{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T21:12:51Z","timestamp":1776719571790,"version":"3.51.2"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62425603"],"award-info":[{"award-number":["62425603"]}],"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":["62372233"],"award-info":[{"award-number":["62372233"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Science and Technology Program of Jiangsu Province","award":["BG2024042"],"award-info":[{"award-number":["BG2024042"]}]},{"DOI":"10.13039\/501100005145","name":"Basic Research Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20243018"],"award-info":[{"award-number":["BK20243018"]}],"id":[{"id":"10.13039\/501100005145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["30923010915"],"award-info":[{"award-number":["30923010915"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651086","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:52Z","timestamp":1768255312000},"page":"2996-3009","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Modal Knowledge Distillation Hashing Based on CLIP for Weakly Supervised Image Retrieval"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7821-6950","authenticated-orcid":false,"given":"Zhengyun","family":"Lu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2964-426X","authenticated-orcid":false,"given":"Lu","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.227"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.598"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00134"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2929957"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298947"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2467315"},{"key":"ref7","first-page":"798","article-title":"Greedy hash: Towards fast optimization for accurate hash coding in CNN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Su","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/115"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00315"},{"key":"ref10","first-page":"24286","article-title":"One loss for all: Deep hashing with a single cosine similarity based learning objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hoe","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00923"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3248170"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310333"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01062"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087356"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16380"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3589185"},{"key":"ref19","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref21","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","year":"2021"},{"key":"ref22","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref23","article-title":"Visual classification via description from large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Menon","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25159"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28139"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339628"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"ref38","first-page":"753","article-title":"Spectral hashing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"21","author":"Weiss","year":"2008"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.193"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459466"},{"key":"ref41","first-page":"353","article-title":"Minimal loss hashing for compact binary codes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Norouzi","year":"2011"},{"key":"ref42","first-page":"1061","article-title":"Hamming distance metric learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Norouzi","year":"2012"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298598"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2421443"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2636870"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2797248"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00306"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947358"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2929068"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2710186"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995267"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749160"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3131042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2776745"},{"key":"ref56","first-page":"10792","article-title":"Cross-modal learning with adversarial samples","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969792"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2869601"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2883522"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3044473"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00446"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2816743"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00505"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00130"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_6"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00314"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3064840"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01820"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355461"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329168.pdf?arnumber=11329168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:05:17Z","timestamp":1776715517000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329168\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651086","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}