SAL-Net: Self-Supervised Attribute Learning for Object Recognition and Segmentation

Existing attribute learning methods rely on predefined attributes, which require manual annotations. Due to the limitation of human experience, the predefined attributes are not capable enough of providing enough description. This paper proposes a self-supervised attribute learning (SAL) method, whi...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Wireless communications and mobile computing Ročník 2021; číslo 1
Hlavní autori:	Yang, Shu, JingWang, Arif, Sheeraz, Jia, Minli, Zhong, Shunan
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Oxford Hindawi 2021 John Wiley & Sons, Inc
Predmet:	Algorithms Annotations Classification Datasets Dictionaries Image annotation Image classification Image segmentation Learning Neural networks Object recognition Semantic segmentation Semantics
ISSN:	1530-8669, 1530-8677
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Existing attribute learning methods rely on predefined attributes, which require manual annotations. Due to the limitation of human experience, the predefined attributes are not capable enough of providing enough description. This paper proposes a self-supervised attribute learning (SAL) method, which automatically generates attribute descriptions by differentially occluding the object region to deal with the above problems. The relationship between attributes is formulated with triplet loss functions and is utilized to supervise the CNN. Attribute learning is used as an auxiliary task of a multitask image classification and segmentation network, in which self-supervision of attributes motivates the CNN to learn more discriminative features for the main semantic tasks. Experimental results on public benchmarks CUB-2011 and Pascal VOC show that the proposed SAL-Net can obtain more accurate classification and segmentation results without additional annotations. Moreover, the SAL-Net is embedded into a multiobject recognition and segmentation system, which realizes instance-aware semantic segmentation with the help of a region proposal algorithm and a fusion nonmaximum suppression algorithm.
AbstractList	Existing attribute learning methods rely on predefined attributes, which require manual annotations. Due to the limitation of human experience, the predefined attributes are not capable enough of providing enough description. This paper proposes a self‐supervised attribute learning (SAL) method, which automatically generates attribute descriptions by differentially occluding the object region to deal with the above problems. The relationship between attributes is formulated with triplet loss functions and is utilized to supervise the CNN. Attribute learning is used as an auxiliary task of a multitask image classification and segmentation network, in which self‐supervision of attributes motivates the CNN to learn more discriminative features for the main semantic tasks. Experimental results on public benchmarks CUB‐2011 and Pascal VOC show that the proposed SAL‐Net can obtain more accurate classification and segmentation results without additional annotations. Moreover, the SAL‐Net is embedded into a multiobject recognition and segmentation system, which realizes instance‐aware semantic segmentation with the help of a region proposal algorithm and a fusion nonmaximum suppression algorithm.
