{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:11:04Z","timestamp":1773137464652,"version":"3.50.1"},"reference-count":117,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62273301"],"award-info":[{"award-number":["62273301"]}],"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":["62273302"],"award-info":[{"award-number":["62273302"]}],"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":["62302140"],"award-info":[{"award-number":["62302140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2024HGTB0261"],"award-info":[{"award-number":["JZ2024HGTB0261"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3645621","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:34:14Z","timestamp":1766082854000},"page":"1820-1832","source":"Crossref","is-referenced-by-count":0,"title":["LEViT: Locally Enhanced Vision Transformer for Efficient Object Re-Identification"],"prefix":"10.1109","volume":"28","author":[{"given":"Shenqi","family":"Lai","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Telecommunications, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyuan","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computer Vision, Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8395-1463","authenticated-orcid":false,"given":"Junshi","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Vision, Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8142-0642","authenticated-orcid":false,"given":"Haifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9817-4065","authenticated-orcid":false,"given":"Deng","family":"Cai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Computer-Aided Design (CAD) and Computer Graphics (CG), Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3173-6307","authenticated-orcid":false,"given":"Xueming","family":"Qian","sequence":"additional","affiliation":[{"name":"Key Laboratory for Intelligent Networks and Network Security, Ministry of Education, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6596-8117","authenticated-orcid":false,"given":"Yaxiong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref3","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054775"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240552"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00048"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207895"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475202"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00461"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3301856"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_25"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00117"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.427"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00076"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00431"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref25","first-page":"21125","article-title":"Improving visual quality of image synthesis by a token-based generator with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zeng","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00292"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01813-x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00539"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01683"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01587"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0670"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_18"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25180"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25273"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28312"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref45","first-page":"24898","article-title":"IA-RED$^{2}$: Interpretability-aware redundancy reduction for vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00380"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027589"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141267"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3247159"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01886"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3339167"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00471"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20155"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01036"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3379908"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00623"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00412"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00713"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_22"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413541"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3014488"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029299"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3410684"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3238642"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3257873"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.389"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.405"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7553002"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.238"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00516"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00655"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00809"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01437"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00660"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_35"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01185"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01906"},{"key":"ref85","first-page":"5462","article-title":"Generalized sum pooling for metric learning","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Grbz","year":"2023"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01014"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref88","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413896"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00110"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00758"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3061265"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3135013"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3175601"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3453008"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3352418"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3378453"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01506"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3246999"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110698"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108899"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3088639"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2958756"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01844"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110455"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110437"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3225285"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"ref115","article-title":"Efficient modulation for vision networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2024"},{"key":"ref116","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11303951.pdf?arnumber=11303951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:59:17Z","timestamp":1773086357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11303951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":117,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3645621","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}