{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:42:49Z","timestamp":1775324569960,"version":"3.50.1"},"reference-count":58,"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":["U20A20183"],"award-info":[{"award-number":["U20A20183"]}],"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":["62021001"],"award-info":[{"award-number":["62021001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GPU cluster"},{"name":"MCC Lab"},{"DOI":"10.13039\/501100009076","name":"University of Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009076","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.2023.3321504","type":"journal-article","created":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T19:13:36Z","timestamp":1696878816000},"page":"4281-4293","source":"Crossref","is-referenced-by-count":15,"title":["Multi-Granularity Matching Transformer for Text-Based Person Search"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2812-688X","authenticated-orcid":false,"given":"Liping","family":"Bao","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6916-3009","authenticated-orcid":false,"given":"Longhui","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Science, University of Science and Technology of China and Huawei Cloud, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8406-085X","authenticated-orcid":false,"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4831-9451","authenticated-orcid":false,"given":"Lingxi","family":"Xie","sequence":"additional","affiliation":[{"name":"Huawei Cloud, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Cloud, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2958756"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01180"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_14"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413864"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972168"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350991"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref18","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3073718"},{"key":"ref26","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3159171"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2870522"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050082"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3092579"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2920905"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.427"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.357"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_6"},{"key":"ref35","first-page":"1","article-title":"Vl-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"ref37","article-title":"Contextual non-local alignment over full-scale representation for text-based person search","author":"Gao","year":"2021"},{"key":"ref38","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":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref40","first-page":"1","article-title":"Text-based person search with limited data","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Han","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref42","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3203630"},{"key":"ref48","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Henaff","year":"2020"},{"key":"ref49","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Khosla","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref52","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413895"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/148"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10274673.pdf?arnumber=10274673","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:56:42Z","timestamp":1725904602000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10274673\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3321504","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}