{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T23:17:59Z","timestamp":1784330279529,"version":"3.55.0"},"reference-count":137,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3444817","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T17:23:55Z","timestamp":1723829035000},"page":"115716-115741","source":"Crossref","is-referenced-by-count":21,"title":["Cross-Modal Retrieval: A Review of Methodologies, Datasets, and Future Perspectives"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2992-5697","authenticated-orcid":false,"given":"Zhichao","family":"Han","sequence":"first","affiliation":[{"name":"Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4118-4809","authenticated-orcid":false,"given":"Azreen Bin","family":"Azman","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5088-2871","authenticated-orcid":false,"given":"Mas","family":"Rina Binti Mustaffa","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5791-065X","authenticated-orcid":false,"given":"Fatimah","family":"Binti Khalid","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3168431"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2002.1017738"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2705068"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21422"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3412847"},{"key":"ref6","first-page":"48","article-title":"Learning semantic attributes via a common latent space","volume-title":"Proc. Int. Conf. Comput. Vis. Theory Appl. (VISAPP)","volume":"2","author":"Al-Halah"},{"key":"ref7","article-title":"A comprehensive survey on cross-modal retrieval","author":"Wang","year":"2016","journal-title":"arXiv:1607.06215"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2020.100336"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-05744-1_25"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1511.08458"},{"key":"ref12","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"ref13","article-title":"Approximating CNNs with bag-of-local-features models works surprisingly well on ImageNet","author":"Brendel","year":"2019","journal-title":"arXiv:1904.00760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0494-3"},{"key":"ref17","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andrew"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.466"},{"key":"ref19","first-page":"34","article-title":"Overview and recent advances in partial least squares","volume-title":"Proc. Int. Stat. Optim. Perspect. Workshop Subspace, Latent Struct. Feature Selection","author":"Rosipal"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957143"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref24","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref29","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. 28th Int. Conf. Mach. Learn. (ICML)","author":"Ngiam"},{"key":"ref30","first-page":"2222","article-title":"Multimodal learning with deep Boltzmann machines","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Srivastava"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2507401"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70791"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2928180"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107335"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3424341"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3153962"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/119"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3380019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3563390"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"ref48","first-page":"1035","article-title":"Hugs are better than handshakes: Unsupervised cross-modal transformer hashing with multi-granularity alignment","volume-title":"Proc. 33rd Brit. Mach. Vis. Conf.","author":"Wang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109316"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.011"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957854"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.11.042"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107813"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108343"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119543"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-009-9117-9"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806240"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-018-3608-9"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2942494"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.5591\/978-1-57735-516-8\/IJCAI11-230"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539928"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2564638"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6006-5"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296813"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240547"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2861000"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940446"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10719"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11249"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.052"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/662"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2866771"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101968"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963957"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2974877"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109891"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.037"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109972"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263054"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654906"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.219"},{"key":"ref88","first-page":"3946","article-title":"Quantized correlation hashing for fast cross-modal search","volume-title":"Proc. 24th Int. Conf. Artif. Intell.","author":"Wu"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2607421"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914710"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.02.004"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3389547"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.439"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/396"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00312"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353752"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390673"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401086"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3014727"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.12.058"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019549"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11263"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301176"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2922128"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428330"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.087"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897500"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3172716"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3135420"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3177356"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3218656"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4567-3"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350934"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2019.00053"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00177"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2868826"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190722"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190641"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2879846"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2911456"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00089"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029181"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953692"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.05.006"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109211"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312385"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3263221"},{"key":"ref128","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2400779"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.14257\/ijsip.2015.8.4.13"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.02.011"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.2307\/2984875"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10638061.pdf?arnumber=10638061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T04:13:36Z","timestamp":1725164016000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10638061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":137,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3444817","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}