Transductive Zero-Shot Hashing for Multilabel Image Retrieval

Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes. While some newly int...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transaction on neural networks and learning systems Ročník 33; číslo 4; s. 1673 - 1687
Hlavní autori:	Zou, Qin, Cao, Ling, Zhang, Zheng, Chen, Long, Wang, Song
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States IEEE 01.04.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Annotations Binary codes Data models Deep hashing Hash functions Image coding Image management Image retrieval Labels multilabel image Quantization (signal) Semantics Training transductive learning Visualization zero-shot learning
ISSN:	2162-237X, 2162-2388, 2162-2388
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes. While some newly introduced images may contain undefined semantic labels, which we call unseen images, zero-shot hashing (ZSH) techniques have been studied for retrieval. However, existing ZSH methods mainly focus on the retrieval of single-label images and cannot handle multilabel ones. In this article, for the first time, a novel transductive ZSH method is proposed for multilabel unseen image retrieval. In order to predict the labels of the unseen/target data, a visual-semantic bridge is built via instance-concept coherence ranking on the seen/source data. Then, pairwise similarity loss and focal quantization loss are constructed for training a hashing model using both the seen/source and unseen/target data. Extensive evaluations on three popular multilabel data sets demonstrate that the proposed hashing method achieves significantly better results than the comparison methods.
AbstractList	Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes. While some newly introduced images may contain undefined semantic labels, which we call unseen images, zero-shot hashing (ZSH) techniques have been studied for retrieval. However, existing ZSH methods mainly focus on the retrieval of single-label images and cannot handle multilabel ones. In this article, for the first time, a novel transductive ZSH method is proposed for multilabel unseen image retrieval. In order to predict the labels of the unseen/target data, a visual-semantic bridge is built via instance-concept coherence ranking on the seen/source data. Then, pairwise similarity loss and focal quantization loss are constructed for training a hashing model using both the seen/source and unseen/target data. Extensive evaluations on three popular multilabel data sets demonstrate that the proposed hashing method achieves significantly better results than the comparison methods.Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes. While some newly introduced images may contain undefined semantic labels, which we call unseen images, zero-shot hashing (ZSH) techniques have been studied for retrieval. However, existing ZSH methods mainly focus on the retrieval of single-label images and cannot handle multilabel ones. In this article, for the first time, a novel transductive ZSH method is proposed for multilabel unseen image retrieval. In order to predict the labels of the unseen/target data, a visual-semantic bridge is built via instance-concept coherence ranking on the seen/source data. Then, pairwise similarity loss and focal quantization loss are constructed for training a hashing model using both the seen/source and unseen/target data. Extensive evaluations on three popular multilabel data sets demonstrate that the proposed hashing method achieves significantly better results than the comparison methods. Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes. While some newly introduced images may contain undefined semantic labels, which we call unseen images, zero-shot hashing (ZSH) techniques have been studied for retrieval. However, existing ZSH methods mainly focus on the retrieval of single-label images and cannot handle multilabel ones. In this article, for the first time, a novel transductive ZSH method is proposed for multilabel unseen image retrieval. In order to predict the labels of the unseen/target data, a visual-semantic bridge is built via instance-concept coherence ranking on the seen/source data. Then, pairwise similarity loss and focal quantization loss are constructed for training a hashing model using both the seen/source and unseen/target data. Extensive evaluations on three popular multilabel data sets demonstrate that the proposed hashing method achieves significantly better results than the comparison methods.
