{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T06:08:43Z","timestamp":1781330923855,"version":"3.54.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["61925201"],"award-info":[{"award-number":["61925201"]}],"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":["62132001"],"award-info":[{"award-number":["62132001"]}],"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":["62373043"],"award-info":[{"award-number":["62373043"]}],"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":["62432001"],"award-info":[{"award-number":["62432001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3459788","type":"journal-article","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T18:05:31Z","timestamp":1726682731000},"page":"5312-5326","source":"Crossref","is-referenced-by-count":17,"title":["SIM-OFE: Structure Information Mining and Object-Aware Feature Enhancement for Fine-Grained Visual Categorization"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2639-9035","authenticated-orcid":false,"given":"Hongbo","family":"Sun","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8502-5685","authenticated-orcid":false,"given":"Xiangteng","family":"He","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1553-5441","authenticated-orcid":false,"given":"Jinglin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7658-3845","authenticated-orcid":false,"given":"Yuxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref2","article-title":"The caltech-UCSD Birds-200-2011 dataset","author":"Wah","year":"2011"},{"issue":"1","key":"ref3","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","volume":"2","author":"Khosla"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2834480"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01179"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16384"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055617"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3135477"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263870"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298685"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3330076"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612403"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16176"},{"key":"ref18","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475561"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248791"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3244340"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548308"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01176-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00977"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6912"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2996736"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.128"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref32","article-title":"Bird species categorization using pose normalized deep convolutional nets","author":"Branson","year":"2014","journal-title":"arXiv:1406.2952"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00107"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355461"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01483"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205215"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00725"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01873-z"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3340225"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"ref42","first-page":"1","article-title":"Learning deep bilinear transformation for fine-grained image representation","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Zheng"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3492221"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/87"},{"key":"ref45","first-page":"1","article-title":"Learning to parameterize visual attributes for open-set fine-grained retrieval","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Wang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181492"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3273455"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref50","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref51","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ouyang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3238548"},{"key":"ref57","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310076"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref61","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01131"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00066"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3126490"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109547"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref71","first-page":"1","article-title":"Maximum-entropy fine grained classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Dubey"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3020227"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_4"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10684043.pdf?arnumber=10684043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T04:14:08Z","timestamp":1727583248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10684043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3459788","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}