{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T17:50:07Z","timestamp":1773942607482,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["U20B2052"],"award-info":[{"award-number":["U20B2052"]}],"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":["61936011"],"award-info":[{"award-number":["61936011"]}],"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":["62236006"],"award-info":[{"award-number":["62236006"]}],"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":["62402013"],"award-info":[{"award-number":["62402013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M730056"],"award-info":[{"award-number":["2023M730056"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Okawa Foundation Research Award"},{"name":"Ant Group Research Fund"},{"name":"Kunpeng&Ascend Center of Excellence, Peking University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3543066","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T13:39:30Z","timestamp":1740404370000},"page":"5009-5022","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Modal Reference Learning for Fine-Grained Text-to-Image Retrieval"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1533-2651","authenticated-orcid":false,"given":"Zehong","family":"Ma","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6853-3298","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2870-1178","authenticated-orcid":false,"given":"Wei","family":"Zeng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}]},{"given":"Limin","family":"Su","sequence":"additional","affiliation":[{"name":"Beijing Union University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9053-9314","authenticated-orcid":false,"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378461"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050082"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3174768"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01675"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref11","author":"Gao","year":"2021","journal-title":"Contextual non-local alignment over full-scale representation for text-based person search"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463652"},{"key":"ref13","volume-title":"Semantically Self-Aligned Network for Text-To-Image Part-Aware Person Re-Identification","author":"Ding","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3280734"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3024822"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01642"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475184"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3337653"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612427"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.47"},{"key":"ref30","first-page":"513","article-title":"Neighbourhood component analysis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Goldberger","year":"2004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_27"},{"key":"ref32","first-page":"17792","article-title":"Fewer is more: A deep graph metric learning perspective using fewer proxies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhu","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00330"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00052"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00727"},{"key":"ref36","article-title":"CLIP-ViP: Adapting pre-trained image-text model to video-language alignment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xue","year":"2023"},{"key":"ref37","first-page":"25461","article-title":"Intra-modal proxy learning for zero-shot visual categorization with clip","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Qian","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00081"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00321"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3163451"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3052354"},{"key":"ref43","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":"ref44","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.10"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref47","volume-title":"Representation Learning with Contrastive Predictive Coding","author":"Oord","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.09.024"},{"key":"ref49","volume-title":"ClipCap: CLIP Prefix For Image Captioning","author":"Mokady","year":"2021"},{"issue":"8","key":"ref50","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972168"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3225754"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612009"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321504"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3344354"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref60","volume-title":"The CALTECH-UCSD Birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88007-1_38"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108891"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref69","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00190"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10902097.pdf?arnumber=10902097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T18:10:28Z","timestamp":1756404628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10902097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3543066","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}