{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:56:57Z","timestamp":1777568217547,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62472390"],"award-info":[{"award-number":["62472390"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023MF033"],"award-info":[{"award-number":["ZR2023MF033"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFC1408405"],"award-info":[{"award-number":["2019YFC1408405"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3618279","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:39:41Z","timestamp":1759772381000},"page":"3679-3692","source":"Crossref","is-referenced-by-count":2,"title":["LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition"],"prefix":"10.1109","volume":"36","author":[{"given":"Jialu","family":"Shi","sequence":"first","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2830-8301","authenticated-orcid":false,"given":"Zhiqiang","family":"Wei","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4952-7666","authenticated-orcid":false,"given":"Jie","family":"Nie","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4087-3677","authenticated-orcid":false,"given":"Lei","family":"Huang","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248791"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298685"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01179"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3144186"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.47"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275382"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01434"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_30"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/200"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1282"},{"key":"ref15","first-page":"852","article-title":"TransFG: A transformer architecture for fine-grained recognition","volume-title":"Proc. AAAI Conf. Artif. Intell. (AAAI)","author":"Ju"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25860"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747591"},{"key":"ref20","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref22","article-title":"The caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref26","article-title":"Self-supervised learning with Swin transformers","author":"Xie","year":"2021","journal-title":"arXiv:2105.04553"},{"key":"ref27","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","author":"Bardes","year":"2021","journal-title":"arXiv:2105.04906"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref30","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref33","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref34","article-title":"IBOT: Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhou"},{"key":"ref35","article-title":"Efficient self-supervised vision transformers for representation learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref36","article-title":"Patch-level contrastive learning via positional query for visual pre-training","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3415112"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00212"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02178"},{"key":"ref41","first-page":"40676","article-title":"Siamese masked autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Gupta"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3126490"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3244340"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3325001"},{"key":"ref45","article-title":"Fine-grained visual classification with high-temperature refinement and background suppression","author":"Chou","year":"2023","journal-title":"arXiv:2303.06442"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3236636"},{"key":"ref47","article-title":"Align yourself: Self-supervised pre-training for fine-grained recognition via saliency alignment","author":"Wu","year":"2021","journal-title":"arXiv:2106.15788"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17312"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01405"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01556"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01096"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref53","article-title":"Representation learning with contrastive predictive coding","author":"Van Den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_26"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11194183.pdf?arnumber=11194183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:53Z","timestamp":1773086453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11194183\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":56,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3618279","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}