{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:37:20Z","timestamp":1780601840872,"version":"3.54.1"},"reference-count":69,"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":["62101453"],"award-info":[{"award-number":["62101453"]}],"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":["62176198"],"award-info":[{"award-number":["62176198"]}],"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":["62476223"],"award-info":[{"award-number":["62476223"]}],"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":["62201467"],"award-info":[{"award-number":["62201467"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013064","name":"Key Research and Development Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2024GX-YBXM-135"],"award-info":[{"award-number":["2024GX-YBXM-135"]}],"id":[{"id":"10.13039\/501100013064","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Talent Fund of Xi\u2019an Association for Science and Technology","award":["959202313088"],"award-info":[{"award-number":["959202313088"]}]},{"name":"Innovation Capability Support Program of Shaanxi","award":["2024ZC-KJXX-043"],"award-info":[{"award-number":["2024ZC-KJXX-043"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3556531","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T22:20:40Z","timestamp":1744064440000},"page":"2450-2462","source":"Crossref","is-referenced-by-count":8,"title":["Prompt-Based Modality Alignment for Effective Multi-Modal Object Re-Identification"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3429-576X","authenticated-orcid":false,"given":"Shizhou","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5439-2749","authenticated-orcid":false,"given":"Wenlong","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4603-847X","authenticated-orcid":false,"given":"De","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Telecommunications Engineering, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6021-8261","authenticated-orcid":false,"given":"Yinghui","family":"Xing","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8710-5520","authenticated-orcid":false,"given":"Guoqiang","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9218-9132","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6796"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16467"},{"key":"ref3","article-title":"Multi-spectral vehicle re-identification with cross-directional consistency network and a high-quality benchmark","author":"Zheng","year":"2022","journal-title":"arXiv:2208.00632"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28388"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01620"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/s23094206"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref8","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP54964.2022.9778769"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20165"},{"key":"ref11","article-title":"GraFT: Gradual fusion transformer for multimodal re-identification","author":"Yin","year":"2023","journal-title":"arXiv:2310.16856"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521681"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25483"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26569"},{"key":"ref18","first-page":"1","article-title":"CLIP-ViP: Adapting pre-trained image-text model to video-language alignment","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xue"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285758"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3169693"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2977528"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240552"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01844"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3301856"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141267"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01886"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01160"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2958756"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_16"},{"key":"ref36","first-page":"1988","article-title":"Deep learning face representation by joint identification-verification","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.149"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00297"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.05.028"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00325"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00336"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01642"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25226"},{"key":"ref44","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":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237155"},{"key":"ref46","article-title":"Attend to the difference: Cross-modality person re-identification via contrastive correlation","author":"Zhang","year":"2019","journal-title":"arXiv:1910.11656"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP58490.2023.10248672"},{"key":"ref48","article-title":"UniCat: Crafting a stronger fusion baseline for multimodal re-identification","author":"Crawford","year":"2023","journal-title":"arXiv:2310.18812"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref53","article-title":"Dynamic enhancement network for partial multi-modality person re-identification","author":"Zheng","year":"2023","journal-title":"arXiv:2305.15762"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00380"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054775"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28398"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref61","article-title":"ImageNet-21K pretraining for the masses","author":"Ridnik","year":"2021","journal-title":"arXiv:2104.10972"},{"key":"ref62","article-title":"Automatic differentiation in PyTorch","author":"Paszke","year":"2017"},{"key":"ref63","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2935128"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928294"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00225"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"issue":"86","key":"ref69","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10955143.pdf?arnumber=10955143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T18:00:06Z","timestamp":1746468006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955143\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3556531","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}