{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T19:23:00Z","timestamp":1769541780140,"version":"3.49.0"},"reference-count":73,"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":["62225208"],"award-info":[{"award-number":["62225208"]}],"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":["62450046"],"award-info":[{"award-number":["62450046"]}],"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":["62521007"],"award-info":[{"award-number":["62521007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chinese Academy of Sciences (CAS) Project for Young Scientists in Basic Research","award":["YSBR-117"],"award-info":[{"award-number":["YSBR-117"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3652371","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:41:45Z","timestamp":1768423305000},"page":"786-799","source":"Crossref","is-referenced-by-count":0,"title":["EinsPT: Efficient Instance-Aware Pre-Training of Vision Foundation Models"],"prefix":"10.1109","volume":"35","author":[{"given":"Zhaozhi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5103-3748","authenticated-orcid":false,"given":"Yunjie","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4831-9451","authenticated-orcid":false,"given":"Lingxi","family":"Xie","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1215-6259","authenticated-orcid":false,"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref5","first-page":"611","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref14","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. 26th Annu. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref17","first-page":"8344","article-title":"Hivit: A simpler and more efficient design of hierarchical vision transformer","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01785"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref26","first-page":"2245","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. ICLR","author":"Gidaris"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111386"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref30","article-title":"Semantic-aware generation for self-supervised visual representation learning","author":"Tian","year":"2021","journal-title":"arXiv:2111.13163"},{"key":"ref31","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","volume":"1","author":"Chen"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref34","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. NeurIPS","author":"Caron"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref36","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref37","article-title":"Context autoencoder for self-supervised representation learning","author":"Chen","year":"2022","journal-title":"arXiv:2202.03026"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104295"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3608643"},{"key":"ref40","article-title":"BEiT v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022","journal-title":"arXiv:2208.06366"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01509"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"ref45","first-page":"894","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref46","first-page":"8587","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref47","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref48","article-title":"Revisiting DETR pre-training for object detection","author":"Ma","year":"2023","journal-title":"arXiv:2308.01300"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00120"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref51","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. NeurIPS","author":"Dai"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32940"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"ref56","article-title":"Focal self-attention for local\u2013global interactions in vision transformers","author":"Yang","year":"2021","journal-title":"arXiv:2107.00641"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref59","first-page":"4061","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref60","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00628"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00781"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00095"},{"key":"ref65","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02204-6"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref68","first-page":"1071","article-title":"MIM-refiner: A contrastive learning boost from intermediate pre-trained masked image modeling representations","volume-title":"Proc. ICLR","author":"Alkin"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02356"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref72","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref73","first-page":"9448","article-title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","volume-title":"Proc. NeurIPS","volume":"32","author":"Barbu"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11353396.pdf?arnumber=11353396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:07:15Z","timestamp":1769494035000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353396\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3652371","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}