{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T11:05:21Z","timestamp":1785927921488,"version":"3.56.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["61860206004"],"award-info":[{"award-number":["61860206004"]}],"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":["72071001"],"award-info":[{"award-number":["72071001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2108085Y23"],"award-info":[{"award-number":["2108085Y23"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation for the Higher Education Institutions of Anhui Province","award":["KJ2021A0038"],"award-info":[{"award-number":["KJ2021A0038"]}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2020-013"],"award-info":[{"award-number":["GXXT-2020-013"]}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2022-032"],"award-info":[{"award-number":["GXXT-2022-032"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3244340","type":"journal-article","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T21:09:34Z","timestamp":1676581774000},"page":"9015-9028","source":"Crossref","is-referenced-by-count":152,"title":["Fine-Grained Visual Classification via Internal Ensemble Learning Transformer"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9020-2006","authenticated-orcid":false,"given":"Qin","family":"Xu","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6438-1506","authenticated-orcid":false,"given":"Jiahui","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-1596","authenticated-orcid":false,"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[{"name":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1414-3307","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05148-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.envpol.2018.06.016"},{"key":"ref3","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref5","first-page":"806","article-title":"Novel dataset for fine-grained image categorization","volume-title":"Proc. 1st Workshop Fine-Grained Vis. Categorization IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Khosla","year":"2011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.132"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3135477"},{"key":"ref15","article-title":"Re-rank coarse classification with local region enhanced features for fine-grained image recognition","author":"Yang","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2933510"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6712"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3112768"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723400"},{"key":"ref26","first-page":"4277","article-title":"Learning deep bilinear transformation for fine-grained image representation","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Zheng","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6882"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01483"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2932058"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3209666"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3227737"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475561"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747591"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.037"},{"key":"ref40","article-title":"Feature fusion vision transformer for fine-grained visual categorization","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Wang","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3126490"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3214431"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3181439"},{"key":"ref46","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref47","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00342"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1249"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3492221"},{"key":"ref52","first-page":"148","article-title":"Experiments with a new boosting algorithm","volume-title":"Proc. 13th Int. Conf. Int. Conf. Mach. Learn.","author":"Freund","year":"1996"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16176"},{"key":"ref54","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref55","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref56","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref58","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00200"},{"key":"ref60","first-page":"393","article-title":"Investigation on the effect of a Gaussian Blur in image filtering and segmentation","volume-title":"Proc. ELMAR","author":"Gedraite","year":"2011"},{"key":"ref61","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126668"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00204"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00432"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33676-9_5"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"ref68","first-page":"8250","article-title":"Fixing the train-test resolution discrepancy","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Touvron","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.136"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.36"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2973812"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00091"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10042971.pdf?arnumber=10042971","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:04:16Z","timestamp":1703030656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10042971\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3244340","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}