Author	Jia, Minli Zhong, Shunan Arif, Sheeraz Yang, Shu JingWang
Author_xml	– sequence: 1 givenname: Shu orcidid: 0000-0003-1587-0474 surname: Yang fullname: Yang, Shu organization: School of Information and ElectronicsBeijing Institute of TechnologyBeijing 100081Chinabit.edu.cn – sequence: 2 orcidid: 0000-0002-3653-9951 surname: JingWang fullname: JingWang organization: School of Information and ElectronicsBeijing Institute of TechnologyBeijing 100081Chinabit.edu.cn – sequence: 3 givenname: Sheeraz orcidid: 0000-0002-3590-9535 surname: Arif fullname: Arif, Sheeraz organization: Department of Computer ScienceFaculty of Information TechnologySalim Habib UniversityKarachi 75400Pakistan – sequence: 4 givenname: Minli orcidid: 0000-0002-8955-4549 surname: Jia fullname: Jia, Minli organization: Research Institute of China Mobile Communications Co.Ltd.Beijing 100053China – sequence: 5 givenname: Shunan orcidid: 0000-0002-2981-0459 surname: Zhong fullname: Zhong, Shunan organization: School of Information and ElectronicsBeijing Institute of TechnologyBeijing 100081Chinabit.edu.cn
BookMark	eNp9kEtLw0AUhQepYFvd-QMCLjV2nsnEXSm-oFgwug4zyZ06pZ3UyUTx35uQ4kLQ1X3wnXu4Z4JGrnaA0DnB14QIMaOYkhmVGWGYHaExEQzHMknT0U-fZCdo0jQbjDHr4DHK8_kyfoJwE-WwNXHe7sF_2AaqaB6Ct7oNEC1BeWfdOjK1j1Z6A2WInqGs184GW7tIuapTr3fgguoXp-jYqG0DZ4c6Ra93ty-Lh3i5un9cdH4lY2mIuRJGE04M5byiSSkBS86hIoIInRAlDSdYCIFppqnSVGOVaCpJpkQ3aMOm6GK4u_f1ewtNKDZ1611nWVAhsZBpynhHXQ1U6eum8WCKvbc75b8Kgos-tqKPrTjE1uH0F17a4a3gld3-JbocRG_WVerT_m_xDVYxfO0
CitedBy_id	crossref_primary_10_1155_2021_8927822 crossref_primary_10_1155_2022_7086599 crossref_primary_10_1155_2022_6014795
Cites_doi	10.1109/CVPRW.2016.99 10.1155/2018/3748141 10.1109/TCSVT.2019.2892802 10.1007/s11063-020-10241-8 10.1109/ICCV.2015.167 10.1007/s11263-015-0816-y 10.1109/CVPRW.2009.5206594 10.1109/tpami.2017.2738004 10.1109/ICCV.1999.790410 10.1109/ICCV.2017.139 10.1007/s11042-020-09316-4 10.1109/ICCV.2015.170 10.1007/978-3-319-10602-1_48 10.1109/TMM.2016.2631122 10.1109/TPAMI.2016.2645157 10.1109/CVPR.2005.177 10.1007/s11263-013-0620-5 10.1109/CVPR.2015.7299046 10.1109/CVPR.2018.00779 10.1016/j.cviu.2021.103184 10.1109/TIP.2017.2751960 10.1007/s11263-009-0275-4 10.1109/ACCESS.2020.3012695 10.1109/TPAMI.2017.2723882 10.1109/CVPR.2015.7298594 10.1109/ITSC.2018.8569372 10.1109/CVPR.2014.411 10.1007/11744023_32 10.1007/978-3-030-68780-9_26 10.1109/CVPR.2016.308 10.1109/TMM.2019.2919469 10.1016/j.patcog.2019.06.006 10.21629/JSEE.2020.01.06 10.1109/TPAMI.2013.128 10.1145/2647868.2654966 10.4018/IJMDEM.2020070103 10.1109/TMM.2015.2438712 10.1155/2020/6689134 10.1109/TPAMI.2017.2781233 10.1109/TPAMI.2011.48 10.1109/CVPRW.2009.5206772 10.1145/3240508.3240550 10.1109/CVPR.2016.90 10.1007/978-3-319-46487-9_40 10.1007/978-3-319-46466-4_6 10.1155/2020/8861886 10.1109/ICPR.2018.8546066 10.1109/TMM.2021.3103605 10.1109/TPAMI.2015.2487986 10.1109/CVPR.2012.6248089 10.1609/aaai.v31i1.11202
