Dual-Level Representation Enhancement on Characteristic and Context for Image-Text Retrieval
Image-text retrieval is a fundamental and vital task in multi-media retrieval and has received growing attention since it connects heterogeneous data. Previous methods that perform well on image-text retrieval mainly focus on the interaction between image regions and text words. But these approaches...
Saved in:
| Published in | IEEE transactions on circuits and systems for video technology Vol. 32; no. 11; pp. 8037 - 8050 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
01.11.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Image-text retrieval is a fundamental and vital task in multi-media retrieval and has received growing attention since it connects heterogeneous data. Previous methods that perform well on image-text retrieval mainly focus on the interaction between image regions and text words. But these approaches lack joint exploration of characteristics and contexts of regions and words, which will cause semantic confusion of similar objects and loss of contextual understanding. To address these issues, a dual-level representation enhancement network (DREN) is proposed to strength the characteristic and contextual representations by innovative block-level and instance-level representation enhancement modules, respectively. The block-level module focuses on mining the potential relations between multiple blocks within each instance representation, while the instance-level module concentrates on learning the contextual relations between different instances. To facilitate the accurate matching of image-text pairs, we propose the graph correlation inference and weighted adaptive filtering to conduct the local and global matching between image-text pairs. Extensive experiments on two challenging datasets (i.e., Flickr30K and MSCOCO) verify the superiority of our method for image-text retrieval. |
|---|---|
| AbstractList | Image-text retrieval is a fundamental and vital task in multi-media retrieval and has received growing attention since it connects heterogeneous data. Previous methods that perform well on image-text retrieval mainly focus on the interaction between image regions and text words. But these approaches lack joint exploration of characteristics and contexts of regions and words, which will cause semantic confusion of similar objects and loss of contextual understanding. To address these issues, a dual-level representation enhancement network (DREN) is proposed to strength the characteristic and contextual representations by innovative block-level and instance-level representation enhancement modules, respectively. The block-level module focuses on mining the potential relations between multiple blocks within each instance representation, while the instance-level module concentrates on learning the contextual relations between different instances. To facilitate the accurate matching of image-text pairs, we propose the graph correlation inference and weighted adaptive filtering to conduct the local and global matching between image-text pairs. Extensive experiments on two challenging datasets (i.e., Flickr30K and MSCOCO) verify the superiority of our method for image-text retrieval. |
| Author | Li, Xuanya Li, Qiang Yang, Song Liu, An-An Li, Wenhui |
| Author_xml | – sequence: 1 givenname: Song orcidid: 0000-0002-8238-8226 surname: Yang fullname: Yang, Song organization: School of Microelectronics, Tianjin University, Tianjin, China – sequence: 2 givenname: Qiang surname: Li fullname: Li, Qiang organization: School of Microelectronics, Tianjin University, Tianjin, China – sequence: 3 givenname: Wenhui orcidid: 0000-0001-9609-6120 surname: Li fullname: Li, Wenhui email: liwenhui@tju.edu.cn organization: School of Electrical and Information Engineering, Tianjin University, Tianjin, China – sequence: 4 givenname: Xuanya orcidid: 0000-0002-2227-207X surname: Li fullname: Li, Xuanya organization: Baidu Inc., Beijing, China – sequence: 5 givenname: An-An orcidid: 0000-0001-5755-9145 surname: Liu fullname: Liu, An-An email: anan0422@gmail.com organization: School of Electrical and Information Engineering, Tianjin University, Tianjin, China |
| BookMark | eNp9kMFOwzAMhiM0JLbBC8ClEueOxGna5IjKgEmTkMbghFRlqcM6delIswneno5NHDhwsf1b_mz5H5CeaxwScsnoiDGqbub58-t8BBRgxJmEBNIT0mdCyBiAil5XU8FiCUyckUHbrihliUyyPnm72-o6nuIO62iGG48tuqBD1bho7JbaGVx3jaiT-VJ7bQL6qg2VibQro7xxAT9DZBsfTdb6HeP5Xs4w-Ap3uj4np1bXLV4c85C83I_n-WM8fXqY5LfT2IASIS6FZTrjVoJAmxqthE3RljwzZaLAIGcoRVqCXaQ8ydRiAYoJRMnKBLgqEz4k14e9G998bLENxarZetedLCADlXJJuzAk8jBlfNO2Hm1hqsOrweuqLhgt9l4WP14Wey-Lo5cdCn_Qja_W2n_9D10doAoRfwGVqSRNFf8GqA-DDA |
| CODEN | ITCTEM |
| CitedBy_id | crossref_primary_10_1038_s41598_023_50739_4 crossref_primary_10_1016_j_knosys_2024_111503 crossref_primary_10_1109_TCSVT_2024_3394551 crossref_primary_10_1155_2023_9604454 crossref_primary_10_32604_cmes_2023_028018 crossref_primary_10_61186_ijbc_15_3_13 crossref_primary_10_1007_s00500_023_09223_4 crossref_primary_10_1007_s10723_023_09717_3 crossref_primary_10_1007_s11356_023_29118_z crossref_primary_10_3389_fpubh_2023_1273253 crossref_primary_10_1155_2023_2768126 crossref_primary_10_1109_JPROC_2024_3525147 crossref_primary_10_1109_TCSVT_2024_3358411 crossref_primary_10_1007_s00500_023_09587_7 crossref_primary_10_1016_j_suscom_2023_100921 crossref_primary_10_1155_2024_8014111 crossref_primary_10_3390_math11204322 crossref_primary_10_1109_ACCESS_2023_3319452 crossref_primary_10_1109_TCSVT_2024_3480949 crossref_primary_10_1007_s10257_023_00665_9 crossref_primary_10_1109_ACCESS_2023_3318120 crossref_primary_10_1007_s00500_023_09313_3 crossref_primary_10_1109_TCSVT_2023_3253548 crossref_primary_10_3390_app13158838 crossref_primary_10_1016_j_engappai_2024_108150 crossref_primary_10_1109_TCSVT_2024_3497997 crossref_primary_10_1109_TMM_2023_3289753 crossref_primary_10_1109_TMM_2023_3261443 crossref_primary_10_2147_JMDH_S410301 crossref_primary_10_1049_cit2_12319 crossref_primary_10_1007_s00500_023_09210_9 crossref_primary_10_1007_s00500_023_09423_y crossref_primary_10_1109_TCSVT_2022_3233042 crossref_primary_10_1016_j_ipm_2023_103280 crossref_primary_10_1111_exsy_13468 crossref_primary_10_1007_s10723_023_09708_4 crossref_primary_10_1007_s11042_023_17704_9 crossref_primary_10_1109_ACCESS_2023_3339553 crossref_primary_10_1007_s11042_023_17956_5 crossref_primary_10_7717_peerj_cs_1666 crossref_primary_10_1109_TCSVT_2024_3392619 crossref_primary_10_1007_s00500_023_09264_9 crossref_primary_10_1109_TCSVT_2022_3224068 crossref_primary_10_1007_s00521_023_09366_3 crossref_primary_10_1109_LSP_2023_3310870 crossref_primary_10_3390_bioengineering10080979 crossref_primary_10_1016_j_compbiomed_2023_107293 crossref_primary_10_1016_j_patcog_2024_111247 crossref_primary_10_3389_fnins_2023_1256351 crossref_primary_10_1016_j_engappai_2023_106787 crossref_primary_10_3390_app13169346 crossref_primary_10_1016_j_engappai_2023_107037 crossref_primary_10_1016_j_ipm_2024_103990 crossref_primary_10_1007_s00500_023_09222_5 crossref_primary_10_1007_s00500_023_09224_3 crossref_primary_10_1016_j_heliyon_2023_e22156 crossref_primary_10_1007_s11760_023_02761_2 crossref_primary_10_1109_TMM_2024_3521736 crossref_primary_10_1007_s10723_024_09755_5 crossref_primary_10_1016_j_knosys_2025_113355 crossref_primary_10_3390_math11194132 crossref_primary_10_1109_TCSVT_2023_3254530 crossref_primary_10_1109_ACCESS_2023_3317893 crossref_primary_10_1016_j_asoc_2023_110655 crossref_primary_10_1109_TCSVT_2024_3384297 crossref_primary_10_1080_15397734_2023_2229913 crossref_primary_10_1109_ACCESS_2024_3358422 crossref_primary_10_1186_s13677_023_00554_z crossref_primary_10_1016_j_inffus_2023_102006 crossref_primary_10_3390_rs15225342 crossref_primary_10_1007_s12559_023_10179_8 crossref_primary_10_1109_TCSVT_2024_3369656 crossref_primary_10_1007_s00500_023_09162_0 crossref_primary_10_1080_15376494_2023_2227413 crossref_primary_10_1016_j_patcog_2025_111556 crossref_primary_10_1109_ACCESS_2023_3311027 crossref_primary_10_1007_s00500_023_09115_7 crossref_primary_10_1007_s00500_023_09319_x crossref_primary_10_1007_s10723_023_09705_7 crossref_primary_10_1007_s10723_023_09709_3 crossref_primary_10_1145_3623396 crossref_primary_10_1007_s00500_023_09032_9 crossref_primary_10_3390_cancers15174412 crossref_primary_10_1007_s00500_023_09031_w crossref_primary_10_1007_s11042_023_16517_0 crossref_primary_10_1007_s40747_023_01183_4 crossref_primary_10_1007_s11276_023_03546_8 crossref_primary_10_3233_JIFS_237410 crossref_primary_10_1109_TCSVT_2023_3307554 crossref_primary_10_7717_peerj_cs_1681 crossref_primary_10_1007_s11071_023_09170_7 crossref_primary_10_1038_s41598_023_47089_6 |
| Cites_doi | 10.1109/ICCV.2019.00591 10.1109/TIP.2018.2882225 10.1109/CVPR.2018.00750 10.1109/TCSVT.2021.3067449 10.1109/TCSVT.2021.3060713 10.1007/978-3-319-10602-1_48 10.1111/j.1551-6709.2009.01023.x 10.1109/CVPR.2018.00645 10.1109/CBMS.1992.245041 10.1109/TCSVT.2021.3127562 10.1109/CVPR42600.2020.00359 10.1109/TMM.2022.3151145 10.1007/s11280-018-0541-x 10.24963/ijcai.2019/720 10.1109/TPAMI.2021.3053577 10.1145/3343031.3350869 10.1109/TPAMI.2016.2598339 10.1109/CVPR.2016.541 10.1109/cvpr.2016.90 10.1109/CVPR42600.2020.01280 10.1109/TPAMI.2018.2797921 10.1109/ICCV.2019.00586 10.1007/978-3-030-01225-0_13 10.1109/ICCV.2019.00475 10.24963/ijcai.2019/526 10.1109/TCSVT.2020.3030656 10.1109/cvpr42600.2020.01267 10.1162/neco.1997.9.8.1735 10.1109/TNNLS.2020.2978386 10.1109/ICCV.2015.301 10.1007/s11263-016-0965-7 10.1097/MD.0000000000024427 10.1145/3394171.3413961 10.1109/tpami.2016.2577031 10.1109/WACV45572.2020.9093614 10.1109/TIP.2021.3106805 10.24963/ijcai.2019/111 10.1109/TCSVT.2021.3061153 10.1109/TMM.2021.3128744 10.1109/TNNLS.2022.3152990 10.1109/CVPR42600.2020.01093 |
| 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 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TCSVT.2022.3182426 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present 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://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2205 |
| EndPage | 8050 |
| ExternalDocumentID | 10_1109_TCSVT_2022_3182426 9794669 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Key Research and Development Program of China grantid: 2021YFF0704003 funderid: 10.13039/501100012166 – fundername: National Natural Science Foundation of China grantid: U21B2024 funderid: 10.13039/501100001809 – fundername: Baidu Program funderid: 10.13039/100018903 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION RIG 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c295t-d5f1a73f825ef6ca95f6efd37cd492ce31e856d2fb63479bb2915ee81d4239d43 |
| IEDL.DBID | RIE |
| ISSN | 1051-8215 |
