Zero-Shot Hashing via Asymmetric Ratio Similarity Matrix

Zero-shot hashing targets to learn the hash codes of images in unseen classes based on the limited training data provided by seen classes. In zero-shot hashing, transferring the supervised knowledge, such as attributes and semantic relations, from seen classes to unseen ones is a widely employed met...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on knowledge and data engineering Ročník 35; číslo 5; s. 5426 - 5437
Hlavní autori:	Shi, Yang, Nie, Xiushan, Liu, Xingbo, Yang, Lu, Yin, Yilong
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 01.05.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	asymmetric ratio similarity matrix Asymmetry Binary codes Hamming distance Hash functions Hashing Mathematical analysis Optimization Semantics Similarity Symmetric matrices Visualization zero-shot
ISSN:	1041-4347, 1558-2191
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Zero-shot hashing targets to learn the hash codes of images in unseen classes based on the limited training data provided by seen classes. In zero-shot hashing, transferring the supervised knowledge, such as attributes and semantic relations, from seen classes to unseen ones is a widely employed method, where the performance is always subject to the ability to capture these supervised knowledge (which is always difficult to obtain). Therefore, in this study, we propose a new methodology for zero-shot hashing via an asymmetric ratio similarity matrix (ASZH), which only needs to calculate the semantic similarity among seen classes for hash learning. Specifically, we use an asymmetric ratio matrix in the similarity calculation to further explore the influence of similarity, where the values of positive weights for similar samples are not equivalent to those of negative ones for dissimilar samples. Additionally, a theoretical analysis regarding the utilization of an asymmetric ratio matrix is provided in this study. The experiments on three large benchmark datasets indicate that the proposed method achieves excellent performance than several state-of-the-art hashing methods.
AbstractList	Zero-shot hashing targets to learn the hash codes of images in unseen classes based on the limited training data provided by seen classes. In zero-shot hashing, transferring the supervised knowledge, such as attributes and semantic relations, from seen classes to unseen ones is a widely employed method, where the performance is always subject to the ability to capture these supervised knowledge (which is always difficult to obtain). Therefore, in this study, we propose a new methodology for zero-shot hashing via an asymmetric ratio similarity matrix (ASZH), which only needs to calculate the semantic similarity among seen classes for hash learning. Specifically, we use an asymmetric ratio matrix in the similarity calculation to further explore the influence of similarity, where the values of positive weights for similar samples are not equivalent to those of negative ones for dissimilar samples. Additionally, a theoretical analysis regarding the utilization of an asymmetric ratio matrix is provided in this study. The experiments on three large benchmark datasets indicate that the proposed method achieves excellent performance than several state-of-the-art hashing methods.
Author	Yin, Yilong Liu, Xingbo Shi, Yang Yang, Lu Nie, Xiushan
