{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T15:57:14Z","timestamp":1774627034008,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["U20B2064"],"award-info":[{"award-number":["U20B2064"]}],"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":["U21B2043"],"award-info":[{"award-number":["U21B2043"]}],"id":[{"id":"10.13039\/501100001809","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":[[2024,8]]},"DOI":"10.1109\/tcsvt.2024.3370731","type":"journal-article","created":{"date-parts":[[2024,2,27]],"date-time":"2024-02-27T19:30:42Z","timestamp":1709062242000},"page":"7135-7148","source":"Crossref","is-referenced-by-count":31,"title":["Learning Contrastive Self-Distillation for Ultra-Fine-Grained Visual Categorization Targeting Limited Samples"],"prefix":"10.1109","volume":"34","author":[{"given":"Ziye","family":"Fang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4522-0096","authenticated-orcid":false,"given":"Xin","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6973-8121","authenticated-orcid":false,"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3144186"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263870"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108769"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248791"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3227737"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3236636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108067"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108691"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6968"},{"key":"ref12","article-title":"ViT-FOD: A vision transformer based fine-grained object discriminator","author":"Zhang","year":"2022","journal-title":"arXiv:2203.12816"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3238642"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109131"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/504"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413884"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475561"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108792"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00621"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA52665.2021.9647081"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.01.029"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248782"},{"key":"ref26","article-title":"Triplet contrastive representation learning for unsupervised vehicle re-identification","author":"Shen","year":"2023","journal-title":"arXiv:2301.09498"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3240195"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref29","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01389"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00650"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015565"},{"key":"ref36","first-page":"1602","article-title":"Born-again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Furlanello"},{"key":"ref37","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Li"},{"key":"ref38","first-page":"1","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00149"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref43","article-title":"The plant pathology 2020 challenge dataset to classify foliar disease of apples","author":"Thapa","year":"2020","journal-title":"arXiv:2004.11958"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00899"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref46","article-title":"The caltech-UCSD birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref49","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref51","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref53","article-title":"Improved regularization of convolutional neural networks with cutout","author":"Devries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00232"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref57","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.","author":"Dosovitskiy"},{"key":"ref58","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Touvron"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548308"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055617"},{"key":"ref62","article-title":"Feature fusion vision transformer for fine-grained visual categorization","author":"Wang","year":"2021","journal-title":"arXiv:2107.02341"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3244340"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109547"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2648498"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2751960"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2928494"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref69","article-title":"A continual development methodology for large-scale multitask dynamic ML systems","author":"Gesmundo","year":"2022","journal-title":"arXiv:2209.07326"},{"issue":"11","key":"ref70","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00516"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10445701.pdf?arnumber=10445701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:12:28Z","timestamp":1723525948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445701\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":73,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3370731","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}