{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T13:25:24Z","timestamp":1774445124270,"version":"3.50.1"},"reference-count":121,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea government","award":["NRF2021R1A2C2006703"],"award-info":[{"award-number":["NRF2021R1A2C2006703"]}]},{"name":"Yonsei Signature Research Cluster Program of 2024","award":["2024-22-0161"],"award-info":[{"award-number":["2024-22-0161"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tpami.2024.3461778","type":"journal-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T17:55:32Z","timestamp":1726509332000},"page":"99-115","source":"Crossref","is-referenced-by-count":5,"title":["Prototype-Guided Attention Distillation for Discriminative Person Search"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9002-2726","authenticated-orcid":false,"given":"Hanjae","family":"Kim","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyoung","family":"Lee","sequence":"additional","affiliation":[{"name":"NAVER AI Lab, Seongnam, Gyeonggi, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3715-0331","authenticated-orcid":false,"given":"Kwanghoon","family":"Sohn","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_45"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.27"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.360"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00090"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01263"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00712"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.140"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref10","article-title":"In defense of the triplet loss for person re-identification","author":"Hermans","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"ref12","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Gutmann"},{"key":"ref13","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.47"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00483"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00760"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00924"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00480"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_33"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00243"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00588"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.57"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00226"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00129"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00686"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00166"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910414"},{"key":"ref30","first-page":"28 104","article-title":"Unsupervised part discovery from contrastive reconstruction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Choudhury"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654965"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.357"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00991"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-00929-3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_21"},{"issue":"3","key":"ref38","first-page":"1","article-title":"Beyond the parts: Learning coarse-to-fine adaptive alignment representation for person search","volume":"19","author":"Huang","year":"2023","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16297"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3221079"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28329"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110047"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240552"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_36"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00076"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00325"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00730"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00148"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00292"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_23"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref60","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.103"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01176"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277389"},{"key":"ref64","article-title":"Spectral normalization for generative adversarial networks","author":"Miyato","year":"2018"},{"key":"ref65","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02325"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref70","article-title":"Knowledge distillation for end-to-end person search","author":"Munjal","year":"2019"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16454"},{"key":"ref72","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Komodakis"},{"key":"ref73","first-page":"5776","article-title":"MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref74","article-title":"Attention distillation: Self-supervised vision transformer students need more guidance","author":"Wang","year":"2022"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01142"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00427"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01153"},{"key":"ref78","article-title":"Revisiting self-distillation","author":"Pham","year":"2022"},{"key":"ref79","first-page":"16 797","article-title":"Comprehensive attention self-distillation for weakly-supervised object detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref82","first-page":"3351","article-title":"Self-distillation amplifies regularization in hilbert space","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mobahi"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01036"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01032"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref89","article-title":"Residual non-local attention networks for image restoration","author":"Zhang","year":"2019"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref91","article-title":"How much position information do convolutional neural networks encode?","author":"Islam","year":"2020"},{"key":"ref92","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00173"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00266"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01197"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.10.028"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.61"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_6"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00226"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6623"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00291"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00096"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref106","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00225"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.149"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref112","first-page":"12 084","article-title":"Improved feature distillation via projector ensemble","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00888"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"ref115","article-title":"Unsupervised part mining for fine-grained image classification","author":"Zhang","year":"2019"},{"key":"ref116","article-title":"Part-based face recognition with vision transformers","author":"Sun","year":"2022"},{"key":"ref117","article-title":"MARS: Paying more attention to visual attributes for text-based person search","author":"Ergasti","year":"2024"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3329220"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"ref120","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref121","first-page":"12 888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10777928\/10681282.pdf?arnumber=10681282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T19:33:28Z","timestamp":1743795208000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10681282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":121,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3461778","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}