Author_xml	– sequence: 1 givenname: Yang orcidid: 0000-0003-2515-1588 surname: Shi fullname: Shi, Yang email: shiyang@mail.sdu.edu.cn organization: School of Software, Shandong University, Jinan, China – sequence: 2 givenname: Xiushan orcidid: 0000-0001-9644-9723 surname: Nie fullname: Nie, Xiushan email: niexsh@hotmail.com organization: School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China – sequence: 3 givenname: Xingbo orcidid: 0000-0002-7236-8715 surname: Liu fullname: Liu, Xingbo email: sclxb@mail.sdu.edu.cn organization: School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China – sequence: 4 givenname: Lu orcidid: 0000-0002-5186-6504 surname: Yang fullname: Yang, Lu email: yangluhi@163.com organization: School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China – sequence: 5 givenname: Yilong orcidid: 0000-0002-8465-1294 surname: Yin fullname: Yin, Yilong email: ylyin@sdu.edu.cn organization: School of Software, Shandong University, Jinan, China
BookMark	eNp9kE9PwjAYhxujiYB-AONliefh23Zd2yNBFCPGRPDipem6Vkpgw64Y-fZugXjw4Klvmt_z_nn66LSqK4vQFYYhxiBvF093kyEBQoYUM-ASTlAPMyZSgiU-bWvIcJrRjJ-jftOsAEBwgXtIvNtQp_NlHZOpbpa--ki-vE5GzX6zsTF4k7zq6Otk7jd-rYOP--RZt__fF-jM6XVjL4_vAL3dTxbjaTp7eXgcj2apIZLGlDlZGkIlMKFdBrJkueGUYOdKxrksnMSFKKUrhNEgictpgY0Wuc5ZCe05dIBuDn23of7c2SaqVb0LVTtSES6ZAJqBaFP8kDKhbppgnTI-dotXMWi_VhhUp0l1mlSnSR01tST-Q26D3-iw_5e5PjDeWvublxwTKjL6A48fc7c
CODEN	ITKEEH
CitedBy_id	crossref_primary_10_1109_TKDE_2023_3312109 crossref_primary_10_1016_j_engappai_2024_108197 crossref_primary_10_1109_TCSVT_2022_3195874 crossref_primary_10_1177_15501477211066305 crossref_primary_10_1016_j_neucom_2022_09_037 crossref_primary_10_1109_JBHI_2022_3161341 crossref_primary_10_1109_TBDATA_2022_3161905 crossref_primary_10_1016_j_knosys_2024_111820 crossref_primary_10_1016_j_ins_2023_119376 crossref_primary_10_1145_3734871 crossref_primary_10_1007_s00530_022_00988_6 crossref_primary_10_1145_3624016
Cites_doi	10.1109/TKDE.2019.2913383 10.1109/TPAMI.2012.193 10.1145/3209978.3210035 10.1109/CVPR.2014.253 10.1109/TKDE.2015.2507127 10.1023/A:1011139631724 10.1109/CVPR.2009.5206772 10.1145/2964284.2964319 10.1109/TCSVT.2020.3040863 10.1109/CVPR.2016.227 10.1109/TKDE.2017.2752156 10.1109/CVPR.2010.5539994 10.1609/aaai.v32i1.11814 10.1109/TPAMI.2017.2699960 10.1145/2766462.2767725 10.1007/s11263-020-01327-w 10.1109/TKDE.2012.76 10.1109/CVPR.2010.5540129 10.1109/TCSVT.2013.2276713 10.1145/1327452.1327494 10.1109/TPAMI.2018.2857768 10.24963/ijcai.2019/420 10.1145/997817.997857 10.1109/TKDE.2015.2485224 10.1109/TIP.2020.2970577 10.1109/CVPR.2015.7298598 10.1109/TPAMI.2017.2769047 10.1109/TIP.2020.2963952 10.1016/j.patrec.2018.04.011 10.1109/CVPR.2012.6247912 10.1109/TIP.2020.3036735 10.1109/ICME.2017.8019425 10.1109/JPROC.2015.2487976 10.1109/TIP.2018.2864894 10.1109/CVPR.2018.00134 10.14778/2732939.2732947 10.1109/TPAMI.2013.140 10.1109/TPAMI.2018.2849378 10.1109/TKDE.2016.2562624 10.1109/ICCV.2017.598 10.24963/ijcai.2017/245 10.5244/C.28.6
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TKDE.2022.3150790
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) 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 Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1558-2191
EndPage	5437
ExternalDocumentID	10_1109_TKDE_2022_3150790 9712384
Genre	orig-research
GrantInformation_xml	– fundername: Taishan Scholar Project of Shandong Province grantid: tsqn202103088 funderid: 10.13039/501100010040 – fundername: National Natural Science Foundation of China grantid: 62176141; 62176139; 61876098 funderid: 10.13039/501100001809 – fundername: Shandong Provincial Natural Science Foundation for Distinguished Young Scholars grantid: ZR2021JQ26 – fundername: Natural Science Foundation of Shandong Province grantid: ZR2021ZD15 funderid: 10.13039/501100007129 – fundername: Shandong Jianzhu University funderid: 10.13039/501100007927
