{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:04:40Z","timestamp":1784099080607,"version":"3.55.0"},"reference-count":88,"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\/501100001381","name":"National Research Foundation, Singapore, through the AI Singapore Program","doi-asserted-by":"publisher","award":["2021-08-006"],"award-info":[{"award-number":["2021-08-006"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore, through the AI Singapore Program","doi-asserted-by":"publisher","award":["AISG-100E-2023-121"],"award-info":[{"award-number":["AISG-100E-2023-121"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3531299","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T19:10:02Z","timestamp":1738005002000},"page":"785-800","source":"Crossref","is-referenced-by-count":7,"title":["Not Every Patch is Needed: Toward a More Efficient and Effective Backbone for Video-Based Person Re-Identification"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7309-3330","authenticated-orcid":false,"given":"Lanyun","family":"Zhu","sequence":"first","affiliation":[{"name":"Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Tampines, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0177-0157","authenticated-orcid":false,"given":"Tianrun","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deyi","family":"Ji","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8662-5818","authenticated-orcid":false,"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4365-4165","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing and Communications, Lancaster University, Lancaster, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00719"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01725"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00128"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_39"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01574"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00844"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547826"},{"key":"ref11","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01551"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01182"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01151"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018287"},{"key":"ref16","article-title":"SparseFormer: Sparse visual recognition via limited latent tokens","author":"Gao","year":"2023","journal-title":"arXiv:2304.03768"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_14"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00205"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_24"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00735"},{"key":"ref23","first-page":"14596","article-title":"Orthogonal transformer: An efficient vision transformer backbone with token orthogonalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Huang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3247159"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3341762"},{"key":"ref26","first-page":"2390","article-title":"Fast decoding in sequence models using discrete latent variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kaiser"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00406"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018618"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00292"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01814"},{"key":"ref32","first-page":"12934","article-title":"EfficientFormer: Vision transformers at MobileNet speed","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref33","article-title":"EVIT: Expediting vision transformers via token reorganizations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liang"},{"key":"ref34","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01882"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2038834"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02030"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2715499"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00435"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3296901"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3271353"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01313"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01946"},{"key":"ref44","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00599"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_25"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.148"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00818"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"ref51","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Rao"},{"key":"ref52","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00065"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3231103"},{"key":"ref56","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01181"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00208"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_32"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3305817"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00717"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3001693"},{"key":"ref66","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00297"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00335"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3362136"},{"key":"ref70","first-page":"33319","article-title":"ShiftAddViT: Mixture of multiplication primitives towards efficient vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"You"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01387"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28500"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01183"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01620"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2718188"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01042"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3355807"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00505"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"ref82","article-title":"Person re-identification: Past, present and future","author":"Zheng","year":"2016","journal-title":"arXiv:1610.02984"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00224"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00380"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.717"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00156"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2911396"},{"key":"ref88","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10852593.pdf?arnumber=10852593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T05:30:05Z","timestamp":1738301405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10852593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3531299","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}