{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T11:44:45Z","timestamp":1792151085930,"version":"4.4.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Artificial Intelligence-National Science and Technology Major Project","award":["2023ZD0121200"],"award-info":[{"award-number":["2023ZD0121200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222212"],"award-info":[{"award-number":["62222212"]}],"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":["62336001"],"award-info":[{"award-number":["62336001"]}],"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":["82141123"],"award-info":[{"award-number":["82141123"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tcsvt.2025.3558996","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T14:12:50Z","timestamp":1744121570000},"page":"9502-9516","source":"Crossref","is-referenced-by-count":5,"title":["Matryoshka Learning With Metric Transfer for Image-Text Matching"],"prefix":"10.1109","volume":"35","author":[{"given":"Pengzhe","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2839-8693","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nenan","family":"Lyu","sequence":"additional","affiliation":[{"name":"Department of Gynecology, National Cancer Institute, the National Clinical Research Center for Cancer, and Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref3","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.314"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3392619"},{"key":"ref10","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. BMVC","author":"Faghri"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3480949"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475634"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.226"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303754"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"ref23","first-page":"3887","article-title":"Accelerating large-scale inference with anisotropic vector quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3254530"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253548"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"ref31","first-page":"8242","article-title":"Revisiting training strategies and generalization performance in deep metric learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Roth"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_35"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1013"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3257193"},{"key":"ref35","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","volume-title":"Proc. NIPS","author":"Frome"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182426"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3394551"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01389"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11783"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00302"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00396"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_41"},{"key":"ref52","first-page":"30233","article-title":"Matryoshka representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kusupati"},{"key":"ref53","article-title":"ESE: Espresso sentence embeddings","volume-title":"arXiv:2402.14776v2","author":"Li","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_252"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_45"},{"key":"ref56","first-page":"9095","article-title":"Simultaneous similarity-based self-distillation for deep metric learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Roth"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref59","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Karpathy"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3307554"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref64","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266887"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123553"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611703"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3294980"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref74","article-title":"MIMIC-CXR database","author":"Johnson"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref76","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"issue":"1","key":"ref80","first-page":"3221","article-title":"Accelerating t-SNE using tree-based algorithms","volume":"15","author":"Van Der Maaten","year":"2014","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11154820\/10955419.pdf?arnumber=10955419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:49:38Z","timestamp":1757526578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":80,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3558996","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}