{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:54:24Z","timestamp":1777888464043,"version":"3.51.4"},"reference-count":79,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006465","name":"Korea Creative Content Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006465","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003561","name":"Ministry of Culture, Sports and Tourism","doi-asserted-by":"publisher","award":["RS-2024-00352578"],"award-info":[{"award-number":["RS-2024-00352578"]}],"id":[{"id":"10.13039\/501100003561","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002551","name":"Seoul National University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002551","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01888","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20301-20312","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Prior Knowledge of Diffusion Model for Person Search"],"prefix":"10.1109","author":[{"given":"Giyeol","family":"Kim","sequence":"first","affiliation":[{"name":"Chung-Ang University,GSAIM"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sooyoung","family":"Yang","sequence":"additional","affiliation":[{"name":"Seoul National University,IPAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihyong","family":"Oh","sequence":"additional","affiliation":[{"name":"Chung-Ang University,GSAIM"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Myungjoo","family":"Kang","sequence":"additional","affiliation":[{"name":"Seoul National University,IPAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanho","family":"Eom","sequence":"additional","affiliation":[{"name":"Chung-Ang University,GSAIM"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The eurocity persons dataset: A novel benchmark for object detection","author":"Braun","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076733"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00924"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_45"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01263"},{"key":"ref6","article-title":"Your diffusion model is secretly a certifiably robust classifier","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01445"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00291"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00266"},{"key":"ref12","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref13","article-title":"Learning disentangled representation for robust person re-identification","volume":"32","author":"Eom","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01451"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01358"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00991"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16241"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3221079"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01474"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00173"},{"key":"ref24","article-title":"Intriguing properties of generative classifiers","author":"Jaini","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3524733"},{"key":"ref26","article-title":"Scene-adaptive person search via bilateral modulations","author":"Jiang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00483"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01592"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.27"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16297"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298832"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00533"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref40","article-title":"Diffusion hyperfeatures: Searching through time and space for semantic correspondence","volume":"36","author":"Luo","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","article-title":"Diffusionseg: Adapting diffusion towards unsupervised object discovery","author":"Ma","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/0098-3004(93)90090-R"},{"key":"ref43","article-title":"Not all diffusion model activations have been evaluated as discriminative features","author":"Meng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","first-page":"253","article-title":"Do text-free diffusion models learn discriminative visual representations?","volume-title":"European Conference on Computer Vision","author":"Mukhopadhyay"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00090"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3359"},{"key":"ref47","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00507"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00384"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref51","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"issue":"2","key":"ref52","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref53","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref58","article-title":"Crowdhuman: A benchmark for detecting human in a crowd","author":"Shao","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref59","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.427"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00341"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28329"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240552"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548267"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00016"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.10.028"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.360"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref71","volume-title":"Denoiserep: Denoising model for representation learning","author":"Xu","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00760"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00712"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1973"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00584"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.357"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.357"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00686"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444065.pdf?arnumber=11444065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:45:40Z","timestamp":1777610740000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444065\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01888","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}