{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:55:28Z","timestamp":1782312928783,"version":"3.54.5"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["62222203"],"award-info":[{"award-number":["62222203"]}],"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":["62072080"],"award-info":[{"award-number":["62072080"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"New Cornerstone Science Foundation through the XPLORER PRIZE"},{"DOI":"10.13039\/501100019065","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2023-XT00-00001-GX"],"award-info":[{"award-number":["2023-XT00-00001-GX"]}],"id":[{"id":"10.13039\/501100019065","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":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3487908","type":"journal-article","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T13:36:16Z","timestamp":1730208976000},"page":"2881-2893","source":"Crossref","is-referenced-by-count":8,"title":["Cross-Modal Uncertainty Modeling With Diffusion-Based Refinement for Text-Based Person Retrieval"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6340-012X","authenticated-orcid":false,"given":"Shenshen","family":"Li","sequence":"first","affiliation":[{"name":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-3123","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"He","sequence":"additional","affiliation":[{"name":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7303-3231","authenticated-orcid":false,"given":"Fumin","family":"Shen","sequence":"additional","affiliation":[{"name":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng","family":"Tao Shen","sequence":"additional","affiliation":[{"name":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref2","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021","journal-title":"arXiv:2107.12666"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01099"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612244"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref8","article-title":"CLIP-driven fine-grained text-image person re-identification","author":"Yan","year":"2022","journal-title":"arXiv:2210.10276"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475248"},{"key":"ref13","article-title":"Word representations via Gaussian embedding","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Vilnis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"ref16","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306738"},{"key":"ref20","article-title":"OH-former: Omni-relational high-order transformer for person re-identification","author":"Chen","year":"2021","journal-title":"arXiv:2109.11159"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218738"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045530"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3262832"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3392831"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1151"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382633"},{"key":"ref34","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref35","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref36","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume-title":"Proc. NeurIPS","author":"Austin"},{"key":"ref37","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref39","first-page":"1","article-title":"Diffusion-LM improves controllable text generation","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3516033"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.5.1.1"},{"key":"ref42","first-page":"5660","article-title":"Learning from uncertain curves: The 2-Wasserstein metric for Gaussian processes","volume-title":"Proc. NeurIPS","author":"Mallasto"},{"key":"ref43","article-title":"Analog bits: Generating discrete data using diffusion models with self-conditioning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611832"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01026"},{"key":"ref48","article-title":"Exploiting the textual potential from vision-language pre-training for text-based person search","author":"Wang","year":"2023","journal-title":"arXiv:2303.04497"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00295"},{"key":"ref50","article-title":"An empirical study of CLIP for text-based person search","author":"Cao","year":"2023","journal-title":"arXiv:2308.10045"},{"key":"ref51","article-title":"Noisy-correspondence learning for text-to-image person re-identification","author":"Qin","year":"2023","journal-title":"arXiv:2308.09911"},{"key":"ref52","article-title":"UFineBench: Towards text-based person retrieval with ultra-fine granularity","author":"Zuo","year":"2023","journal-title":"arXiv:2312.03441"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3310118"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3251104"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10737387.pdf?arnumber=10737387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:46Z","timestamp":1767638446000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10737387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":58,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3487908","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}