primary_10_3389_fnbot_2022_1082346 crossref_primary_10_1007_s00371_023_03202_4 crossref_primary_10_1155_2022_3264485 crossref_primary_10_1016_j_displa_2021_102050 crossref_primary_10_1080_09540091_2022_2052264 crossref_primary_10_3389_fnbot_2023_1193823 crossref_primary_10_1155_2022_7316133 crossref_primary_10_1016_j_displa_2021_102054 crossref_primary_10_1016_j_displa_2021_102052 crossref_primary_10_1007_s11042_022_12055_3 crossref_primary_10_3390_app12094356 crossref_primary_10_1155_2022_8409780 crossref_primary_10_1007_s11042_022_12459_1 crossref_primary_10_3390_s23229055 crossref_primary_10_1155_2021_3370580 crossref_primary_10_1016_j_patcog_2022_108783 crossref_primary_10_3390_s22041410 crossref_primary_10_1016_j_displa_2021_102062 crossref_primary_10_1155_2022_2778181 crossref_primary_10_1080_13682199_2023_2212572 crossref_primary_10_3389_fevo_2023_1212732 crossref_primary_10_3389_fnins_2023_1226154 crossref_primary_10_1016_j_neucom_2023_127125 crossref_primary_10_1016_j_displa_2021_102102 crossref_primary_10_1016_j_displa_2021_102067 crossref_primary_10_1016_j_displa_2023_102588 crossref_primary_10_1016_j_displa_2021_102107 crossref_primary_10_1007_s00521_021_06151_y crossref_primary_10_1080_09540091_2022_2139352 crossref_primary_10_1007_s11042_023_17545_6 crossref_primary_10_1002_cpe_6873 crossref_primary_10_1155_2022_1686219 crossref_primary_10_1007_s11760_025_03983_2 crossref_primary_10_1155_2022_5297605 crossref_primary_10_1016_j_displa_2021_102076 crossref_primary_10_3389_fenrg_2022_972437 crossref_primary_10_1016_j_displa_2021_102073 crossref_primary_10_1007_s11042_022_12250_2 crossref_primary_10_1016_j_displa_2021_102077 crossref_primary_10_1007_s11042_022_12078_w crossref_primary_10_1016_j_displa_2021_102114 crossref_primary_10_1007_s11042_022_12708_3 crossref_primary_10_3390_s25113288 crossref_primary_10_1016_j_displa_2021_102080 crossref_primary_10_1007_s11042_022_12242_2 crossref_primary_10_1002_cpe_7151 crossref_primary_10_1016_j_displa_2021_102089 crossref_primary_10_1007_s11042_023_14874_4 crossref_primary_10_1016_j_displa_2022_102149 crossref_primary_10_1007_s11042_022_13327_8 crossref_primary_10_1155_2022_4448036
Cites_doi	10.1109/TPAMI.2018.2885995 10.1109/CVPR.2019.00119 10.1109/ICCVW.2017.190 10.24963/ijcai.2018/309 10.1145/311535.311556 10.1109/ICCVW.2019.00063 10.1109/CVPR.2018.00741 10.1109/ICCV.2015.421 10.1109/TCYB.2014.2307067 10.1109/CVPR.2016.454 10.1109/CVPR.2017.713 10.1109/CVPR.2016.90 10.1007/978-3-319-24574-4_28 10.1109/CVPR.2016.23 10.1109/ICCV.2015.425 10.1109/CVPR.2013.75 10.1007/978-3-319-46484-8_29 10.1109/CVPR.2019.00584 10.1007/978-3-030-01264-9_33 10.1109/TPAMI.2010.63 10.1007/s11263-013-0667-3
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/LSP.2020.3032277
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Computer and Information Systems Abstracts Electronics & Communications 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 Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-2361
EndPage	1948
ExternalDocumentID	10_1109_LSP_2020_3032277 9235526
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 61901436 funderid: 10.13039/501100001809
GroupedDBID	-~X .DC 0R~ 29I 3EH 4.4 5GY 5VS 6IK 85S 97E AAJGR AARMG AASAJ AAWTH AAYJJ ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TAE TN5 VH1 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c291t-e9fb8e3ec2a5c20e824cb092e4cf595ad4cf0c6a781fac9a18c043b503b1acf63
IEDL.DBID	RIE
ISICitedReferencesCount	150
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000589190600004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1070-9908
IngestDate	Sun Nov 30 04:57:41 EST 2025 Sat Nov 29 03:38:51 EST 2025 Tue Nov 18 21:18:44 EST 2025 Wed Aug 27 02:29:33 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c291t-e9fb8e3ec2a5c20e824cb092e4cf595ad4cf0c6a781fac9a18c043b503b1acf63
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-9668-2883 0000-0001-7897-1673
PQID	2460169005
PQPubID	75747
PageCount	5
ParticipantIDs	proquest_journals_2460169005 crossref_primary_10_1109_LSP_2020_3032277 crossref_citationtrail_10_1109_LSP_2020_3032277 ieee_primary_9235526
PublicationCentury	2000
PublicationDate	20200000 2020-00-00 20200101
PublicationDateYYYYMMDD	2020-01-01
PublicationDate_xml	– year: 2020 text: 20200000
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE signal processing letters
PublicationTitleAbbrev	LSP
