HiCoS-Net: hierarchical cross-modal graph learning with dynamic attention for hard negative-aware image-text matching

Fine-grained image-text matching, which is pivotal to multimodal intelligence, has advanced semantic correspondence inference through inter-modal region-word aggregation. Despite the efficacy of this approach, it remains limited by its inability to accommodate the semantic associations of hard negat...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Journal of King Saud University. Computer and information sciences Ročník 37; číslo 9; s. 281 - 30
Hlavní autoři:	Feng, Dingcheng, Luo, Ning, Zhang, Shudong, Zhou, Lijuan, Wei, Bing
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Cham Springer International Publishing 01.11.2025 Springer Nature B.V Springer
Témata:	Adaptation Associations Attention Computer Imaging Computer Science Database Management Dynamic graph attention mechanism Effectiveness Embedding Embedding similarity graph Hard negative samples HiCoS-Net Hierarchical inter-modal semantic network Knowledge Learning Machine Learning Matching Neural networks Original Paper Pattern Recognition and Graphics Semantics Software Engineering/Programming and Operating Systems Systems and Data Security Theory of Computation Vision Hierarchical inter-modal semantic network Hard negative samples HiCoS-Net Dynamic graph attention mechanism Embedding similarity graph
ISSN:	1319-1578, 2213-1248, 1319-1578
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Fine-grained image-text matching, which is pivotal to multimodal intelligence, has advanced semantic correspondence inference through inter-modal region-word aggregation. Despite the efficacy of this approach, it remains limited by its inability to accommodate the semantic associations of hard negative samples. To illustrate this point, consider the failure to leverage shared knowledge across multiple samples on analogous topics. This failure results in an inadequate capacity to differentiate hard negative samples. In this study, it is posited that the establishment of sample relationships facilitates the learning of semantic associations between different samples. This, in turn, enables the effective identification of subtle differences between hard negative samples, thereby enhancing the overall embedding process. The proposal of HiCoS-Net is the subject of this paper. The proposed model is a novel hierarchical inter-modal semantic network that learns robust embeddings through local-to-sample semantic interaction propagation. Specifically, at the local level, a dynamic graph attention mechanism is designed to achieve region-lexicon fine-grained interactions; at the sample level, an embedding similarity graph is constructed by combining the relational mapping matrix with the semantic matching matrix to explicitly model the topological associations and semantic coupling strengths of inter-modal samples. A substantial programme of experimentation is undertaken to validate the advantages of the proposed HiCoS-Net method. This has been demonstrated to achieve state-of-the-art image-text matching results on the public benchmark datasets Flickr30K and MS-COCO.
AbstractList	Abstract Fine-grained image-text matching, which is pivotal to multimodal intelligence, has advanced semantic correspondence inference through inter-modal region-word aggregation. Despite the efficacy of this approach, it remains limited by its inability to accommodate the semantic associations of hard negative samples. To illustrate this point, consider the failure to leverage shared knowledge across multiple samples on analogous topics. This failure results in an inadequate capacity to differentiate hard negative samples. In this study, it is posited that the establishment of sample relationships facilitates the learning of semantic associations between different samples. This, in turn, enables the effective identification of subtle differences between hard negative samples, thereby enhancing the overall embedding process. The proposal of HiCoS-Net is the subject of this paper. The proposed model is a novel hierarchical inter-modal semantic network that learns robust embeddings through local-to-sample semantic interaction propagation. Specifically, at the local level, a dynamic graph attention mechanism is designed to achieve region-lexicon fine-grained interactions; at the sample level, an embedding similarity graph is constructed by combining the relational mapping matrix with the semantic matching matrix to explicitly model the topological associations and semantic coupling strengths of inter-modal samples. A substantial programme of experimentation is undertaken to validate the advantages of the proposed HiCoS-Net method. This has been demonstrated to achieve state-of-the-art image-text matching results on the public benchmark datasets Flickr30K and MS-COCO. Fine-grained image-text matching, which is pivotal to multimodal intelligence, has advanced semantic correspondence inference through inter-modal region-word aggregation. Despite the efficacy of this approach, it remains limited by its inability to accommodate the semantic associations of hard negative samples. To illustrate this point, consider the failure to leverage shared knowledge across multiple samples on analogous topics. This failure results in an inadequate capacity to differentiate hard negative samples. In this study, it is posited that the establishment of sample relationships facilitates the learning of semantic associations between different samples. This, in turn, enables the effective identification of subtle differences between hard negative samples, thereby enhancing the overall embedding process. The proposal of HiCoS-Net is the subject of this paper. The proposed model is a novel hierarchical inter-modal semantic network that learns robust embeddings through local-to-sample semantic interaction propagation. Specifically, at the local level, a dynamic graph attention mechanism is designed to achieve region-lexicon fine-grained interactions; at the sample level, an embedding similarity graph is constructed by combining the relational mapping matrix with the semantic matching matrix to explicitly model the topological associations and semantic coupling strengths of inter-modal samples. A substantial programme of experimentation is undertaken to validate the advantages of the proposed HiCoS-Net method. This has been demonstrated to achieve state-of-the-art image-text matching results on the public benchmark datasets Flickr30K and MS-COCO.
ArticleNumber	281
Author	Wei, Bing Luo, Ning Zhou, Lijuan Zhang, Shudong Feng, Dingcheng
Author_xml	– sequence: 1 givenname: Dingcheng surname: Feng fullname: Feng, Dingcheng organization: School of Cyberspace Security, Hainan University – sequence: 2 givenname: Ning surname: Luo fullname: Luo, Ning email: luoning@hainanu.edu.cn organization: School of Cyberspace Security, Hainan University – sequence: 3 givenname: Shudong surname: Zhang fullname: Zhang, Shudong organization: School of Cyberspace Security, Hainan University – sequence: 4 givenname: Lijuan surname: Zhou fullname: Zhou, Lijuan organization: School of Cyberspace Security, Hainan University – sequence: 5 givenname: Bing surname: Wei fullname: Wei, Bing organization: School of Cyberspace Security, Hainan University
BookMark	eNp9kU9v1DAQxS1UJJbSL8DJEmeD_8SJww2toK1UwQE4WxN7kni1ay-Ol26_PWaD4MZcZmS99_No3ktyFVNEQl4L_lZw3r1bmlqKcakZ50oodn5GNlLWQcjGXJGNUKJnQnfmBblZlh3nXHStblS7Iae7sE1f2Wcs7-kcMEN2c3Cwpy6nZWGH5Os8ZTjOdI-QY4gTfQxlpv4pwiE4CqVgLCFFOqZMZ8ieRpyghJ_I4BEy0nCACVnBc6EHKBUfp1fk-Qj7BW_-9Gvy_dPHb9s79vDl9n774YE5ZWRhpuFG-AG596JrZDdKLp3WBjn2btSjcq3rB6Wl4oPoQRsF_aANdK5TjVZOXZP7lesT7Owx11Xyk00Q7OUh5clCLsHt0VYUauBaCF2vOXaD4V4J50FybYaxq6w3K-uY048TLsXu0inHur5Vsm1Fr1TbVJVcVZf7ZRz__iq4_Z2WXdOyNS17Scueq0mtpqWK44T5H_o_rl_5H5oI
Cites_doi	10.1109/CVPR42600.2020.01267 10.1109/TPAMI.2022.3148470 10.1007/978-3-031-43990-2_70 10.1109/TMM.2020.2972125 10.1016/j.inffus.2024.102344 10.1109/TNNLS.2021.3084827 10.1016/j.ijpe.2019.06.012 10.1016/j.bspc.2024.105943 10.1109/CVPR42600.2020.01095 10.1109/CVPR46437.2021.00881 10.4249/scholarpedia.5947 10.1109/CVPR46437.2021.01553 10.1007/978-3-030-58607-2_16 10.1109/CVPR.2004.1315142 10.1145/3474085.3475634 10.1016/j.neucom.2018.03.030 10.1109/CVPR42600.2020.01093 10.18653/v1/N16-1174 10.1109/ICCV.2015.303 10.3390/app10144913 10.1109/SIBGRAPI62404.2024.10716271 10.1109/ICCV.2019.00586 10.1609/aaai.v38i16.29752 10.1109/TCYB.2022.3179020 10.1109/CVPR52688.2022.01602 10.1109/ICCV.2019.00356 10.1109/ICCV.2015.279 10.24963/ijcai.2022/292 10.1016/j.neucom.2021.03.091 10.1007/s11263-022-01653-1 10.1145/3132847.3132892 10.1145/3451390 10.1109/CVPR.2019.01064 10.1109/TCSVT.2023.3254530 10.1109/TPAMI.2016.2587640 10.1007/978-3-030-01240-3_17 10.1109/TIFS.2024.3388949 10.1109/CVPR52688.2022.01521 10.1145/3219819.3220036 10.1109/CVPR.2017.173 10.24963/ijcai.2022/348
ContentType	Journal Article
Copyright	The Author(s) 2025 The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by-nc-nd/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: The Author(s) 2025 – notice: The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	C6C AAYXX CITATION 8FE 8FG ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- P62 PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS DOA
DOI	10.1007/s44443-025-00313-x
DatabaseName	Springer Nature OA Free Journals CrossRef ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest SciTech Premium Collection Technology Collection Advanced Technologies & Aerospace Collection ProQuest Central Essentials - QC ProQuest Central ProQuest Technology Collection ProQuest One ProQuest Central ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database 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 DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Publicly Available Content Database Advanced Technologies & Aerospace Collection Computer Science Database ProQuest Central Student Technology Collection ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New)
DatabaseTitleList	Publicly Available Content Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	2213-1248 1319-1578
EndPage	30
ExternalDocumentID	oai_doaj_org_article_c6ce5a05115444f7b80d31cda2058bf7 10_1007_s44443_025_00313_x
GrantInformation_xml	– fundername: National Key R&D Project grantid: 2023YFF0905404
GroupedDBID	--K 0R~ 4.4 457 5VS AAEDT AAEDW AAIKJ AAJSJ AALRI AASML AAXUO AAYWO ABEEZ ABMAC ACGFS ACULB ADBBV ADEZE ADVLN AEXQZ AFFHD AFGXO AFJKZ AFKRA AFTJW AGHFR AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ APXCP ARAPS BCNDV BENPR BGLVJ C6C CCPQU EBS FDB GROUPED_DOAJ HCIFZ IXB K7- KQ8 O-L O9- OK1 PHGZM PHGZT PIMPY PQGLB ROL SES SOJ SSZ XH2 AAQXK AAYXX ABWVN AGQPQ ASPBG AVWKF AZFZN CITATION EJD FEDTE FGOYB HVGLF HZ~ IPNFZ M41 R2- RIG 8FE 8FG ABUWG AZQEC DWQXO GNUQQ JQ2 P62 PKEHL PQEST PQQKQ PQUKI PRINS
ID	FETCH-LOGICAL-c382t-84081dbe0dd17427f202c558e0e9cf5f3c6c9b35230b19a583a9b58a7c73453c3
IEDL.DBID	DOA
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001603362600002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1319-1578
IngestDate	Mon Nov 24 19:21:12 EST 2025 Fri Nov 21 05:41:09 EST 2025 Thu Nov 27 00:53:16 EST 2025 Thu Nov 20 01:11:31 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	9
Keywords	Hierarchical inter-modal semantic network Hard negative samples HiCoS-Net Dynamic graph attention mechanism Embedding similarity graph
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c382t-84081dbe0dd17427f202c558e0e9cf5f3c6c9b35230b19a583a9b58a7c73453c3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
OpenAccessLink	https://doaj.org/article/c6ce5a05115444f7b80d31cda2058bf7
PQID	3266193364
PQPubID	7424686
PageCount	30
ParticipantIDs	doaj_primary_oai_doaj_org_article_c6ce5a05115444f7b80d31cda2058bf7 proquest_journals_3266193364 crossref_primary_10_1007_s44443_025_00313_x springer_journals_10_1007_s44443_025_00313_x
PublicationCentury	2000
PublicationDate	2025-11-01
PublicationDateYYYYMMDD	2025-11-01
PublicationDate_xml	– month: 11 year: 2025 text: 2025-11-01 day: 01
PublicationDecade	2020
PublicationPlace	Cham
PublicationPlace_xml	– name: Cham – name: Amsterdam
PublicationTitle	Journal of King Saud University. Computer and information sciences
PublicationTitleAbbrev	J. King Saud Univ. Comput. Inf. Sci
PublicationYear	2025
Publisher	Springer International Publishing Springer Nature B.V Springer
Publisher_xml	– name: Springer International Publishing – name: Springer Nature B.V – name: Springer
References	313_CR7 313_CR8 J Li (313_CR17) 2021; 34 313_CR5 313_CR6 313_CR3 313_CR4 313_CR1 313_CR2 313_CR27 313_CR28 313_CR25 313_CR24 313_CR21 313_CR22 313_CR20 MU Saeed (313_CR34) 2024; 91 313_CR61 313_CR60 K Zhou (313_CR62) 2022; 130 K Li (313_CR19) 2022; 45 X Sun (313_CR38) 2018; 299 T Kramberger (313_CR16) 2020; 10 Z Niu (313_CR30) 2021; 452 313_CR39 313_CR36 313_CR37 313_CR35 313_CR32 313_CR33 313_CR31 X Liu (313_CR23) 2022; 54 313_CR49 313_CR47 C Zhao (313_CR59) 2020; 22 313_CR48 313_CR46 313_CR44 F Locatello (313_CR26) 2020; 33 313_CR41 313_CR42 313_CR40 Y Wang (313_CR45) 2023; 33 Z Li (313_CR18) 2021; 33 313_CR58 J In (313_CR14) 2019; 218 313_CR15 313_CR12 313_CR56 313_CR13 O Vinyals (313_CR43) 2016; 39 313_CR57 313_CR9 313_CR10 S Xu (313_CR51) 2024; 107 313_CR54 313_CR11 313_CR55 313_CR52 313_CR53 N Messina (313_CR29) 2021; 17 313_CR50
References_xml	– ident: 313_CR54 doi: 10.1109/CVPR42600.2020.01267 – volume: 45 start-page: 641 issue: 1 year: 2022 ident: 313_CR19 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2022.3148470 – ident: 313_CR22 doi: 10.1007/978-3-031-43990-2_70 – ident: 313_CR11 doi: 10.1109/TMM.2020.2972125 – volume: 33 start-page: 11525 year: 2020 ident: 313_CR26 publication-title: Adv Neural Inf Process Syst – volume: 107 start-page: 102344 year: 2024 ident: 313_CR51 publication-title: Inform Fus doi: 10.1016/j.inffus.2024.102344 – ident: 313_CR46 – ident: 313_CR9 doi: 10.1109/TNNLS.2021.3084827 – volume: 218 start-page: 297 year: 2019 ident: 313_CR14 publication-title: Int J Prod Econ doi: 10.1016/j.ijpe.2019.06.012 – ident: 313_CR33 doi: 10.1016/j.bspc.2024.105943 – ident: 313_CR57 doi: 10.1109/CVPR42600.2020.01095 – ident: 313_CR12 – ident: 313_CR52 doi: 10.1109/TPAMI.2022.3148470 – ident: 313_CR37 – ident: 313_CR21 doi: 10.1109/CVPR46437.2021.00881 – ident: 313_CR20 doi: 10.4249/scholarpedia.5947 – ident: 313_CR27 – ident: 313_CR58 doi: 10.1109/CVPR46437.2021.01553 – ident: 313_CR15 doi: 10.1007/978-3-030-58607-2_16 – ident: 313_CR44 doi: 10.1109/CVPR.2004.1315142 – ident: 313_CR55 doi: 10.1145/3474085.3475634 – ident: 313_CR42 doi: 10.1016/j.neucom.2018.03.030 – ident: 313_CR60 doi: 10.1109/CVPR42600.2020.01093 – ident: 313_CR36 doi: 10.18653/v1/N16-1174 – volume: 22 start-page: 3180 issue: 12 year: 2020 ident: 313_CR59 publication-title: IEEE Trans Multimedia doi: 10.1109/TMM.2020.2972125 – ident: 313_CR49 doi: 10.1109/ICCV.2015.303 – volume: 10 start-page: 4913 issue: 14 year: 2020 ident: 313_CR16 publication-title: Appl Sci doi: 10.3390/app10144913 – ident: 313_CR13 doi: 10.1109/SIBGRAPI62404.2024.10716271 – ident: 313_CR53 doi: 10.1109/ICCV.2019.00586 – ident: 313_CR32 doi: 10.1609/aaai.v38i16.29752 – volume: 299 start-page: 42 year: 2018 ident: 313_CR38 publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.03.030 – ident: 313_CR5 doi: 10.1109/TCYB.2022.3179020 – ident: 313_CR35 doi: 10.1109/CVPR52688.2022.01602 – ident: 313_CR28 – volume: 91 start-page: 105943 year: 2024 ident: 313_CR34 publication-title: Biomed Sign Process Control doi: 10.1016/j.bspc.2024.105943 – ident: 313_CR39 doi: 10.1109/ICCV.2019.00356 – ident: 313_CR2 doi: 10.1109/ICCV.2015.279 – ident: 313_CR56 doi: 10.24963/ijcai.2022/292 – volume: 452 start-page: 48 year: 2021 ident: 313_CR30 publication-title: Neurocomputing doi: 10.1016/j.neucom.2021.03.091 – volume: 130 start-page: 2337 issue: 9 year: 2022 ident: 313_CR62 publication-title: Int J Comput Vision doi: 10.1007/s11263-022-01653-1 – volume: 34 start-page: 9694 year: 2021 ident: 313_CR17 publication-title: Adv Neural Inf Process Syst – ident: 313_CR40 doi: 10.3390/app10144913 – ident: 313_CR6 doi: 10.1016/j.neucom.2021.03.091 – ident: 313_CR7 doi: 10.1145/3132847.3132892 – volume: 17 start-page: 1 issue: 4 year: 2021 ident: 313_CR29 publication-title: ACM Trans Multimed Comput Commun Appl (TOMM) doi: 10.1145/3451390 – ident: 313_CR1 doi: 10.1109/CVPR.2019.01064 – ident: 313_CR61 doi: 10.1109/TCSVT.2023.3254530 – volume: 33 start-page: 6999 issue: 12 year: 2021 ident: 313_CR18 publication-title: IEEE Trans Neural Netw Learn Syst doi: 10.1109/TNNLS.2021.3084827 – ident: 313_CR10 – ident: 313_CR48 doi: 10.1109/TPAMI.2016.2587640 – ident: 313_CR24 doi: 10.1007/978-3-030-01240-3_17 – ident: 313_CR41 doi: 10.1109/TIFS.2024.3388949 – ident: 313_CR50 doi: 10.1109/CVPR52688.2022.01521 – ident: 313_CR4 doi: 10.1016/j.inffus.2024.102344 – volume: 39 start-page: 652 issue: 4 year: 2016 ident: 313_CR43 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2016.2587640 – volume: 33 start-page: 6144 issue: 10 year: 2023 ident: 313_CR45 publication-title: IEEE Trans Circuits Syst Video Technol doi: 10.1109/TCSVT.2023.3254530 – ident: 313_CR25 – volume: 54 start-page: 948 issue: 2 year: 2022 ident: 313_CR23 publication-title: IEEE Trans cybern doi: 10.1109/TCYB.2022.3179020 – ident: 313_CR3 doi: 10.1145/3219819.3220036 – ident: 313_CR8 doi: 10.1109/CVPR.2017.173 – ident: 313_CR31 – ident: 313_CR47 doi: 10.24963/ijcai.2022/348
SSID	ssj0001765436
Score	2.3211296
Snippet	Fine-grained image-text matching, which is pivotal to multimodal intelligence, has advanced semantic correspondence inference through inter-modal region-word... Abstract Fine-grained image-text matching, which is pivotal to multimodal intelligence, has advanced semantic correspondence inference through inter-modal...
SourceID	doaj proquest crossref springer
SourceType	Open Website Aggregation Database Index Database Publisher
StartPage	281
SubjectTerms	Adaptation Associations Attention Computer Imaging Computer Science Database Management Dynamic graph attention mechanism Effectiveness Embedding Embedding similarity graph Hard negative samples HiCoS-Net Hierarchical inter-modal semantic network Knowledge Learning Machine Learning Matching Neural networks Original Paper Pattern Recognition and Graphics Semantics Software Engineering/Programming and Operating Systems Systems and Data Security Theory of Computation Vision
SummonAdditionalLinks	– databaseName: Publicly Available Content Database dbid: PIMPY link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9NAEB6VlAMX-gDUQKn2wK2sanu9XpsLgqpVK5UoUotUTtY-oxwalySF_nxmNutGRYJTfbJsa7XWzM57vgH4UJZFQMXmuZJaUEuO4aYyOa986YLKjc5tBHG9UKNRfX3djFN79CKVVfYyMQrqFdoz1W2jED5ynaWI-ZEgvYK-eFV-vv3JaYYU5VrTQI1nsEnAW9kANsfn38Y_1jEXRZ2UVeqdiR10JV6UyJQ8ohjy-0f6KcL4P7I9_0qXRi10uvW0-9-Gl8kaZV9W7LMDG362C1v9pAeWDv4ruDubHneXfOSXnxgNz47pB6Quiz_BbzqH9xH7mqUxFBNGEV7mVgPvGaF4xrpKhkYyo04vNvOTCDrO9W8992x6g5KNUx0KQyM6Vni-hu-nJ1fHZzwNbOBW1MWSo7OI5q_xmXPo6BQqFFlhJXJC5hsbZBC2so0RFIg2eaNlLXRjZK2VVaKUwoo3MJh1M78HTLpSOpQ-RgaPK6FbKCrhpVF5cIRyOITDnkzt7QqXo31AYI5EbZGoEflUtPdD-EqUfPiSMLXjg24-adMRbXFzXmoUUgRQVAZl6syJ3DpdZLI2QQ1hv6dsmw76ol0Tcggfe95Yv_73lt7-f7V38KIgroxdj_swWM7v_Ht4bn8tp4v5QWLsP0PdB7Q priority: 102 providerName: ProQuest
Title	HiCoS-Net: hierarchical cross-modal graph learning with dynamic attention for hard negative-aware image-text matching
URI	https://link.springer.com/article/10.1007/s44443-025-00313-x https://www.proquest.com/docview/3266193364 https://doaj.org/article/c6ce5a05115444f7b80d31cda2058bf7
Volume	37
WOSCitedRecordID	wos001603362600002&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2213-1248 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001765436 issn: 1319-1578 databaseCode: DOA dateStart: 20250101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 2213-1248 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001765436 issn: 1319-1578 databaseCode: K7- dateStart: 20250301 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2213-1248 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001765436 issn: 1319-1578 databaseCode: BENPR dateStart: 20250301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 2213-1248 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001765436 issn: 1319-1578 databaseCode: PIMPY dateStart: 20250301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwEB5VtAcuLRRQt1DkQ2_FIonjOOkNEIiq7WpVQIJT5CfaA7vVshR-fmcmWV5SxaWXKEoix5oZ2zP2fN8AfC7LIuHCFqXRVhEkx0lXuVxWsQzJ5M7mnklcf5jhsD4_b0aPSn1RTlhHD9wJbtdXPmqLpkO0MWUyrs6Cyn2wRaZrlxhHnpnmUTDFuyuGMJMMLSKUTo522SNmGDeHLZV0fKklcxfKuyerEpP3P_E4nx2S8tpztAJve6dR7HWdXYVXcfIe3i0KMoh-fK7BzfH4YHoih3H-VVCNaz4lQCUI_qu8mga8Z4pq0VeLuBS0EStCV5deENkmpz8K9GUFAbLEJF4yN7i0t3YWxfgKJyBJ6SICfV1OxFyHs6PD04Nj2ddVkF7VxVxiTIdeqotZCBiPFCYVWeE1KiyLjU86KZR54xTtF7u8sbpWtnG6tsYbVWrl1QYsTaaT-AGEDqUOOEk4nSK2hNGbqlTUzuQpEBnhAL4s5Nr-7ugz2nuiZNZCi1pgglLV3g1gn0R__yVRX_MDNIi2N4j2JYMYwNZCcW0_Hq9bRX5Io1RVDmBnocyH1__u0sf_0aVNWC7I2BjCuAVL89lN_ARv_J_5-Hq2Da_3D4ejX9tswXj9biQ-G337Obr4Cy628p0
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VFAkuLU-RUmAPcIIVttfrdZAQgkKVqGkUiSKVk7svRznELklK2z_Fb2RmYzcqEtx6wCfLtla762_nsTvzDcDLNE1KVGyeK6kFpeQYbjIT88ynrlSx0bENJK5DNRrlx8e98Qb8anNhKKyylYlBULva0h75W0GaBL3vLP1w-oNT1Sg6XW1LaKxgceAvz9FlW7wffMb_-ypJ9r8c7fV5U1WAW5EnS44eDdpoxkfOoTWeqBLdfyuxu5Hv2VKWwma2ZwTtlpq4p2UudM_IXCurRCqFFdjuLdjEQcqoA5vjweH4-3pXR1GuZtZk54QcvRQvOiqVPPAk8otrGjAUCrhm3f5xIBv03P72_zZD92CrsajZx9USuA8bvnoA2221CtYIr4dw1p_u1V_5yC_fMSoAHo5QEKEsTBOf1Q7vA383a0ppTBjtUjN3WenZ1DJiIg2xoQwNfUbZaqzyk0CczvW5nns2naF05hRLw9ARCFGqj-DbjQz-MXSquvJPgEmXSocS1MjSY0vo2opMeGlUXDpiauzC6xYIxemKW6S4YpEOsCkQNoG9VRQXXfhEWLn6knjBw4N6PikaMVNg57zUKGiJZCktlckjJ2LrdBLJ3JSqC7stdopGWC2KNXC68KZF3_r137u08-_WXsCd_tHhsBgORgdP4W5CayBkce5CZzk_88_gtv25nC7mz5tlxODkpnH5G6i0V78
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=HiCoS-Net%3A+hierarchical+cross-modal+graph+learning+with+dynamic+attention+for+hard+negative-aware+image-text+matching&rft.jtitle=Journal+of+King+Saud+University.+Computer+and+information+sciences&rft.au=Dingcheng+Feng&rft.au=Ning+Luo&rft.au=Shudong+Zhang&rft.au=Lijuan+Zhou&rft.date=2025-11-01&rft.pub=Springer&rft.issn=1319-1578&rft.eissn=2213-1248&rft.volume=37&rft.issue=9&rft.spage=1&rft.epage=30&rft_id=info:doi/10.1007%2Fs44443-025-00313-x&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_c6ce5a05115444f7b80d31cda2058bf7
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1319-1578&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1319-1578&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1319-1578&client=summon