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB 1OL 5VS 9M8 AAYXX ABFSI AETIX AGSQL AI. AIBXA ALLEH CITATION E.L H~9 ICLAB IFJZH RNI RZB TAF VH1 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c293t-5f9dc239058af409d56c7321ffd5779bf91b8d9fb8ca092f63b1ca86a65d00223
IEDL.DBID	RIE
ISICitedReferencesCount	20
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000964880800074&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1041-4347
IngestDate	Mon Jun 30 03:42:55 EDT 2025 Sat Nov 29 02:36:05 EST 2025 Tue Nov 18 22:17:19 EST 2025 Wed Aug 27 02:14:19 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	5
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c293t-5f9dc239058af409d56c7321ffd5779bf91b8d9fb8ca092f63b1ca86a65d00223
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-9644-9723 0000-0002-5186-6504 0000-0003-2515-1588 0000-0002-7236-8715 0000-0002-8465-1294
PQID	2795803408
PQPubID	85438
PageCount	12
ParticipantIDs	crossref_citationtrail_10_1109_TKDE_2022_3150790 proquest_journals_2795803408 crossref_primary_10_1109_TKDE_2022_3150790 ieee_primary_9712384
PublicationCentury	2000
PublicationDate	2023-05-01
PublicationDateYYYYMMDD	2023-05-01
PublicationDate_xml	– month: 05 year: 2023 text: 2023-05-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on knowledge and data engineering
PublicationTitleAbbrev	TKDE
PublicationYear	2023
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 ref12 Oliva (ref47) 2001; 42 ref14 Wah (ref45) 2011 ref11 ref10 ref17 ref16 ref19 ref50 ref48 ref42 ref41 ref44 Liu (ref43) ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref33 ref32 ref2 ref1 ref39 ref38 Li (ref30) Liu (ref18) Wang (ref20) ref24 Krizhevsky (ref46) 2009 ref23 ref26 ref25 ref22 ref21 ref28 ref27 ref29 Weiss (ref15) Li (ref31)
References_xml	– ident: ref26 doi: 10.1109/TKDE.2019.2913383 – start-page: 3419 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref43 article-title: Discrete graph hashing – ident: ref2 doi: 10.1109/TPAMI.2012.193 – year: 2009 ident: ref46 article-title: Learning multiple layers of features from tiny images – ident: ref23 doi: 10.1145/3209978.3210035 – ident: ref42 doi: 10.1109/CVPR.2014.253 – ident: ref8 doi: 10.1109/TKDE.2015.2507127 – volume: 42 start-page: 145 issue: 3 year: 2001 ident: ref47 article-title: Modeling the shape of the scene: A holistic representation of the spatial envelope publication-title: Int. J. Comput. Vis. doi: 10.1023/A:1011139631724 – ident: ref36 doi: 10.1109/CVPR.2009.5206772 – ident: ref37 doi: 10.1145/2964284.2964319 – ident: ref27 doi: 10.1109/TCSVT.2020.3040863 – ident: ref29 doi: 10.1109/CVPR.2016.227 – ident: ref12 doi: 10.1109/TKDE.2017.2752156 – ident: ref19 doi: 10.1109/CVPR.2010.5539994 – ident: ref32 doi: 10.1609/aaai.v32i1.11814 – ident: ref10 doi: 10.1109/TPAMI.2017.2699960 – start-page: 1 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref18 article-title: Hashing with graphs – start-page: 1711 volume-title: Proc. Int. Joint Conf. Artif. Intell. ident: ref30 article-title: Feature learning based deep supervised hashing with pairwise labels – year: 2011 ident: ref45 article-title: The Caltech-UCSD Birds-200–2011 dataset – ident: ref22 doi: 10.1145/2766462.2767725 – ident: ref34 doi: 10.1007/s11263-020-01327-w – start-page: 1753 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref15 article-title: Spectral hashing – ident: ref9 doi: 10.1109/TKDE.2012.76 – ident: ref16 doi: 10.1109/CVPR.2010.5540129 – ident: ref21 doi: 10.1109/TCSVT.2013.2276713 – ident: ref1 doi: 10.1145/1327452.1327494 – start-page: 1127 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref20 article-title: Sequential projection learning for hashing with compact codes – ident: ref44 doi: 10.1109/TPAMI.2018.2857768 – ident: ref28 doi: 10.24963/ijcai.2019/420 – ident: ref13 doi: 10.1145/997817.997857 – ident: ref4 doi: 10.1109/TKDE.2015.2485224 – ident: ref25 doi: 10.1109/TIP.2020.2970577 – ident: ref3 doi: 10.1109/CVPR.2015.7298598 – start-page: 2479 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref31 article-title: Deep supervised discrete hashing – ident: ref5 doi: 10.1109/TPAMI.2017.2769047 – ident: ref24 doi: 10.1109/TIP.2020.2963952 – ident: ref40 doi: 10.1016/j.patrec.2018.04.011 – ident: ref41 doi: 10.1109/CVPR.2012.6247912 – ident: ref49 doi: 10.1109/TIP.2020.3036735 – ident: ref38 doi: 10.1109/ICME.2017.8019425 – ident: ref14 doi: 10.1109/JPROC.2015.2487976 – ident: ref33 doi: 10.1109/TIP.2018.2864894 – ident: ref48 doi: 10.1109/CVPR.2018.00134 – ident: ref11 doi: 10.14778/2732939.2732947 – ident: ref35 doi: 10.1109/TPAMI.2013.140 – ident: ref6 doi: 10.1109/TPAMI.2018.2849378 – ident: ref17 doi: 10.1109/TKDE.2016.2562624 – ident: ref7 doi: 10.1109/ICCV.2017.598 – ident: ref39 doi: 10.24963/ijcai.2017/245 – ident: ref50 doi: 10.5244/C.28.6
SSID	ssj0008781
Score	2.509219
Snippet	Zero-shot hashing targets to learn the hash codes of images in unseen classes based on the limited training data provided by seen classes. In zero-shot...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	5426
SubjectTerms	asymmetric ratio similarity matrix Asymmetry Binary codes Hamming distance Hash functions Hashing Mathematical analysis Optimization Semantics Similarity Symmetric matrices Visualization zero-shot
Title	Zero-Shot Hashing via Asymmetric Ratio Similarity Matrix
URI	https://ieeexplore.ieee.org/document/9712384 https://www.proquest.com/docview/2795803408
Volume	35
WOSCitedRecordID	wos000964880800074&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: 1558-2191 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008781 issn: 1041-4347 databaseCode: RIE dateStart: 19890101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEB1q8aAHq1WxWiUHT-JqNtndJMeilYJYxFYQL0uSTbBgW-kX-u9NdreloAjeckhgeZPMzNtJ5gGcM2oNsUYGCZW-zKhYIIUNgyTRliqZUUsLsQnW7fKXF_FYgcvVWxhjTH75zFz5YV7Lz8Z67n-VXQvm_CyPNmCDMVa81Vp5Xc5yQVLHLhwnohErK5ghFtf9-9u2Y4KEOILq0h_vftdiUC6q8sMT5-Hlrva_D9uFnTKNRK3C7ntQMaM61JYSDag8sXXYXus3uA_81UzGQe9tPEOdQkQJLQYStaZfw6FX1tLoyRsK9QbDgWO8LkFHD76F_-cBPN-1-zedoJROCLSL37MgtiLThAocc2kdhcviRDNKQmuzmDGhrAgVz4RVXEssiE2oCrXkiUzizId1egjV0XhkjgAx5VyQYYooqiMZUhVZrJilkuJMc00agJdgprrsK-7lLd7TnF9gkXr8U49_WuLfgIvVko-iqcZfk_c94KuJJdYNaC4tlpbHbpoSJmKOaYT58e-rTmDL68UXNxabUJ1N5uYUNvViNphOzvId9Q0iice6
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB7qA9SDb7E-c_AkrmaT3U1yFLVU1CK2gnhZkmyCBdtKX-i_N9ndloIieMshgeWbZGa-nWQ-gBNGrSHWyCCh0pcZFQuksGGQJNpSJTNqaSE2wRoN_vIiHitwNn0LY4zJL5-Zcz_Ma_lZT4_8r7ILwZyf5dEcLMRRRMLitdbU73KWS5I6fuFYEY1YWcMMsbho3V3fOC5IiKOoLgHyDngmCuWyKj98cR5gamv_-7R1WC0TSXRZWH4DKqa7CWsTkQZUntlNWJnpOLgF_NX0e0HzrTdE9UJGCY3bEl0Ovjodr62l0ZM3FWq2O23HeV2Kjh58E__PbXiu3bSu6kEpnhBoF8GHQWxFpgkVOObSOhKXxYlmlITWZjFjQlkRKp4Jq7iWWBCbUBVqyROZxJkP7HQH5ru9rtkFxJRzQoYpoqiOZEhVZLFilkqKM801qQKegJnqsrO4F7h4T3OGgUXq8U89_mmJfxVOp0s-irYaf03e8oBPJ5ZYV-FgYrG0PHiDlDARc0wjzPd-X3UMS_XWw316f9u424dlrx5f3F88gPlhf2QOYVGPh-1B_yjfXd-zBcsB
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=Zero-shot+Hashing+via+Asymmetric+Ratio+Similarity+Matrix&rft.jtitle=IEEE+transactions+on+knowledge+and+data+engineering&rft.au=Shi%2C+Yang&rft.au=Nie%2C+Xiushan&rft.au=Liu%2C+Xingbo&rft.au=Yang%2C+Lu&rft.date=2023-05-01&rft.issn=1041-4347&rft.eissn=1558-2191&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FTKDE.2022.3150790&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TKDE_2022_3150790
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1041-4347&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1041-4347&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1041-4347&client=summon