ContentType	Journal Article
Copyright	Copyright © 2021 Shu Yang et al. Copyright © 2021 Shu Yang et al. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: Copyright © 2021 Shu Yang et al. – notice: Copyright © 2021 Shu Yang et al. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	RHU RHW RHX AAYXX CITATION 7SC 7SP 7XB 8FD 8FE 8FG ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- L7M L~C L~D M0N P5Z P62 PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS Q9U
DOI	10.1155/2021/2891303
DatabaseName	Hindawi Publishing Complete Hindawi Publishing Subscription Journals Hindawi Publishing Open Access CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts ProQuest Central (purchase pre-March 2016) Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials - QC ProQuest Central Technology collection ProQuest One Community College ProQuest Central ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Computing Database ProQuest advanced technologies & aerospace journals ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database 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 ProQuest Central Basic
DatabaseTitle	CrossRef Publicly Available Content Database Computer Science Database ProQuest Central Student Technology Collection Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Central Korea ProQuest Central (New) Advanced Technologies Database with Aerospace Advanced Technologies & Aerospace Collection ProQuest Computing ProQuest Central Basic ProQuest One Academic Eastern Edition Electronics & Communications Abstracts ProQuest Technology Collection ProQuest SciTech Collection Computer and Information Systems Abstracts Professional Advanced Technologies & Aerospace Database ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New)
DatabaseTitleList	CrossRef Publicly Available Content Database
Database_xml	– sequence: 1 dbid: RHX name: Hindawi Publishing Open Access url: http://www.hindawi.com/journals/ sourceTypes: Publisher – sequence: 2 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1530-8677
Editor	Yan, Ming
Editor_xml	– sequence: 1 givenname: Ming surname: Yan fullname: Yan, Ming
ExternalDocumentID	10_1155_2021_2891303
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 61620106002 – fundername: Central Government Guides Local Science and Technology Development Fund Project of China grantid: 2021ZY0004
GroupedDBID	.3N .4S .DC .GA 05W 0R~ 123 1L6 1OC 33P 3SF 3WU 4.4 4ZD 50Y 50Z 52M 52O 52T 52U 52W 66C 6OB 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 930 A03 AAESR AAFWJ AAJEY AAONW ABIJN ABPVW ACGFO ADBBV ADIZJ AENEX AEUQT AFBPY AFKRA AIAGR AJXKR ALAGY ALMA_UNASSIGNED_HOLDINGS AMBMR ARAPS ARCSS ASPBG ATUGU AVWKF AZBYB AZQEC AZVAB BAFTC BCNDV BENPR BGLVJ BHBCM BNHUX BROTX BRXPI CCPQU CS3 D-E D-F DPXWK DR2 DU5 DWQXO EBS EDO F00 F01 F04 F21 G-S G.N GNP GNUQQ GODZA GROUPED_DOAJ H.T H.X HCIFZ HZ~ I-F IAO ITC ITG ITH IX1 JPC K7- KQQ LAW LITHE LP6 LP7 M0N MK4 MY~ N04 N05 NF~ O66 O9- OIG OK1 P2P P2W P2X P4D PIMPY Q.N QB0 QRW R.K RHU RHW RHX RWI RX1 RYL SUPJJ TUS UB1 W8V W99 WBKPD WIH WLBEL XPP XV2 ~IA ~WT .Y3 24P 31~ 5VS AAEVG AAMMB AANHP AAYXX AAZKR ACBWZ ACCMX ACRPL ACXQS ACYXJ ADNMO AEFGJ AEIMD AEUCX AFFHD AFZJQ AGQPQ AGXDD AIDQK AIDYY ALUQN AZFZN BDRZF BFHJK CITATION EJD FEDTE H13 HF~ HVGLF LH4 LW6 O8X PHGZM PHGZT PQGLB ROL WYUIH 7SC 7SP 7XB 8FD 8FE 8FG ABUWG JQ2 L7M L~C L~D P62 PKEHL PQEST PQQKQ PQUKI PRINS Q9U
ID	FETCH-LOGICAL-c337t-4a5fb141f244d26c8e0844ed1515b61a8f410555029b2ab2b0a6b2819a5b2bbf3
IEDL.DBID	RHX
ISICitedReferencesCount	3
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000803809500004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1530-8669
IngestDate	Fri Jul 25 09:29:55 EDT 2025 Sat Nov 29 01:44:04 EST 2025 Tue Nov 18 20:55:51 EST 2025 Sun Jun 02 18:51:36 EDT 2024
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1
Language	English
License	This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c337t-4a5fb141f244d26c8e0844ed1515b61a8f410555029b2ab2b0a6b2819a5b2bbf3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-3590-9535 0000-0003-1587-0474 0000-0002-2981-0459 0000-0002-3653-9951 0000-0002-8955-4549
OpenAccessLink	https://dx.doi.org/10.1155/2021/2891303
PQID	2580587734
PQPubID	2034344
ParticipantIDs	proquest_journals_2580587734 crossref_primary_10_1155_2021_2891303 crossref_citationtrail_10_1155_2021_2891303 hindawi_primary_10_1155_2021_2891303
PublicationCentury	2000
PublicationDate	2021-00-00
PublicationDateYYYYMMDD	2021-01-01
PublicationDate_xml	– year: 2021 text: 2021-00-00
PublicationDecade	2020
PublicationPlace	Oxford
PublicationPlace_xml	– name: Oxford
PublicationTitle	Wireless communications and mobile computing
PublicationYear	2021
Publisher	Hindawi John Wiley & Sons, Inc
Publisher_xml	– name: Hindawi – name: John Wiley & Sons, Inc
References	e_1_2_9_52_2 e_1_2_9_50_2 e_1_2_9_33_2 e_1_2_9_56_2 e_1_2_9_12_2 e_1_2_9_31_2 e_1_2_9_54_2 e_1_2_9_14_2 e_1_2_9_37_2 e_1_2_9_16_2 e_1_2_9_35_2 e_1_2_9_58_2 e_1_2_9_18_2 e_1_2_9_39_2 e_1_2_9_41_2 e_1_2_9_20_2 e_1_2_9_45_2 e_1_2_9_22_2 e_1_2_9_43_2 e_1_2_9_6_2 e_1_2_9_4_2 e_1_2_9_2_2 e_1_2_9_8_2 e_1_2_9_24_2 e_1_2_9_49_2 e_1_2_9_26_2 e_1_2_9_47_2 e_1_2_9_28_2 e_1_2_9_51_2 e_1_2_9_30_2 e_1_2_9_34_2 e_1_2_9_55_2 e_1_2_9_11_2 e_1_2_9_32_2 e_1_2_9_53_2 Wah C. (e_1_2_9_10_2) 2011 e_1_2_9_13_2 e_1_2_9_38_2 e_1_2_9_59_2 e_1_2_9_15_2 e_1_2_9_57_2 e_1_2_9_17_2 e_1_2_9_19_2 e_1_2_9_40_2 e_1_2_9_21_2 e_1_2_9_44_2 e_1_2_9_23_2 e_1_2_9_42_2 e_1_2_9_7_2 e_1_2_9_5_2 e_1_2_9_3_2 Chi S. (e_1_2_9_36_2) 2016 e_1_2_9_9_2 e_1_2_9_25_2 e_1_2_9_48_2 e_1_2_9_27_2 e_1_2_9_46_2 Ferrari V. (e_1_2_9_1_2) 2007 e_1_2_9_29_2
