{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:25:50Z","timestamp":1783787150568,"version":"3.55.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["62273275"],"award-info":[{"award-number":["62273275"]}],"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":["62133012"],"award-info":[{"award-number":["62133012"]}],"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":["61936006"],"award-info":[{"award-number":["61936006"]}],"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":["62103314"],"award-info":[{"award-number":["62103314"]}],"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":["62303366"],"award-info":[{"award-number":["62303366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects of Shaanxi Province","doi-asserted-by":"publisher","award":["2020ZDLGY04-07"],"award-info":[{"award-number":["2020ZDLGY04-07"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Capability Support Program of Shaanxi","award":["2021TD-05"],"award-info":[{"award-number":["2021TD-05"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JST CREST","award":["JPMJCR20D3"],"award-info":[{"award-number":["JPMJCR20D3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3519112","type":"journal-article","created":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T19:18:37Z","timestamp":1734376717000},"page":"2186-2198","source":"Crossref","is-referenced-by-count":6,"title":["Cross-Modal Guided Visual Representation Learning for Social Image Retrieval"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2413-4698","authenticated-orcid":false,"given":"Ziyu","family":"Guan","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7622-0665","authenticated-orcid":false,"given":"Wanqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Northwest University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9834-4087","authenticated-orcid":false,"given":"Hongmin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology and the Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8000-3567","authenticated-orcid":false,"given":"Yuta","family":"Nakashima","sequence":"additional","affiliation":[{"name":"Institute for Datability Science, Osaka University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3320-896X","authenticated-orcid":false,"given":"Noboru","family":"Babaguchi","sequence":"additional","affiliation":[{"name":"Institute for Datability Science, Osaka University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9107-2354","authenticated-orcid":false,"given":"Xiaofei","family":"He","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/525"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01062"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01331-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16380"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.08.033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref11","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01547-8"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654948"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301269"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1016-8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00661"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02178"},{"key":"ref27","first-page":"48382","article-title":"StableRep: Synthetic images from text-to-image models make strong visual representation learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tian"},{"key":"ref28","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25172"},{"key":"ref30","first-page":"1","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mikolov"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3589185"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599439"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277791"},{"key":"ref36","first-page":"4444","article-title":"ConceptNet 5.5: An open multilingual graph of general knowledge","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Speer"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01376"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"ref39","first-page":"1753","article-title":"Spectral hashing","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Weiss"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.193"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.133"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3588683"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612596"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3001583"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11814"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3289765"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","article-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref51","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kendall"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108264"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10804591.pdf?arnumber=10804591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:39:32Z","timestamp":1738867172000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10804591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":54,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3519112","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}