Author	Cao, Ling Chen, Long Zou, Qin Wang, Song Zhang, Zheng
Author_xml	– sequence: 1 givenname: Qin orcidid: 0000-0001-7955-0782 surname: Zou fullname: Zou, Qin email: qzou@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan, China – sequence: 2 givenname: Ling orcidid: 0000-0002-5566-1186 surname: Cao fullname: Cao, Ling email: lingcao@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan, China – sequence: 3 givenname: Zheng surname: Zhang fullname: Zhang, Zheng email: zhengzhang@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan, China – sequence: 4 givenname: Long orcidid: 0000-0003-4925-0572 surname: Chen fullname: Chen, Long email: chenl46@mail.sysu.edu.cn organization: School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China – sequence: 5 givenname: Song orcidid: 0000-0003-4152-5295 surname: Wang fullname: Wang, Song email: songwang@cec.sc.edu organization: Department of Computer Science and Engineering, University of South Carolina, Columbia, SC, USA
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/33361006$$D View this record in MEDLINE/PubMed
BookMark	eNp9kU1LAzEQhoMoVmv_gIIsePGyNV-b3Rw8iPhRqAq2gngJaXZWI9uNJtmC_97Vth56MJfJwPMMw7z7aLtxDSB0SPCQECzPpvf348mQYoqHDHNGZbGF9igRNKWsKLb__vlzDw1CeMfdEzgTXO6iHmNMkK7fQ-dTr5tQtibaBSQv4F06eXMxudXhzTavSeV8ctfW0dZ6BnUymutXSB4hegsLXR-gnUrXAQar2kdP11fTy9t0_HAzurwYp4ZlJKYGCOWZEdhkIq_IjGssZtCtIykvqWSlLrXMNZOcZ5oYXhasIExLafKy4lCyPjpdzv3w7rOFENXcBgN1rRtwbVCU54xTnPGiQ0820HfX-qbbTlHBc06FwKyjjldUO5tDqT68nWv_pdaH6YBiCRjvQvBQKWOjjtY10WtbK4LVTwzqNwb1E4NaxdCpdENdT_9XOlpKFgD-BMmwxISybyYokJw
CODEN	ITNNAL
CitedBy_id	crossref_primary_10_1109_TIP_2023_3251028 crossref_primary_10_1016_j_knosys_2022_109306 crossref_primary_10_1109_ACCESS_2025_3597396 crossref_primary_10_1016_j_neucom_2022_09_037 crossref_primary_10_1109_TNNLS_2024_3363163 crossref_primary_10_1145_3734871 crossref_primary_10_1007_s11432_022_3748_5 crossref_primary_10_1007_s13369_025_10135_8
Cites_doi	10.1109/CVPR.2015.7298947 10.1109/TIP.2016.2592800 10.1109/TIP.2019.2913079 10.1007/s11263-016-0893-6 10.1109/TIP.2018.2878966 10.1109/TPAMI.2011.219 10.1109/CVPR.2008.4587633 10.1109/TKDE.2009.191 10.1145/2964284.2964319 10.1109/CVPR.2015.7298965 10.1145/3293318 10.1016/j.patrec.2018.04.011 10.1145/997817.997857 10.1109/CVPR.2017.572 10.1109/CVPR.2018.00379 10.1109/CVPR.2019.01022 10.1109/ICCV.2017.598 10.1145/1646396.1646452 10.1109/CVPR.2019.01200 10.1007/978-3-642-33715-4_25 10.1109/TPAMI.2015.2408363 10.1007/s11263-009-0275-4 10.1109/CVPR.2018.00111 10.1109/TMM.2018.2838320 10.1109/TIP.2017.2696747 10.1109/TPAMI.2020.3008694 10.1109/ICCV.2019.00994 10.1007/s11263-016-0983-5 10.1109/TNNLS.2015.2495345 10.1145/582415.582418 10.1109/CVPR.2018.00581 10.1109/TMM.2020.2967645 10.1109/CVPR.2015.7298911 10.1016/j.neucom.2017.10.061 10.1109/CVPR.2019.00722 10.1109/TNNLS.2016.2636870 10.3115/v1/D14-1162 10.1109/ICCV.2019.00312 10.1109/TMM.2017.2697824 10.1109/TIP.2017.2781422 10.1109/CVPR.2019.00928 10.1109/CVPR.2014.313 10.1109/TPAMI.2018.2861000 10.1109/ACCESS.2020.2988923 10.1109/TMM.2019.2929957 10.1109/CVPR.2013.205 10.1109/TNNLS.2018.2890550 10.1109/CVPR.2009.5206594 10.1109/TPAMI.2015.2408354 10.1109/CVPR.2016.227 10.1109/CVPR.2011.5995590 10.1109/TPAMI.2018.2789887 10.1109/TMM.2016.2625260 10.1109/TCSVT.2017.2723302 10.1109/TCSVT.2019.2897980 10.1109/CVPR.2014.272 10.1109/TPAMI.2018.2858826 10.24963/ijcai.2017/245 10.1109/TMM.2019.2903448 10.1109/CVPR.2015.7298598 10.1145/3206025.3206026 10.1109/TIP.2015.2467315 10.3115/v1/P14-1132 10.1109/CVPR.2018.00134 10.24963/ijcai.2017/246 10.1109/TNNLS.2018.2797248 10.1109/TITS.2019.2949005