PublicationYear	2020
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref23 ref15 ref14 ref20 ref11 abadi (ref12) 0 ye (ref8) 0 ref22 ref10 ref21 ref2 ref1 ref17 ref16 ref19 ref18 ref7 ref9 ref4 ref3 ref6 ref5
References_xml	– ident: ref17 doi: 10.1109/TPAMI.2018.2885995 – ident: ref6 doi: 10.1109/CVPR.2019.00119 – ident: ref4 doi: 10.1109/ICCVW.2017.190 – ident: ref7 doi: 10.24963/ijcai.2018/309 – ident: ref10 doi: 10.1145/311535.311556 – ident: ref18 doi: 10.1109/ICCVW.2019.00063 – year: 0 ident: ref8 article-title: Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers publication-title: Proc Int Conf Learn Representations – ident: ref9 doi: 10.1109/CVPR.2018.00741 – start-page: 265 year: 0 ident: ref12 article-title: TensorFlow: A system for large-scale machine learning publication-title: 12th USENIX Symp Oper Syst Des Implement (OSDI '16) – ident: ref13 doi: 10.1109/ICCV.2015.421 – ident: ref2 doi: 10.1109/TCYB.2014.2307067 – ident: ref22 doi: 10.1109/CVPR.2016.454 – ident: ref1 doi: 10.1109/CVPR.2017.713 – ident: ref23 doi: 10.1109/CVPR.2016.90 – ident: ref19 doi: 10.1007/978-3-319-24574-4_28 – ident: ref3 doi: 10.1109/CVPR.2016.23 – ident: ref11 doi: 10.1109/ICCV.2015.425 – ident: ref15 doi: 10.1109/CVPR.2013.75 – ident: ref20 doi: 10.1007/978-3-319-46484-8_29 – ident: ref21 doi: 10.1109/CVPR.2019.00584 – ident: ref5 doi: 10.1007/978-3-030-01264-9_33 – ident: ref16 doi: 10.1109/TPAMI.2010.63 – ident: ref14 doi: 10.1007/s11263-013-0667-3
SSID	ssj0008185
Score	2.615376
Snippet	In the field of 3D face alignment, most researchers have focused on improving the prediction accuracy of algorithms and ignored the portability for practical...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1944
SubjectTerms	3D face alignment Algorithms Alignment Coders Decoding Deconvolution encoder decoder network Encoders-Decoders Encoding Face recognition Faces Real time real time application Real-time systems Three-dimensional displays
Title	Real-Time 3D Face Alignment Using an Encoder-Decoder Network With an Efficient Deconvolution Layer
URI	https://ieeexplore.ieee.org/document/9235526 https://www.proquest.com/docview/2460169005
Volume	27
WOSCitedRecordID	wos000589190600004&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: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 1558-2361 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008185 issn: 1070-9908 databaseCode: RIE dateStart: 19940101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UPOjBt7i-yMGLYNw0bZrmKOriYVnEB3or03SqC0uVdfX3m6TdRVEETyl0ppR8yTySeQAcibQgZ8cnPMMIeVKS5gYp4qaK0ypRAjWGriV9PRhkj4_meg5OZrkwRBSCz-jUP4a7_PLFvvujsq4zRpSS6TzMa62bXK2Z1PWKp4kvFNxJ2Gx6JSlMt3977RxB6fxT4Zav1t9UUOip8kMQB-3SW_3ff63BSmtFsrMG9nWYo3oDlr_UFtyE4saZgNxneLD4gvXQEjsbDZ_C5T8LgQIMa3ZZ-5z2Mb-gMLJBExXOHoaT5_A-VJjwLJ6i_mgXKuujM9W34L53eXd-xduGCtxKE004marIKCYrUVkpKJOJLYSRlNhKGYWlG4VNUWdRhdZglFmRxIUScRGhrdJ4Gxbql5p2gAlScaJspEvn1lKsUJhSYSHRuhm2pexAdzrHuW2rjfumF6M8eB3C5A6V3KOSt6h04HjG8dpU2viDdtOjMKNrAejA_hTGvN2Kb7lMQsUZJ212f-fagyX_7eZcZR8WJuN3OoBF-zEZvo0Pwyr7BFSMzv4
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB7xqAQc-uAhtqXUh16QMOs4dhIfUWEFIqwQBcEtmjgTWGkV0LLw-7Gd7KpVKyROjpQZJfJnz8OeB8BPkZTk7HjFM4yQq4pSbpAibuo4qZUWmGLoWpKnw2F2e2suFmB_ngtDRCH4jA78Y7jLrx7ssz8q6ztjRGuZLMKyVkpGbbbWXO561dNGGAruZGw2u5QUpp__vnCuoHQeqnALOE3_UkKhq8o_ojjol8Gn9_3ZZ_jY2ZHssAX-CyxQsw5rf1QX3IDy0hmB3Od4sPiIDdASOxyP7sL1PwuhAgwbdtz4rPYJP6IwsmEbF85uRtP78D7UmPAsnqJ56ZYqy9EZ65twPTi--nXCu5YK3EoTTTmZuswoJitRWykok8qWwkhSttZGY-VGYRNMs6hGazDKrFBxqUVcRmjrJN6CpeahoW1ggnSstI3Syjm2FGsUptJYSrRuhm0le9CfzXFhu3rjvu3FuAh-hzCFQ6XwqBQdKj3Ym3M8trU23qDd8CjM6ToAerAzg7HoNuNTIVWoOePkzdf_c_2AlZOr87zIT4dn32DVf6c9ZdmBpenkmb7DB_syHT1NdsOKewVCydJF
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=Real-Time+3D+Face+Alignment+Using+an+Encoder-Decoder+Network+With+an+Efficient+Deconvolution+Layer&rft.jtitle=IEEE+signal+processing+letters&rft.au=Ning%2C+Xin&rft.au=Duan%2C+Pengfei&rft.au=Li%2C+Weijun&rft.au=Zhang%2C+Shaolin&rft.date=2020&rft.issn=1070-9908&rft.eissn=1558-2361&rft.volume=27&rft.spage=1944&rft.epage=1948&rft_id=info:doi/10.1109%2FLSP.2020.3032277&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LSP_2020_3032277
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1070-9908&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1070-9908&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1070-9908&client=summon