{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T15:58:35Z","timestamp":1784563115991,"version":"3.55.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62371208"],"award-info":[{"award-number":["62371208"]}],"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":["62371209"],"award-info":[{"award-number":["62371209"]}],"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":["2015M581720"],"award-info":[{"award-number":["2015M581720"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2016M600360"],"award-info":[{"award-number":["2016M600360"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3410129","type":"journal-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T17:56:11Z","timestamp":1717610171000},"page":"10678-10691","source":"Crossref","is-referenced-by-count":25,"title":["Learning Semantic Polymorphic Mapping for Text-Based Person Retrieval"],"prefix":"10.1109","volume":"26","author":[{"given":"Jiayi","family":"Li","sequence":"first","affiliation":[{"name":"Engineering Research Center of Intelligent Technology for Healthcare, Ministry of Education, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3826-6405","authenticated-orcid":false,"given":"Min","family":"Jiang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Technology for Healthcare, Ministry of Education, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2551-4748","authenticated-orcid":false,"given":"Jun","family":"Kong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1142-619X","authenticated-orcid":false,"given":"Xuefeng","family":"Tao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7581-4963","authenticated-orcid":false,"given":"Xi","family":"Luo","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Technology for Healthcare, Ministry of Education, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746846"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3225754"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251104"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972168"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3220115"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3179441"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3135274"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3024822"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3289753"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/148"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108891"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref24","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205216"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref27","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":"ref28","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068825"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref39","first-page":"337","article-title":"Text-based person search with limited data","volume-title":"Proc. 32nd Brit. Mach. Vis. Conf.","author":"Han","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3327924"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02226"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_40"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268446"},{"key":"ref47","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":"ref48","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"Proc. 10th Int. Conf. Learn. Representations"},{"key":"ref49","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Gu","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928126"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413821"},{"key":"ref52","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bao","year":"2022"},{"key":"ref53","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475703"},{"key":"ref56","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"issue":"1","key":"ref59","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3310118"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054775"},{"key":"ref64","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10384483\/10549861.pdf?arnumber=10549861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:25:26Z","timestamp":1732667126000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10549861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3410129","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}