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION NPM 7QF 7QO 7QP 7QQ 7QR 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8
DOI	10.1109/TNNLS.2020.3043298
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Calcium & Calcified Tissue Abstracts Ceramic Abstracts Chemoreception Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Neurosciences Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Materials Research Database Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Materials Business File Aerospace Database Engineered Materials Abstracts Biotechnology Research Abstracts Chemoreception Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Civil Engineering Abstracts Aluminium Industry Abstracts Electronics & Communications Abstracts Ceramic Abstracts Neurosciences Abstracts METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Solid State and Superconductivity Abstracts Engineering Research Database Calcium & Calcified Tissue Abstracts Corrosion Abstracts MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic PubMed Materials Research Database
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	2162-2388
EndPage	1687
ExternalDocumentID	33361006 10_1109_TNNLS_2020_3043298 9309012
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: National Key Research Development Program of China grantid: 2019QY(Y)0206 funderid: 10.13039/501100012166 – fundername: Key R&D Program of Hubei Province grantid: 2020BAB018 – fundername: National Natural Science Foundation of China grantid: 61872277; 61672376; U1803264 funderid: 10.13039/501100001809
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF M43 MS~ O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION NPM 7QF 7QO 7QP 7QQ 7QR 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8
ID	FETCH-LOGICAL-c351t-ce1245c60c567f1b4a06be060924d293dada97a39445a1c4d83813a99c7df4ed3
IEDL.DBID	RIE
ISICitedReferencesCount	9
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000778930100028&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2162-237X 2162-2388
IngestDate	Sat Sep 27 22:17:10 EDT 2025 Sun Nov 30 04:14:16 EST 2025 Thu Jan 02 22:58:29 EST 2025 Sat Nov 29 01:40:10 EST 2025 Tue Nov 18 21:01:01 EST 2025 Wed Aug 27 02:40:50 EDT 2025
IsPeerReviewed	false
IsScholarly	true
Issue	4
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-c351t-ce1245c60c567f1b4a06be060924d293dada97a39445a1c4d83813a99c7df4ed3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-7955-0782 0000-0003-4152-5295 0000-0002-5566-1186 0000-0003-4925-0572
PMID	33361006
PQID	2647426603
PQPubID	85436
PageCount	15
ParticipantIDs	ieee_primary_9309012 pubmed_primary_33361006 crossref_citationtrail_10_1109_TNNLS_2020_3043298 crossref_primary_10_1109_TNNLS_2020_3043298 proquest_miscellaneous_2473420548 proquest_journals_2647426603
