{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T03:14:56Z","timestamp":1778901296545,"version":"3.51.4"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176271"],"award-info":[{"award-number":["62176271"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772568"],"award-info":[{"award-number":["61772568"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2019A1515012029"],"award-info":[{"award-number":["2019A1515012029"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Program of Guangzhou","award":["202201011681"],"award-info":[{"award-number":["202201011681"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/tcsvt.2022.3203247","type":"journal-article","created":{"date-parts":[[2022,9,7]],"date-time":"2022-09-07T19:32:29Z","timestamp":1662579149000},"page":"920-934","source":"Crossref","is-referenced-by-count":18,"title":["Deep Supervised Dual Cycle Adversarial Network for Cross-Modal Retrieval"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4751-504X","authenticated-orcid":false,"given":"Lei","family":"Liao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0795-3221","authenticated-orcid":false,"given":"Meng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-9519","authenticated-orcid":false,"given":"Bob","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, PAMI Research Group, University of Macau, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. ICML","author":"Andrew"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2900171"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref5","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. NeuIPS","author":"Goodfellow"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_33"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350974"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331213"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029181"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3088863"},{"key":"ref13","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00536"},{"key":"ref16","first-page":"1","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. ICLR Workshop Papers","author":"Mikolov"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2705068"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2400779"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.142"},{"key":"ref22","first-page":"139","article-title":"Collecting image annotations using Amazon\u2019s mechanical Turk","volume-title":"Proc. NAACL HLT Workshop Creating Speech Lang. Data With Amazon\u2019s Mech. Turk","author":"Rashtchian"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref24","first-page":"1","article-title":"Multi-view canonical correlation analysis","volume-title":"Proc. Conf. Data Mining Data Warehouses (SiKDD)","author":"Rupnik"},{"key":"ref25","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref27","article-title":"A comprehensive survey on cross-modal retrieval","volume-title":"arXiv:1607.06215","author":"Wang","year":"2016"},{"key":"ref28","first-page":"1083","article-title":"On deep multi-view representation learning","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16376"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.08.009"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107335"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240521"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.11.042"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2985540"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8464"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2276704"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2276704"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2647904"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927224"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877127"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref48","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"arXiv:2102.05918","author":"Jia","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref51","article-title":"A comprehensive empirical study of vision-language pre-trained model for supervised cross-modal retrieval","volume-title":"arXiv:2201.02772","author":"Zeng","year":"2022"},{"key":"ref52","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482194"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109316"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9982"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3532519"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878970"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00446"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3144352"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2100463"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075242"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10036154\/09880488.pdf?arnumber=9880488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T03:33:52Z","timestamp":1710387232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9880488\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":65,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3203247","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}