References_xml	– ident: e_1_2_9_32_2 doi: 10.1109/CVPRW.2016.99 – ident: e_1_2_9_22_2 doi: 10.1155/2018/3748141 – ident: e_1_2_9_38_2 – ident: e_1_2_9_52_2 doi: 10.1109/TCSVT.2019.2892802 – ident: e_1_2_9_20_2 doi: 10.1007/s11063-020-10241-8 – ident: e_1_2_9_23_2 doi: 10.1109/ICCV.2015.167 – ident: e_1_2_9_49_2 doi: 10.1007/s11263-015-0816-y – start-page: 433 volume-title: Advances in Neural Information Processing Systems year: 2007 ident: e_1_2_9_1_2 – ident: e_1_2_9_5_2 doi: 10.1109/CVPRW.2009.5206594 – ident: e_1_2_9_31_2 doi: 10.1109/tpami.2017.2738004 – ident: e_1_2_9_46_2 doi: 10.1109/ICCV.1999.790410 – ident: e_1_2_9_59_2 – ident: e_1_2_9_7_2 doi: 10.1109/ICCV.2017.139 – ident: e_1_2_9_45_2 doi: 10.1007/s11042-020-09316-4 – ident: e_1_2_9_53_2 doi: 10.1109/ICCV.2015.170 – ident: e_1_2_9_29_2 doi: 10.1007/978-3-319-10602-1_48 – ident: e_1_2_9_56_2 doi: 10.1109/TMM.2016.2631122 – ident: e_1_2_9_40_2 doi: 10.1109/TPAMI.2016.2645157 – ident: e_1_2_9_47_2 doi: 10.1109/CVPR.2005.177 – ident: e_1_2_9_50_2 doi: 10.1007/s11263-013-0620-5 – ident: e_1_2_9_35_2 doi: 10.1109/CVPR.2015.7299046 – ident: e_1_2_9_44_2 doi: 10.1109/CVPR.2018.00779 – ident: e_1_2_9_57_2 doi: 10.1016/j.cviu.2021.103184 – ident: e_1_2_9_54_2 doi: 10.1109/TIP.2017.2751960 – ident: e_1_2_9_28_2 doi: 10.1007/s11263-009-0275-4 – ident: e_1_2_9_18_2 doi: 10.1109/ACCESS.2020.3012695 – ident: e_1_2_9_43_2 doi: 10.1109/TPAMI.2017.2723882 – ident: e_1_2_9_12_2 – ident: e_1_2_9_13_2 doi: 10.1109/CVPR.2015.7298594 – ident: e_1_2_9_41_2 doi: 10.1109/ITSC.2018.8569372 – ident: e_1_2_9_26_2 – ident: e_1_2_9_39_2 doi: 10.1109/CVPR.2014.411 – ident: e_1_2_9_48_2 doi: 10.1007/11744023_32 – ident: e_1_2_9_19_2 doi: 10.1007/978-3-030-68780-9_26 – ident: e_1_2_9_15_2 doi: 10.1109/CVPR.2016.308 – ident: e_1_2_9_55_2 doi: 10.1109/TMM.2019.2919469 – ident: e_1_2_9_37_2 doi: 10.1016/j.patcog.2019.06.006 – ident: e_1_2_9_34_2 doi: 10.21629/JSEE.2020.01.06 – ident: e_1_2_9_42_2 doi: 10.1109/TPAMI.2013.128 – ident: e_1_2_9_9_2 doi: 10.1145/2647868.2654966 – ident: e_1_2_9_21_2 doi: 10.4018/IJMDEM.2020070103 – ident: e_1_2_9_3_2 doi: 10.1109/TMM.2015.2438712 – ident: e_1_2_9_17_2 doi: 10.1155/2020/6689134 – ident: e_1_2_9_33_2 doi: 10.1109/TPAMI.2017.2781233 – ident: e_1_2_9_25_2 – ident: e_1_2_9_30_2 doi: 10.1109/TPAMI.2011.48 – ident: e_1_2_9_8_2 doi: 10.1109/CVPRW.2009.5206772 – ident: e_1_2_9_4_2 doi: 10.1145/3240508.3240550 – ident: e_1_2_9_14_2 doi: 10.1109/CVPR.2016.90 – ident: e_1_2_9_24_2 doi: 10.1007/978-3-319-46487-9_40 – start-page: 475 volume-title: European Conference on Computer Vision year: 2016 ident: e_1_2_9_36_2 – ident: e_1_2_9_11_2 doi: 10.1007/978-3-319-46466-4_6 – ident: e_1_2_9_16_2 doi: 10.1155/2020/8861886 – ident: e_1_2_9_58_2 doi: 10.1109/ICPR.2018.8546066 – volume-title: The Caltech-UCSD Birds-200-2011 Dataset year: 2011 ident: e_1_2_9_10_2 – ident: e_1_2_9_27_2 doi: 10.1109/TMM.2021.3103605 – ident: e_1_2_9_6_2 doi: 10.1109/TPAMI.2015.2487986 – ident: e_1_2_9_2_2 doi: 10.1109/CVPR.2012.6248089 – ident: e_1_2_9_51_2 doi: 10.1609/aaai.v31i1.11202
SSID	ssj0003021
Score	2.2788837
Snippet	Existing attribute learning methods rely on predefined attributes, which require manual annotations. Due to the limitation of human experience, the predefined...
SourceID	proquest crossref hindawi
SourceType	Aggregation Database Enrichment Source Index Database Publisher
SubjectTerms	Algorithms Annotations Classification Datasets Dictionaries Image annotation Image classification Image segmentation Learning Neural networks Object recognition Semantic segmentation Semantics
SummonAdditionalLinks	– databaseName: Computer Science Database dbid: K7- link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NS8MwFA86FfTgtzidksM8SVibJmnqRYY4BMcUp7BbSdp0DmY3107_fZM2nYKoB3srfQml7_V95_0AaCpBfN-LE6RowBHBWCAhVYx47EqhL20kipH5Xb_X44NBcG8Tbpltq6x0YqGo40lkcuQtTLlDud6XXE5fkUGNMtVVC6GxDFZcjF0j57c-Wmhiz8F2XqqDOGNB1fhOqYn53RY2NboKLsuapLVnEwu_j77p5sLgdLb--6rbYNO6mrBdysYOWFLpLtj4MoBwD_T77S7qqfwC9tU4Qf351KiOTMWwnZdQWAraCaxDqN1beCdN3gY-VG1HkxSKNNarhy_2EFO6D546149XN8jCLKDI8_wcEUET6RI30ZY-xiziyuGEqNi4OpK5giemFVRHMjiQWEgsHcGkqb8Jqm9k4h2AWjpJ1SGAOjrDgstIyiAiARMi4MycASdMr3Adrw7Oqy8dRnYGuYHCGIdFLEJpaPgSWr7UwdmCelrO3viBrmmZ9gdZo2JXaH_ULPzk1dHvj4_ButmszL40QC2fzdUJWI3e8lE2Oy3k7gPNt9vx priority: 102 providerName: ProQuest
Title	SAL-Net: Self-Supervised Attribute Learning for Object Recognition and Segmentation
URI	https://dx.doi.org/10.1155/2021/2891303 https://www.proquest.com/docview/2580587734
Volume	2021
WOSCitedRecordID	wos000803809500004&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: 1530-8677 dateEnd: 20250131 omitProxy: false ssIdentifier: ssj0003021 issn: 1530-8669 databaseCode: P5Z dateStart: 20170101 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 1530-8677 dateEnd: 20250131 omitProxy: false ssIdentifier: ssj0003021 issn: 1530-8669 databaseCode: K7- dateStart: 20170101 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1530-8677 dateEnd: 20250131 omitProxy: false ssIdentifier: ssj0003021 issn: 1530-8669 databaseCode: BENPR dateStart: 20170101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1530-8677 dateEnd: 20250131 omitProxy: false ssIdentifier: ssj0003021 issn: 1530-8669 databaseCode: PIMPY dateStart: 20170101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVWIB databaseName: Wiley Online Library Open Access customDbUrl: eissn: 1530-8677 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0003021 issn: 1530-8669 databaseCode: 24P dateStart: 20170101 isFulltext: true titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3dT8IwEG8ENdEH42dEkfQBn0zj1rVb5xsaCEbEBTRBX5Z265AEB2FD_31bKEQlRvewpMvdHq7X3l3v-jsAqpITz3PiBEnqM0Qw5ogLGSMW24KrRxmJGWR-y2u3Wa_nBwYkKVtN4Strp8Nz-xLrdJpG9SwwqpW30-wtN1zHwgYW1ULMdf1FffsP3m-WZ_NVh7wfg5UteGZXGrtgxziEsDafwT2wJtN9sP0FJvAAdLu1FmrL_Ap25TBB3elYL_BMxrCWzxtWSWhwUvtQOaHwQejTFdhZFAeNUsjTWHH338xVo_QQPDXqjzdNZJohoMhxvBwRThNhEztR9jjGbsSkxQiRsXZIhGtzluiCTRVvYF9gLrCwuCt0loxTNRCJcwSK6SiVxwCqGApzJiIh_Ij4Luc-c_VNbeIqDttySuBiIagwMkjhumHFMJxFDJSGWqyhEWsJnC-px3OEjF_oqkbmf5CVFxMSmuWUhZgyizKlVOTkf385BVt6OD8rKYNiPpnKM7ARveeDbFIB69f1dtCpgMKdh9Q7oC_qW3B7HzxXZqr1CTlTwGQ
linkProvider	Hindawi Publishing
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3BTtwwEB1RoAIOFCgIKG19gBOySBw7cZCqCkERaJcFsSBxS-3EASTILmwA8VN8Yz2JA0gIOHFoblHsiRI_zXjGM28Alo3iURRkOTUilpQzpqjSJqMy87WylzUSFWV-O-p05MlJfDAED00tDKZVNjqxUtRZL8UY-RoT0hPSyuW_-1cUu0bh6WrTQqOGRcvc31mXbfBrd8uu7wpj23-ONneo6ypA0yCISsqVyLXP_dwatoyFqTSe5NxkaNl16CuZY-aj3bizWDOlmfZUqPG4SQl7o_PAyv0EIzyQEXL1tyL6qPkDjzl-Vo_KMIybRHshMMbgrzE8E2zaczkT-PkMfe-78xe2oDJw21_-t18zBZNuK002auxPw5ApZmDiGcHiV-h27Vs7plwnXXOR0-5NH1XjwGRko6xbfRniGGZPid2-k32NcSly2KRV9QqiiszOPr10RVrFLBx_yFfNwXDRK8w8EOt9MiV1qnWc8jhUKpYh1rjz0M7wvWABVpuVTVLHsY6tPi6SytcSIkEcJA4HC7DyOLpfc4u8Mm7ZgeSdYUsNPBKniAbJEzYW3378E8Z2jvbaSXu30_oG4yi4jjQtwXB5fWO-w2h6W54Prn9UmCfw96OR9A-J0zei
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LT9wwEB7xVjnwahFQCj7AqbI2cezEQUIIFVagRQvqthK3YCfOggTZhQ1F_Wv9dXgSB5Aq2hMHcotiO0r8eT7PwzMAW0bxKAqynBoRS8oZU1Rpk1GZ-VrZy5JElTL_JOp25fl5fDYGf5qzMBhW2cjESlBngxRt5C0mpCekHZe3chcWcXbQ3hveUqwghZ7WppxGDZGO-f1g1bfR7vGBnettxtqHP74dUVdhgKZBEJWUK5Frn_u5JbmMhak0nuTcZMjyOvSVzDEK0m7iWayZ0kx7KtToelLC3ug8sOOOw6RlYYFrrBPRJxYIPOZytXpUhmHcBN0LgfYGv8XQP9iU6nJ0OH2JevjD1V-8UJFde_49_6YFmHNbbLJfr4lFGDPFEsy-SLz4EXo9-9auKXdIz1zntHc_RJE5MhnZL-sSYIa4zLN9Yrf15FSjvYp8b8KtBgVRRWZ792_c4a3iE_x8k69aholiUJgVIFYrZUrqVOs45XGoVCxDPPvOQ9vD94JV-NrMcpK63OtYAuQ6qXQwIRLEROIwsQrbT62Hdc6RV9ptOcD8p9l6A5XECahR8oyTtX8_3oQZC6Dk5Ljb-QwfcNzaALUOE-XdvfkCU-mv8mp0t1HBn8DFWwPpEWKDQFw
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=SAL%E2%80%90Net%3A+Self%E2%80%90Supervised+Attribute+Learning+for+Object+Recognition+and+Segmentation&rft.jtitle=Wireless+communications+and+mobile+computing&rft.au=Yang%2C+Shu&rft.au=JingWang&rft.au=Arif%2C+Sheeraz&rft.au=Jia%2C+Minli&rft.date=2021&rft.issn=1530-8669&rft.eissn=1530-8677&rft.volume=2021&rft.issue=1&rft_id=info:doi/10.1155%2F2021%2F2891303&rft.externalDBID=n%2Fa&rft.externalDocID=10_1155_2021_2891303
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-8669&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-8669&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-8669&client=summon