PublicationCentury	2000
PublicationDate	2022-04-01
PublicationDateYYYYMMDD	2022-04-01
PublicationDate_xml	– month: 04 year: 2022 text: 2022-04-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: Piscataway
PublicationTitle	IEEE transaction on neural networks and learning systems
PublicationTitleAbbrev	TNNLS
PublicationTitleAlternate	IEEE Trans Neural Netw Learn Syst
PublicationYear	2022
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	ref57 wang (ref78) 2017 ref56 ref59 ref15 ref58 ref53 ref52 ref55 ref10 ref17 ref19 ref18 jialin pan (ref74) 2010; 22 ren (ref54) 2015 ref51 ref50 guo (ref46) 2017 yan (ref27) 2020 ref45 ref48 ref47 ref85 ref44 ref43 wang (ref70) 2015 krizhevsky (ref13) 2012 ref49 liu (ref8) 2011 ref7 ref9 ref4 ref3 ref6 ref5 jiang (ref82) 2018 ref81 ref40 ref84 ref83 ref80 ref79 ref35 ref34 ref37 ref36 ref75 ref31 ref30 ref77 ref33 ref76 ref32 ref1 frome (ref42) 2013 ref39 zhao (ref23) 2015 ref38 lin (ref14) 2014 xia (ref22) 2014 sun (ref16) 2014 ref71 ref73 liu (ref2) 2012 ref72 ref68 ref67 weiss (ref11) 2009 ref26 ref69 ref25 ref64 ref20 ref63 ref66 mikolov (ref41) 2013 ref65 ref21 ref28 zhu (ref24) 2016 liong (ref12) 2015 ref29 ref60 ref62 ref61
References_xml	– ident: ref5 doi: 10.1109/CVPR.2015.7298947 – start-page: 1753 year: 2009 ident: ref11 article-title: Spectral hashing publication-title: Proc NIPS – ident: ref71 doi: 10.1109/TIP.2016.2592800 – ident: ref15 doi: 10.1109/TIP.2019.2913079 – ident: ref44 doi: 10.1007/s11263-016-0893-6 – ident: ref21 doi: 10.1109/TIP.2018.2878966 – ident: ref1 doi: 10.1109/TPAMI.2011.219 – ident: ref57 doi: 10.1109/CVPR.2008.4587633 – volume: 22 start-page: 1345 year: 2010 ident: ref74 article-title: A survey on transfer learning publication-title: IEEE Trans Knowl Data Eng doi: 10.1109/TKDE.2009.191 – ident: ref30 doi: 10.1145/2964284.2964319 – start-page: 2415 year: 2016 ident: ref24 article-title: Deep hashing network for efficient similarity retrieval publication-title: Proc AAAI – ident: ref20 doi: 10.1109/CVPR.2015.7298965 – ident: ref38 doi: 10.1145/3293318 – ident: ref34 doi: 10.1016/j.patrec.2018.04.011 – ident: ref9 doi: 10.1145/997817.997857 – ident: ref76 doi: 10.1109/CVPR.2017.572 – ident: ref77 doi: 10.1109/CVPR.2018.00379 – start-page: 1556 year: 2015 ident: ref23 article-title: Deep semantic ranking based hashing for multi-label image retrieval publication-title: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) – ident: ref53 doi: 10.1109/CVPR.2019.01022 – year: 2020 ident: ref27 article-title: Deep multi-view enhancement hashing for image retrieval publication-title: IEEE Trans Pattern Anal Mach Intell – ident: ref26 doi: 10.1109/ICCV.2017.598 – ident: ref80 doi: 10.1145/1646396.1646452 – ident: ref51 doi: 10.1109/CVPR.2019.01200 – ident: ref58 doi: 10.1007/978-3-642-33715-4_25 – ident: ref10 doi: 10.1109/TPAMI.2015.2408363 – ident: ref81 doi: 10.1007/s11263-009-0275-4 – ident: ref48 doi: 10.1109/CVPR.2018.00111 – ident: ref36 doi: 10.1109/TMM.2018.2838320 – ident: ref45 doi: 10.1109/TIP.2017.2696747 – ident: ref61 doi: 10.1109/TPAMI.2020.3008694 – ident: ref50 doi: 10.1109/ICCV.2019.00994 – ident: ref39 doi: 10.1007/s11263-016-0983-5 – ident: ref62 doi: 10.1109/TNNLS.2015.2495345 – ident: ref85 doi: 10.1145/582415.582418 – ident: ref47 doi: 10.1109/CVPR.2018.00581 – ident: ref37 doi: 10.1109/TMM.2020.2967645 – ident: ref43 doi: 10.1109/CVPR.2015.7298911 – start-page: 2475 year: 2015 ident: ref12 article-title: Deep hashing for compact binary codes learning publication-title: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) – ident: ref32 doi: 10.1016/j.neucom.2017.10.061 – ident: ref52 doi: 10.1109/CVPR.2019.00722 – ident: ref64 doi: 10.1109/TNNLS.2016.2636870 – ident: ref29 doi: 10.3115/v1/D14-1162 – ident: ref69 doi: 10.1109/ICCV.2019.00312 – start-page: 2121 year: 2013 ident: ref42 article-title: Devise: A deep visual-semantic embedding model publication-title: Proc NIPS – ident: ref60 doi: 10.1109/TMM.2017.2697824 – ident: ref72 doi: 10.1109/TIP.2017.2781422 – start-page: 1097 year: 2012 ident: ref13 article-title: Imagenet classification with deep convolutional neural networks publication-title: Proc NIPS – ident: ref83 doi: 10.1109/CVPR.2019.00928 – ident: ref55 doi: 10.1109/CVPR.2014.313 – ident: ref67 doi: 10.1109/TPAMI.2018.2861000 – ident: ref68 doi: 10.1109/ACCESS.2020.2988923 – start-page: 1 year: 2014 ident: ref22 article-title: Supervised hashing for image retrieval via image representation learning publication-title: Proc AAAI – ident: ref7 doi: 10.1109/TMM.2019.2929957 – ident: ref3 doi: 10.1109/CVPR.2013.205 – ident: ref17 doi: 10.1109/TNNLS.2018.2890550 – ident: ref28 doi: 10.1109/CVPR.2009.5206594 – year: 2015 ident: ref54 article-title: Multi-instance visual-semantic embedding publication-title: arXiv 1512 06963 – start-page: 3890 year: 2015 ident: ref70 article-title: Semantic topic multimodal hashing for cross-media retrieval publication-title: Proc IJCAI – ident: ref75 doi: 10.1109/TPAMI.2015.2408354 – ident: ref25 doi: 10.1109/CVPR.2016.227 – ident: ref84 doi: 10.1109/CVPR.2011.5995590 – ident: ref73 doi: 10.1109/TPAMI.2018.2789887 – ident: ref59 doi: 10.1109/TMM.2016.2625260 – start-page: 740 year: 2014 ident: ref14 article-title: Microsoft COCO: Common objects in context publication-title: Proc ECCV – ident: ref66 doi: 10.1109/TCSVT.2017.2723302 – ident: ref18 doi: 10.1109/TCSVT.2019.2897980 – ident: ref56 doi: 10.1109/CVPR.2014.272 – ident: ref79 doi: 10.1109/TPAMI.2018.2858826 – start-page: 1 year: 2017 ident: ref46 article-title: Zero-shot recognition via direct classifier learning with transferred samples and pseudo labels publication-title: Proc AAAI – year: 2017 ident: ref78 article-title: Multi-label zero-shot human action recognition via joint latent ranking embedding publication-title: arXiv 1709 05107 – ident: ref31 doi: 10.24963/ijcai.2017/245 – ident: ref35 doi: 10.1109/TMM.2019.2903448 – start-page: 3342 year: 2018 ident: ref82 article-title: Asymmetric deep supervised hashing publication-title: Proc AAAI – ident: ref4 doi: 10.1109/CVPR.2015.7298598 – year: 2013 ident: ref41 article-title: Exploiting similarities among languages for machine translation publication-title: arXiv 1309 4168 – ident: ref33 doi: 10.1145/3206025.3206026 – start-page: 1988 year: 2014 ident: ref16 article-title: Deep learning face representation by joint identification-verification publication-title: Proc NIPS – ident: ref6 doi: 10.1109/TIP.2015.2467315 – ident: ref40 doi: 10.3115/v1/P14-1132 – ident: ref65 doi: 10.1109/CVPR.2018.00134 – start-page: 1 year: 2011 ident: ref8 article-title: Hashing with graphs publication-title: Proc ICML – ident: ref49 doi: 10.24963/ijcai.2017/246 – ident: ref63 doi: 10.1109/TNNLS.2018.2797248 – start-page: 2074 year: 2012 ident: ref2 article-title: Supervised hashing with kernels publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref19 doi: 10.1109/TITS.2019.2949005
SSID	ssj0000605649
Score	2.4283767
Snippet	Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1673
SubjectTerms	Annotations Binary codes Data models Deep hashing Hash functions Image coding Image management Image retrieval Labels multilabel image Quantization (signal) Semantics Training transductive learning Visualization zero-shot learning
Title	Transductive Zero-Shot Hashing for Multilabel Image Retrieval
URI	https://ieeexplore.ieee.org/document/9309012 https://www.ncbi.nlm.nih.gov/pubmed/33361006 https://www.proquest.com/docview/2647426603 https://www.proquest.com/docview/2473420548
Volume	33
WOSCitedRecordID	wos000778930100028&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 Electronic Library (IEL) customDbUrl: eissn: 2162-2388 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000605649 issn: 2162-237X databaseCode: RIE dateStart: 20120101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5W8eDF92N1XSJ402jbpE1zFHFZQRbRFRYvJU1SFHQr666_30n6wIMK3gpN0jIzyXyTZOYDOJEsDwxTBQ21LihPtaQqUpoWJpeGMR4JWXiyCTEapZOJvOvAWZsLY631l8_suXv0Z_mm1Au3VXYhWYDuCxfcJSGSKler3U8JEJcnHu1GYRLRiIlJkyMTyIvxaHT7gNFghEGqK0InHU8fYwzBg-M6-uaSPMfK73DTu53B-v9-eAPWanhJLit72ISOnW7BekPdQOqZvA2Vj3K1XnG1I092VtKH53JOhhW3EkEoS3xuLhqJfSU3b7jskHvPvoWmuQOPg-vx1ZDWTApUszicU23Rjcc6CXSciCLMuQqS3KLIMPoy6PCNMkoK5ZJkYxVqblJ05ExJqYUpuDVsF5an5dTuA7EqNHGscs1EylNuFDeo5SJXPMytFXEXwkaYma7LjDu2i9fMhxuBzLwuMqeLrNZFF07bPu9VkY0_W287SbctayF3odfoLKvn4UeGcE84DBKwLhy3r3EGuWMRNbXlAttwgTaJ0BVH3qt03Y7dmMjBz988hNXIpUP4mzw9WJ7PFvYIVvTn_OVj1kcznaR9b6ZfWrTg5g
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS-QwEB9EhbsXv0_Xzwj3dsZtm7RpHkWUFdciugeLLyVNUhR0K-uuf7-T9AMf9ODeCk3SMjPJ_CbJzA_gt2RFYJgqaah1SXmqJVWR0rQ0hTSM8UjI0pNNiCxLx2N5uwAnXS6MtdZfPrOn7tGf5ZtKz91WWV-yAN0XLrhLjjmrydbqdlQCROaJx7tRmEQ0YmLcZskEsj_KsuE9xoMRhqmuDJ10TH2MMYQPju3ok1PyLCvfA07veC5X_--X12ClAZjkrLaIdViwkw1YbckbSDOXN6H2Uq7aK6535MFOK3r_WM3IoGZXIghmic_ORTOxz-TqBRcecuf5t9A4t-Dv5cXofEAbLgWqWRzOqLboyGOdBDpORBkWXAVJYVFkGH8ZdPlGGSWFcmmysQo1Nym6cqak1MKU3Br2CxYn1cTuALEqNHGsCs1EylNuFDeo57JQPCysFXEPwlaYuW4KjTu-i-fcBxyBzL0ucqeLvNFFD_50fV7rMhv_bL3pJN21bITcg_1WZ3kzE99yBHzCoZCA9eC4e41zyB2MqImt5tiGC7RKBK848nat627s1kR2v_7mEfwYjG6G-fAqu96Dn5FLjvD3evZhcTad2wNY1u-zp7fpoTfWD-7740c
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=Transductive+Zero-Shot+Hashing+for+Multilabel+Image+Retrieval&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Zou%2C+Qin&rft.au=Cao%2C+Ling&rft.au=Zhang%2C+Zheng&rft.au=Long%2C+Chen&rft.date=2022-04-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=2162-237X&rft.eissn=2162-2388&rft.volume=33&rft.issue=4&rft.spage=1673&rft_id=info:doi/10.1109%2FTNNLS.2020.3043298&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon