Multimodal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing
In this article, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval. We proposed a novel method, dubbed cross-modal info-max hashing (CMIMH). First, to learn informative representations that...
Saved in:
Published in | IEEE transaction on neural networks and learning systems Vol. 34; no. 9; pp. 6289 - 6302 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
United States
IEEE
01.09.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | In this article, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval. We proposed a novel method, dubbed cross-modal info-max hashing (CMIMH). First, to learn informative representations that can preserve both intramodal and intermodal similarities, we leverage the recent advances in estimating variational lower bound of MI to maximizing the MI between the binary representations and input features and between binary representations of different modalities. By jointly maximizing these MIs under the assumption that the binary representations are modeled by multivariate Bernoulli distributions, we can learn binary representations, which can preserve both intramodal and intermodal similarities, effectively in a mini-batch manner with gradient descent. Furthermore, we find out that trying to minimize the modality gap by learning similar binary representations for the same instance from different modalities could result in less informative representations. Hence, balancing between reducing the modality gap and losing modality-private information is important for the cross-modal retrieval tasks. Quantitative evaluations on standard benchmark datasets demonstrate that the proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods. |
---|---|
AbstractList | In this article, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval. We proposed a novel method, dubbed cross-modal info-max hashing (CMIMH). First, to learn informative representations that can preserve both intramodal and intermodal similarities, we leverage the recent advances in estimating variational lower bound of MI to maximizing the MI between the binary representations and input features and between binary representations of different modalities. By jointly maximizing these MIs under the assumption that the binary representations are modeled by multivariate Bernoulli distributions, we can learn binary representations, which can preserve both intramodal and intermodal similarities, effectively in a mini-batch manner with gradient descent. Furthermore, we find out that trying to minimize the modality gap by learning similar binary representations for the same instance from different modalities could result in less informative representations. Hence, balancing between reducing the modality gap and losing modality-private information is important for the cross-modal retrieval tasks. Quantitative evaluations on standard benchmark datasets demonstrate that the proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods. |
Author | Cheung, Ngai-Man Nguyen, Tam V. Do, Thanh-Toan Hoang, Tuan |
Author_xml | – sequence: 1 givenname: Tuan orcidid: 0000-0002-1076-8043 surname: Hoang fullname: Hoang, Tuan email: hnanhtuan.91@gmail.com organization: Information System Technology and Design (ISTD), Singapore University of Technology and Design (SUTD), Singapore – sequence: 2 givenname: Thanh-Toan orcidid: 0000-0002-6249-0848 surname: Do fullname: Do, Thanh-Toan email: toan.do@monash.edu organization: Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton, VIC, Australia – sequence: 3 givenname: Tam V. orcidid: 0000-0003-0236-7992 surname: Nguyen fullname: Nguyen, Tam V. email: tamnguyen@udayton.edu organization: Department of Computer Science, University of Dayton, Dayton, OH, USA – sequence: 4 givenname: Ngai-Man orcidid: 0000-0003-0135-3791 surname: Cheung fullname: Cheung, Ngai-Man email: ngaiman_cheung@sutd.edu.sg organization: Information System Technology and Design (ISTD), Singapore University of Technology and Design (SUTD), Singapore |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/34982698$$D View this record in MEDLINE/PubMed |
BookMark | eNpdkU1v3CAQhlGUqvlo_kAqRUi95OItDIaF3FbbtIm0uz00kXpDrD1uiGzjGDtq8-vLfnQP5TKMeObVO7xn5LgNLRJyydmEc2Y-P6xWix8TYMAngguZAzsip8AVZCC0Pj7cpz9PyEWMzywdxaTKzXtyInKjQRl9SqrlWA--CaWr6XIcxlTu2yr0jRt8aOnS_faNf9s2N3RGV-EVazrruj644okmkD62ceywf_URS_oFsaPzPsSYLbeady4--fbXB_KucnXEi309J49fbx_md9ni-7f7-WyRFULyIeNSlFpwgLJyAiRHWUlVaixcKQp0ORoJBUwrbWSpJdMGVLHWU7d23OVrJsU5ud7pJoMvI8bBNj4WWNeuxTBGC4orI6VkkNBP_6HPYezb5M6ClmbKmeQsUbCjis1SPVa2633j-j-WM7sJwm6DsJsg7D6INHS1lx7XDZaHkX_fnoCPO8Aj4uHZKKWNMuIvSnuOLw |
CODEN | ITNNAL |
CitedBy_id | crossref_primary_10_3390_electronics13040677 crossref_primary_10_1109_TIP_2022_3195059 crossref_primary_10_1007_s10489_023_04715_0 crossref_primary_10_1007_s00530_023_01161_3 crossref_primary_10_3390_su141912066 crossref_primary_10_1007_s11263_024_02009_7 crossref_primary_10_1109_TCSVT_2022_3233042 crossref_primary_10_1155_2022_9726286 |
Cites_doi | 10.1609/aaai.v31i1.10719 10.1145/2600428.2609610 10.1609/aaai.v32i1.11249 10.1016/j.sigpro.2016.08.012 10.1145/2463676.2465274 10.1609/aaai.v31i1.10487 10.14778/2732296.2732301 10.1109/ICCV.2019.00312 10.1109/TMM.2015.2455415 10.1109/TMM.2019.2912714 10.1109/CVPR.2017.672 10.1109/TIP.2019.2897944 10.1016/j.patcog.2020.107335 10.1109/TCSVT.2017.2723302 10.1007/978-3-319-10602-1_48 10.1002/cpa.3160280102 10.1109/ICCV.2017.55 10.1109/TIP.2020.2963957 10.1145/1460096.1460104 10.1109/TPAMI.2018.2882816 10.1016/j.cviu.2019.102852 10.1109/TIP.2018.2878970 10.1145/3343031.3351053 10.1109/TMM.2019.2922128 10.1109/TMM.2018.2877122 10.1147/rd.41.0066 10.1109/TIP.2018.2890144 10.1609/aaai.v32i1.11263 10.1109/TNNLS.2019.2904991 10.1109/TIP.2020.3014727 10.1109/ICCV.2015.219 10.1109/TIP.2018.2821921 10.1007/978-3-030-01246-5_13 10.1109/TIP.2016.2564638 10.1109/TIP.2018.2863040 10.1109/TIP.2019.2941858 10.24963/ijcai.2018/396 10.1609/aaai.v28i1.8995 10.1109/CVPR46437.2021.01603 10.1109/CVPR42600.2020.00319 10.1109/TMM.2019.2935680 10.1109/CVPR.2017.348 10.1145/2939672.2939812 10.1016/j.ins.2015.07.022 10.1109/CVPR.2017.449 10.1109/CVPR.2018.00446 10.1145/2744204 10.1145/3123266.3123326 10.1609/aaai.v33i01.3301176 10.1007/978-3-030-58621-8_45 10.1109/ICCV.2017.439 10.1145/2647868.2654902 10.1109/TIP.2017.2676345 10.1109/CVPR.2010.5539994 10.1145/1646396.1646452 10.1109/TIP.2016.2607421 10.1145/2502081.2502107 10.1109/CVPR.2015.7299011 10.1109/TNNLS.2018.2869601 10.1109/ISIT44484.2020.9174424 10.1109/TIT.2010.2068870 10.1109/TMM.2018.2866771 10.1109/TPAMI.2012.193 10.1109/ICCV.2017.244 |
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 NPM AAYXX CITATION 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.2021.3135420 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Xplore PubMed CrossRef 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 | PubMed CrossRef 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 | PubMed Materials Research Database |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISSN | 2162-2388 |
EndPage | 6302 |
ExternalDocumentID | 10_1109_TNNLS_2021_3135420 34982698 9668969 |
Genre | orig-research Journal Article |
GrantInformation_xml | – fundername: Singapore University of Technology and Design (SUTD) grantid: PIE-SGP-AI-2018-01 funderid: 10.13039/501100007040 – fundername: National Research Foundation Singapore through its AI Singapore Program grantid: AISG-100E2018-005 funderid: 10.13039/501100001381 |
GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR AASAJ ABQJQ ABVLG ACIWK ACPRK AENEX AFRAH AKJIK ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF M43 MS~ O9- OCL PQQKQ RIA RIE RIG RNS NPM AAYXX CITATION 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-153d83122dfa3251e5f56d8ecad3cea4e952c27f895d8508926cb87aba1a4b053 |
IEDL.DBID | RIE |
ISSN | 2162-237X |
IngestDate | Thu Jul 25 11:17:39 EDT 2024 Fri Sep 13 07:53:08 EDT 2024 Fri Aug 23 03:38:33 EDT 2024 Sat Sep 28 08:21:11 EDT 2024 Wed Jun 26 19:25:19 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | true |
Issue | 9 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c351t-153d83122dfa3251e5f56d8ecad3cea4e952c27f895d8508926cb87aba1a4b053 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ORCID | 0000-0003-0135-3791 0000-0002-1076-8043 0000-0002-6249-0848 0000-0003-0236-7992 |
PMID | 34982698 |
PQID | 2859710510 |
PQPubID | 85436 |
PageCount | 14 |
ParticipantIDs | pubmed_primary_34982698 proquest_miscellaneous_2616955502 ieee_primary_9668969 proquest_journals_2859710510 crossref_primary_10_1109_TNNLS_2021_3135420 |
PublicationCentury | 2000 |
PublicationDate | 2023-09-01 |
PublicationDateYYYYMMDD | 2023-09-01 |
PublicationDate_xml | – month: 09 year: 2023 text: 2023-09-01 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 | 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 ref57 ref12 ref56 ref15 Nowozin (ref49) ref59 ref14 Barber (ref47) ref58 ref53 Chen (ref48) Hu (ref71) ref11 ref55 ref10 ref54 ref17 ref16 ref19 ref18 Weiss (ref52) Kumar (ref23) ref51 ref45 ref42 ref41 ref87 Wu (ref4) Devlin (ref85) 2018 ref8 ref7 ref9 ref3 ref6 ref5 Belghazi (ref50) ref82 ref40 Alemi (ref74) ref84 ref83 Kim (ref81) ref80 ref35 ref34 Krizhevsky (ref86) ref37 ref36 ref31 Hjelm (ref43) ref30 ref33 Poole (ref79) ref32 ref2 ref39 ref38 ref70 ref73 ref72 Hinton (ref78) 2012; 264 Tucker (ref77) ref68 ref67 ref26 ref25 ref69 ref20 ref63 ref22 ref66 ref21 ref65 Tishby (ref75) 2000 Wang (ref64) 2016; abs/1607 ref28 ref27 Maddison (ref76) ref29 Zhen (ref1) Federici (ref46) ref60 ref62 ref61 Rastegari (ref24) van den Oord (ref44) 2018 |
References_xml | – ident: ref15 doi: 10.1609/aaai.v31i1.10719 – ident: ref27 doi: 10.1145/2600428.2609610 – ident: ref13 doi: 10.1609/aaai.v32i1.11249 – ident: ref36 doi: 10.1016/j.sigpro.2016.08.012 – start-page: 1 volume-title: Proc. ICLR ident: ref74 article-title: Deep variational information bottleneck contributor: fullname: Alemi – ident: ref25 doi: 10.1145/2463676.2465274 – volume: abs/1607 start-page: 1 year: 2016 ident: ref64 article-title: A comprehensive survey on cross-modal retrieval publication-title: CoRR contributor: fullname: Wang – ident: ref11 doi: 10.1609/aaai.v31i1.10487 – ident: ref32 doi: 10.14778/2732296.2732301 – ident: ref38 doi: 10.1109/ICCV.2019.00312 – start-page: 1360 volume-title: Proc. IJCAI ident: ref23 article-title: Learning hash functions for cross-view similarity search contributor: fullname: Kumar – ident: ref31 doi: 10.1109/TMM.2015.2455415 – ident: ref17 doi: 10.1109/TMM.2019.2912714 – ident: ref29 doi: 10.1109/CVPR.2017.672 – start-page: 531 volume-title: Proc. ICML ident: ref50 article-title: Mutual information neural estimation contributor: fullname: Belghazi – ident: ref7 doi: 10.1109/TIP.2019.2897944 – volume: 264 start-page: 2146 issue: 1 year: 2012 ident: ref78 article-title: Neural networks for machine learning publication-title: Coursera, Video Lectures contributor: fullname: Hinton – ident: ref22 doi: 10.1016/j.patcog.2020.107335 – ident: ref41 doi: 10.1109/TCSVT.2017.2723302 – ident: ref84 doi: 10.1007/978-3-319-10602-1_48 – start-page: 1 volume-title: Proc. ICLR ident: ref76 article-title: The concrete distribution: A continuous relaxation of discrete random variables contributor: fullname: Maddison – ident: ref80 doi: 10.1002/cpa.3160280102 – ident: ref69 doi: 10.1109/ICCV.2017.55 – ident: ref19 doi: 10.1109/TIP.2020.2963957 – ident: ref82 doi: 10.1145/1460096.1460104 – start-page: 2 volume-title: Proc. NeurIPS ident: ref86 article-title: ImageNet classification with deep convolutional neural networks contributor: fullname: Krizhevsky – ident: ref60 doi: 10.1109/TPAMI.2018.2882816 – ident: ref57 doi: 10.1016/j.cviu.2019.102852 – ident: ref67 doi: 10.1109/TIP.2018.2878970 – ident: ref70 doi: 10.1145/3343031.3351053 – start-page: 1 volume-title: Proc. ICLR ident: ref43 article-title: Learning deep representations by mutual information estimation and maximization contributor: fullname: Hjelm – start-page: 1 volume-title: Proc. ICLR ident: ref46 article-title: Learning robust representations via multi-view information bottleneck contributor: fullname: Federici – ident: ref66 doi: 10.1109/TMM.2019.2922128 – ident: ref18 doi: 10.1109/TMM.2018.2877122 – ident: ref58 doi: 10.1147/rd.41.0066 – ident: ref30 doi: 10.1109/TIP.2018.2890144 – ident: ref34 doi: 10.1609/aaai.v32i1.11263 – start-page: 1 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref71 article-title: Information competing process for learning diversified representations contributor: fullname: Hu – ident: ref62 doi: 10.1109/TNNLS.2019.2904991 – ident: ref37 doi: 10.1109/TIP.2020.3014727 – ident: ref28 doi: 10.1109/ICCV.2015.219 – start-page: 1 volume-title: Proc. NIPS ident: ref77 article-title: REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models contributor: fullname: Tucker – ident: ref10 doi: 10.1109/TIP.2018.2821921 – ident: ref61 doi: 10.1007/978-3-030-01246-5_13 – start-page: 1 volume-title: Proc. ICML ident: ref81 article-title: Disentangling by factorising contributor: fullname: Kim – ident: ref8 doi: 10.1109/TIP.2016.2564638 – ident: ref9 doi: 10.1109/TIP.2018.2863040 – ident: ref35 doi: 10.1109/TIP.2019.2941858 – ident: ref39 doi: 10.24963/ijcai.2018/396 – start-page: 1376 volume-title: Proc. NIPS ident: ref1 article-title: Co-regularized hashing for multimodal data contributor: fullname: Zhen – ident: ref3 doi: 10.1609/aaai.v28i1.8995 – ident: ref72 doi: 10.1109/CVPR46437.2021.01603 – ident: ref87 doi: 10.1109/CVPR42600.2020.00319 – ident: ref56 doi: 10.1109/TMM.2019.2935680 – ident: ref12 doi: 10.1109/CVPR.2017.348 – start-page: 1 volume-title: Proc. NIPS ident: ref52 article-title: Spectral hashing contributor: fullname: Weiss – ident: ref16 doi: 10.1145/2939672.2939812 – ident: ref63 doi: 10.1016/j.ins.2015.07.022 – ident: ref55 doi: 10.1109/CVPR.2017.449 – start-page: 5171 volume-title: Proc. ICML ident: ref79 article-title: On variational bounds of mutual information contributor: fullname: Poole – ident: ref59 doi: 10.1109/CVPR.2018.00446 – start-page: 201 volume-title: Proc. NIPS ident: ref47 article-title: The IM algorithm: A variational approach to information maximization contributor: fullname: Barber – start-page: 3946 volume-title: Proc. IJCAI ident: ref4 article-title: Quantized correlation hashing for fast cross-modal search contributor: fullname: Wu – ident: ref2 doi: 10.1145/2744204 – ident: ref21 doi: 10.1145/3123266.3123326 – ident: ref42 doi: 10.1609/aaai.v33i01.3301176 – volume-title: arXiv:physics/0004057 year: 2000 ident: ref75 article-title: The information bottleneck method contributor: fullname: Tishby – ident: ref73 doi: 10.1007/978-3-030-58621-8_45 – ident: ref14 doi: 10.1109/ICCV.2017.439 – volume-title: arXiv:1810.04805 year: 2018 ident: ref85 article-title: BERT: Pre-training of deep bidirectional transformers for language understanding contributor: fullname: Devlin – ident: ref33 doi: 10.1145/2647868.2654902 – start-page: 1328 volume-title: Proc. ICML ident: ref24 article-title: Predictable dual-view hashing contributor: fullname: Rastegari – start-page: 2180 volume-title: Proc. NIPS ident: ref48 article-title: InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets contributor: fullname: Chen – ident: ref6 doi: 10.1109/TIP.2017.2676345 – ident: ref54 doi: 10.1109/CVPR.2010.5539994 – ident: ref83 doi: 10.1145/1646396.1646452 – ident: ref26 doi: 10.1109/TIP.2016.2607421 – ident: ref40 doi: 10.1145/2502081.2502107 – volume-title: arXiv:1807.03748 year: 2018 ident: ref44 article-title: Representation learning with contrastive predictive coding contributor: fullname: van den Oord – ident: ref5 doi: 10.1109/CVPR.2015.7299011 – ident: ref20 doi: 10.1109/TNNLS.2018.2869601 – ident: ref45 doi: 10.1109/ISIT44484.2020.9174424 – ident: ref51 doi: 10.1109/TIT.2010.2068870 – start-page: 271 volume-title: Proc. NIPS ident: ref49 article-title: F-GAN: Training generative neural samplers using variational divergence minimization contributor: fullname: Nowozin – ident: ref65 doi: 10.1109/TMM.2018.2866771 – ident: ref53 doi: 10.1109/TPAMI.2012.193 – ident: ref68 doi: 10.1109/ICCV.2017.244 |
SSID | ssj0000605649 |
Score | 2.5584142 |
Snippet | In this article, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient... |
SourceID | proquest crossref pubmed ieee |
SourceType | Aggregation Database Index Database Publisher |
StartPage | 6289 |
SubjectTerms | Binary codes Correlation Cross-modal retrieval Intermodal Lower bounds Matrix decomposition Maximization multi-modal mutual information (MI) Optimization Representation learning Representations Retrieval Semantics Similarity Task analysis Training unsupervised hashing Unsupervised learning variational information maximization |
Title | Multimodal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing |
URI | https://ieeexplore.ieee.org/document/9668969 https://www.ncbi.nlm.nih.gov/pubmed/34982698 https://www.proquest.com/docview/2859710510/abstract/ https://search.proquest.com/docview/2616955502 |
Volume | 34 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB61PXGhQHkECjISN8g28WttblWhWiGyF7rS3iLHdiSEmqy6G4T49YwdJxIIJG6R4jhxZsbzje1vBuCN4KVpmBJ5wOM5bxXPjeE6R1fWUutaq1TgDldrudrwT1uxPYJ3MxfGex8Pn_lFuIx7-a63Q1gqu0BorrTUx3CsCjpyteb1lAJxuYxol5aS5pQttxNHptAXN-v15y8YDdISg1QmOA0V4BjXCK61-s0lxRor_4ab0e1cn0I1ffB42uTbYjg0C_vzj1yO_zuiB3A_4U9yOSrMQzjy3SM4nWo7kGTqZ9BGZu5t77BxNQSSCUnMpSBJUpkfX28ThfM9uSTr_rvHXlOCcoINyabbD7swE-29Ix-835GrMPy8in2uxiJOj2Fz_fHmapWnmgy5ZaI85DhBOsVKSl1rGGIjL1ohnfLWOGa94V4LaumyVVo4heBPU2kbtTSNKQ1v0OKfwEnXd_4ZENZwXViUhmwct6LR6E2VdWV4RGhnM3g7iaXejak36hiyFLqO8qyDPOskzwzOwu-dW6Y_m8H5JMk6Wee-Dkn7EFnhdJTB6_k22lXYLDGd7wdsI0upBcZvNIOnowbMfU-K8_zv73wB90JR-vEk2jmcHO4G_xKhy6F5FXX2F4r_6GU |
link.rule.ids | 315,786,790,802,27957,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Nb9QwEB2VcoALBQo0UMBI3MDbxLGzNreqUC2wyYVdaW-RYzsSqpqs2A1C_HrGzodERSVukeI4sWcm88b2mwF4K3iiq1QK6vE45bXkVGuuKLqymhlbGyk9dzgvssWaf9mIzQG8n7gwzrlw-MzN_GXYy7et6fxS2RlCc6kydQfuop-PVc_WmlZUYkTmWcC7LMkYZel8M7JkYnW2KorlN4wHWYJhaio48zXgUq4QXiv5l1MKVVZuB5zB8VweQT5-cn_e5GrW7auZ-X0jm-P_jukhPBgQKDnvVeYRHLjmMRyN1R3IYOzHUAdu7nVrsXHeeZoJGbhLXpYk17--Xw8kzg_knBTtT4e9DinKCTYk62bXbf2_aOcs-ejcllz44dM89Lnoyzg9gfXlp9XFgg5VGahJRbKn-Iu0Mk0Ys7VOER05UYvMSme0TY3T3CnBDJvXUgkrEf4plplKznWlE80rtPmncNi0jTsBklZcxQalkVWWG1Ep9KfS2MQ_IpQ1EbwbxVJu--QbZQhaYlUGeZZenuUgzwiO_fROLYeZjeB0lGQ52Oeu9Gn7EFuhFkXwZrqNluW3S3Tj2g7bZEmmBEZwLIJnvQZMfY-K8_zf73wN9xarfFkuPxdfX8B9X6K-P5d2Cof7H517iUBmX70K-vsH9lbruw |
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=Multimodal+Mutual+Information+Maximization%3A+A+Novel+Approach+for+Unsupervised+Deep+Cross-Modal+Hashing&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Hoang%2C+Tuan&rft.au=Do%2C+Thanh-Toan&rft.au=Nguyen%2C+Tam+V.&rft.au=Cheung%2C+Ngai-Man&rft.date=2023-09-01&rft.issn=2162-237X&rft.eissn=2162-2388&rft.volume=34&rft.issue=9&rft.spage=6289&rft.epage=6302&rft_id=info:doi/10.1109%2FTNNLS.2021.3135420&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TNNLS_2021_3135420 |
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 |