| IngestDate | Mon Jun 30 05:11:05 EDT 2025 Tue Jul 01 00:41:18 EDT 2025 Thu Apr 24 23:03:17 EDT 2025 Wed Aug 27 02:14:46 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 11 |
| 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-c295t-d5f1a73f825ef6ca95f6efd37cd492ce31e856d2fb63479bb2915ee81d4239d43 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-5755-9145 0000-0002-8238-8226 0000-0002-2227-207X 0000-0001-9609-6120 |
| PQID | 2729638096 |
| PQPubID | 85433 |
| PageCount | 14 |
| ParticipantIDs | crossref_citationtrail_10_1109_TCSVT_2022_3182426 proquest_journals_2729638096 crossref_primary_10_1109_TCSVT_2022_3182426 ieee_primary_9794669 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2022-11-01 |
| PublicationDateYYYYMMDD | 2022-11-01 |
| PublicationDate_xml | – month: 11 year: 2022 text: 2022-11-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on circuits and systems for video technology |
| PublicationTitleAbbrev | TCSVT |
| 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 | ref13 ref12 ref15 ref11 ref10 ref17 ref16 ref18 Vaswani (ref20) ref46 ref45 ref48 ref47 ref42 ref44 ref43 Guyon (ref19) 2003; 3 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 Ma (ref49) 2019; 1 ref30 ref33 ref32 ref2 ref1 Karpathy (ref22) ref39 ref24 ref23 ref26 ref25 Kiros (ref41) 2014; abs/1411.2539 ref28 ref27 ref29 Faghri (ref14) Frome (ref21) Chung (ref38) 2014; abs/1412.3555 |
| References_xml | – ident: ref44 doi: 10.1109/ICCV.2019.00591 – start-page: 5998 volume-title: Proc. NIPS ident: ref20 article-title: Attention is all you need – ident: ref29 doi: 10.1109/TIP.2018.2882225 – ident: ref24 doi: 10.1109/CVPR.2018.00750 – ident: ref3 doi: 10.1109/TCSVT.2021.3067449 – volume: abs/1412.3555 start-page: 1 year: 2014 ident: ref38 article-title: Empirical evaluation of gated recurrent neural networks on sequence modeling publication-title: CoRR – ident: ref1 doi: 10.1109/TCSVT.2021.3060713 – ident: ref40 doi: 10.1007/978-3-319-10602-1_48 – ident: ref11 doi: 10.1111/j.1551-6709.2009.01023.x – ident: ref23 doi: 10.1109/CVPR.2018.00645 – volume: 1 start-page: 105 issue: 1 year: 2019 ident: ref49 article-title: PaddlePaddle: An open-source deep learning platform from industrial practice publication-title: Frontiers Data Domputing – ident: ref12 doi: 10.1109/CBMS.1992.245041 – ident: ref7 doi: 10.1109/TCSVT.2021.3127562 – ident: ref16 doi: 10.1109/CVPR42600.2020.00359 – ident: ref27 doi: 10.1109/TMM.2022.3151145 – start-page: 1889 volume-title: Proc. NeurIPS ident: ref22 article-title: Deep fragment embeddings for bidirectional image sentence mapping – ident: ref25 doi: 10.1007/s11280-018-0541-x – start-page: 12 volume-title: Proc. BMVC ident: ref14 article-title: VSE++: Improving visual-semantic embeddings with hard negatives – ident: ref33 doi: 10.24963/ijcai.2019/720 – ident: ref5 doi: 10.1109/TPAMI.2021.3053577 – ident: ref30 doi: 10.1145/3343031.3350869 – ident: ref28 doi: 10.1109/TPAMI.2016.2598339 – ident: ref13 doi: 10.1109/CVPR.2016.541 – ident: ref39 doi: 10.1109/cvpr.2016.90 – ident: ref17 doi: 10.1109/CVPR42600.2020.01280 – volume: abs/1411.2539 start-page: 1 year: 2014 ident: ref41 article-title: Unifying visual-semantic embeddings with multimodal neural language models publication-title: CoRR – ident: ref43 doi: 10.1109/TPAMI.2018.2797921 – ident: ref45 doi: 10.1109/ICCV.2019.00586 – ident: ref46 doi: 10.1007/978-3-030-01225-0_13 – ident: ref34 doi: 10.1109/ICCV.2019.00475 – ident: ref47 doi: 10.24963/ijcai.2019/526 – ident: ref2 doi: 10.1109/TCSVT.2020.3030656 – ident: ref9 doi: 10.1109/cvpr42600.2020.01267 – ident: ref10 doi: 10.1162/neco.1997.9.8.1735 – ident: ref36 doi: 10.1109/TNNLS.2020.2978386 – ident: ref42 doi: 10.1109/ICCV.2015.301 – ident: ref48 doi: 10.1007/s11263-016-0965-7 – ident: ref15 doi: 10.1097/MD.0000000000024427 – ident: ref32 doi: 10.1145/3394171.3413961 – ident: ref37 doi: 10.1109/tpami.2016.2577031 – ident: ref35 doi: 10.1109/WACV45572.2020.9093614 – ident: ref8 doi: 10.1109/TIP.2021.3106805 – start-page: 2121 volume-title: Proc. NIPS ident: ref21 article-title: DeViSE: A deep visual-semantic embedding model – ident: ref31 doi: 10.24963/ijcai.2019/111 – ident: ref6 doi: 10.1109/TCSVT.2021.3061153 – ident: ref26 doi: 10.1109/TMM.2021.3128744 – ident: ref4 doi: 10.1109/TNNLS.2022.3152990 – ident: ref18 doi: 10.1109/CVPR42600.2020.01093 – volume: 3 start-page: 1157 year: 2003 ident: ref19 article-title: An introduction to variable and feature selection publication-title: J. Mach. Learn. Res. |
| SSID | ssj0014847 |
| Score | 2.6366272 |
| Snippet | Image-text retrieval is a fundamental and vital task in multi-media retrieval and has received growing attention since it connects heterogeneous data. Previous... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 8037 |
| SubjectTerms | Adaptive filters Correlation Data mining Dual-level feature enhancement Feature extraction Filtration Image enhancement image-text retrieval Learning systems Matching Modules multi-block matching Multimedia Representations Retrieval Semantics Task analysis Visualization |
| Title | Dual-Level Representation Enhancement on Characteristic and Context for Image-Text Retrieval |
| URI | https://ieeexplore.ieee.org/document/9794669 https://www.proquest.com/docview/2729638096 |
| Volume | 32 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LSwMxEB5qT3rwVcVqlRy8adpu9tHNUWqLivVQq3gQlt3sBEFdRbcg_non2Qe-EG8bSELIzE7mS2a-AdiPReIK6Ss-iFXCPUcoHio34C5qP0aBjqvNhf7kIji58s5u_JsGHNa5MIhog8-waz7tW376pObmqqwnLRu6XIAFAm5Frlb9YuCFtpgYuQsOD-kcqxJk-rI3G15ezwgKCkEINTRn0pdDyFZV-WGK7fkyXoFJtbIirOS-O8-Trnr_Rtr436WvwnLpaLKjQjPWoIHZOix9oh9swe3xPH7g5yZsiE1tRGyZiJSxUXZn1MFMyqg5_ELrzOIsZZbW6i1n5PSy00eySnxmmlNboYvUdwOuxqPZ8ISX1Ra4ImHlPPW1Ew9cTZARdaBi6esAdeoOVOpJodB1MPSDVOgkMNmnSSKk4yOSv2s4BFPP3YRm9pThFjASf0xulVKhkJ4pKUNGlEC4QtIMgoe6DU61_ZEqqchNRYyHyEKSvoysyCIjsqgUWRsO6jHPBRHHn71bRgZ1z3L729CppByV_-prJAhfkBUiLLf9-6gdWDRzFxmIHWjmL3PcJVckT_asDn4Abb3bZQ |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDLZ4HIADb8R45sANMtb0seaIxqYBGwcoiANS1aaOkBgdgk5C_HqctJt4CXFrpKSNYjf2l9ifAQ4SkbpC-oo3E5VyzxGKh8oNuIvaT1Cg42pzoN-_DLo33vmdfzcFR5NcGES0wWdYN4_2Lj8bqpE5KjuWlg1dTsMs2X3fKbO1JncGXmjLiZHD4PCQLNk4RaYhj6PW9W1EYFAIwqihsUpfzJCtq_JjM7YWprME_fHcysCSx_qoSOvq_Rtt438nvwyLlavJTkrdWIEpzFdh4RMB4Rrcn46SAe-ZwCF2ZWNiq1SknLXzB6MQ5qWMmq0vxM4syTNmia3eCkZuLzt7on2JR6Z5ZWt0kQKvw02nHbW6vKq3wBWJq-CZr52k6WoCjagDlUhfB6gzt6kyTwqFroOhH2RCp4HJP01TIR0fkTxewyKYee4GzOTDHDeBkQIk5FgpFQrpmaIytI0SDFdIukEAUdfAGS9_rCoyclMTYxBbUNKQsRVZbEQWVyKrweFkzHNJxfFn7zUjg0nPavlrsDOWclz9ra-xIIRB-xChua3fR-3DXDfq9-Le2eXFNsyb75T5iDswU7yMcJcckyLds_r4AQiF3q4 |
| 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=Dual-Level+Representation+Enhancement+on+Characteristic+and+Context+for+Image-Text+Retrieval&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Yang%2C+Song&rft.au=Li%2C+Qiang&rft.au=Li%2C+Wenhui&rft.au=Li%2C+Xuanya&rft.date=2022-11-01&rft.issn=1051-8215&rft.eissn=1558-2205&rft.volume=32&rft.issue=11&rft.spage=8037&rft.epage=8050&rft_id=info:doi/10.1109%2FTCSVT.2022.3182426&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TCSVT_2022_3182426 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon |