{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T02:38:49Z","timestamp":1784169529112,"version":"3.55.0"},"reference-count":214,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021YFA1001100"],"award-info":[{"award-number":["2021YFA1001100"]}]},{"name":"Natural Science Foundation of Jiangsu Province of China","award":["BK20210340"],"award-info":[{"award-number":["BK20210340"]}]},{"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":["61772256"],"award-info":[{"award-number":["61772256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["30920041111"],"award-info":[{"award-number":["30920041111"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpami.2021.3126648","type":"journal-article","created":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T20:42:40Z","timestamp":1636490560000},"page":"8927-8948","source":"Crossref","is-referenced-by-count":407,"title":["Fine-Grained Image Analysis With Deep Learning: A Survey"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8200-1845","authenticated-orcid":false,"given":"Xiu-Shen","family":"Wei","sequence":"first","affiliation":[{"name":"PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5908-3275","authenticated-orcid":false,"given":"Yi-Zhe","family":"Song","sequence":"additional","affiliation":[{"name":"University of Surrey, Guildford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5787-5073","authenticated-orcid":false,"given":"Oisin Mac","family":"Aodha","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2085-7568","authenticated-orcid":false,"given":"Jianxin","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, 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":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0388-5217","authenticated-orcid":false,"given":"Serge","family":"Belongie","sequence":"additional","affiliation":[{"name":"University of Copenhagen, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/171"},{"key":"ref172","year":"0"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.10.006"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1108\/PIJPSM-11-2016-0158"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_46"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.132"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01036"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_19"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00432"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01078"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11202"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00548"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2688133"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.002"},{"key":"ref30","first-page":"4023","article-title":"Multi-modal reasoning graph for scene-text based fine-grained image classification and retrieval","author":"mafla","year":"2020","journal-title":"Proc IEEE Workshop Appl Comput Vis"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20890-5_37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_25"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref34","article-title":"Deep learning for person re-identification: A survey and outlook","author":"ye","year":"2020"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298641"},{"key":"ref180","first-page":"1","article-title":"Cross-modal hierarchical modelling for fine-grained sketch based image retrieval","author":"sain","year":"2020","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref184","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.45"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.46"},{"key":"ref189","article-title":"Measuring dataset granularity","author":"cui","year":"2019"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_41"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_42"},{"key":"ref186","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019291"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00980"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093373"},{"key":"ref20","article-title":"iNaturalist.","year":"0"},{"key":"ref22","article-title":"Humpback Whale Identification.","year":"0"},{"key":"ref21","article-title":"Nature Conservancy Fisheries Monitoring.","year":"0"},{"key":"ref24","year":"0"},{"key":"ref23","year":"0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP.2018.8652307"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-017-1053-3"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.127"},{"key":"ref51","first-page":"1","article-title":"Fine-grained sketch-based image retrieval by matching deformable part models","author":"li","year":"2014","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2637331"},{"key":"ref153","first-page":"241","article-title":"Fine-grained visual categorization using meta-learning optimization with sample selection of auxiliary data","author":"zhang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6973"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855449"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.290"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00749"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_19"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.117"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00588"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2924811"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298880"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.775"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350974"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00077"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2745106"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.592"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925954"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.93"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.081"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439285"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.130"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11345"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.3233\/SW-140134"},{"key":"ref163","article-title":"Meta-learning in neural networks: A survey","author":"hospedales","year":"2020"},{"key":"ref162","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.311"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2996736"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.109"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01269"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_19"},{"key":"ref5","article-title":"RPC: A large-scale retail product checkout dataset","author":"wei","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01259-0"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/87"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.03.001"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12295"},{"key":"ref9","year":"2019"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/145"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.66"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref48","article-title":"Products-10K: A large-scale product recognition dataset","author":"bai","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref42","first-page":"806","article-title":"Novel dataset for fine-grained image categorization","author":"khosla","year":"2011","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit Workshop Fine-Grained Vis Categorization"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.259"},{"key":"ref44","article-title":"Fine-grained visual classification of aircraft","author":"maji","year":"2013"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11223"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.688"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2531289"},{"key":"ref76","first-page":"842","article-title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299107"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6912"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.136"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.128"},{"key":"ref60","first-page":"9596","article-title":"Presence-only geographical priors for fine-grained image classification","author":"macaodha","year":"2019","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301273"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00033"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00749"},{"key":"ref64","first-page":"1","article-title":"Bird species categorization using pose normalized deep convolutional nets","author":"branson","year":"2014","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298775"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.132"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.129"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700808"},{"key":"ref198","first-page":"3063","article-title":"Meta-reinforced synthetic data for one-shot fine-grained visual recognition","author":"tsutsui","year":"2019","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01436"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref194","article-title":"Synthetic data for deep learning","author":"nikolenko","year":"2019"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048623"},{"key":"ref196","article-title":"When does contrastive visual representation learning work?","author":"cole","year":"2021"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref190","article-title":"Your “flamingo","author":"chang","year":"2020"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00977"},{"key":"ref191","first-page":"1","article-title":"Long-tailed recognition by routing diverse distribution-aware experts","author":"wang","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01176-2"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350989"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.131"},{"key":"ref90","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"ref99","first-page":"2730","article-title":"G$^2$2DeNet: Global Gaussian distribution embedding network and its application to visual recognition","author":"wang","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.325"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00436"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2921876"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_38"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00105"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.63"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093306"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_12"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2971105"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699960"},{"key":"ref202","first-page":"1711","article-title":"Feature learning based deep supervised hashing with pairwise labels","author":"li","year":"2016","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.151"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00923"},{"key":"ref205","first-page":"2962","article-title":"Efficient and robust automated machine learning","author":"feurer","year":"2015","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref206","article-title":"Neural architecture search: A survey","author":"elsken","year":"2018"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_9"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"ref127","first-page":"1243","article-title":"Learning to combine foveal glimpses with a third-order Boltzmann machine","author":"larochelle","year":"2010","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1038\/nrn755"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2834480"},{"key":"ref130","first-page":"737","article-title":"Signature verification using a “siamese","author":"bromley","year":"1993","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2099"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126474"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/103"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299007"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref138","first-page":"92","article-title":"Revisiting the fisher vector for fine-grained classification","author":"gosselin","year":"2015","journal-title":"Pattern Recognit Lett"},{"key":"ref137","article-title":"Deep spatial pyramid: The devil is once again in the details","author":"gao","year":"2015"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.519"},{"key":"ref140","first-page":"2582","article-title":"Deep CNNs meet global covariance pooling: Better representation and generalization","volume":"43","author":"wang","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723400"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487591"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.229"},{"key":"ref2","first-page":"8769","article-title":"The iNaturalist species classification and detection dataset","author":"van horn","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.228"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6712"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"ref107","first-page":"637","article-title":"Maximum entropy fine-grained classification","author":"dubey","year":"2018","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2977457"},{"key":"ref105","first-page":"4277","article-title":"Learning deep bilinear transformation for fine-grained image representation","author":"zheng","year":"2019","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_22"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_35"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_38"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2973812"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6882"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8875910"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2014(98)90005-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995368"},{"key":"ref13","article-title":"The Caltech-UCSD birds-200–2011 dataset","author":"wah","year":"2011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref15","year":"0"},{"key":"ref16","year":"0"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref17","year":"0"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref18","year":"0"},{"key":"ref19","year":"0"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref116","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0713-9"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.10.022"},{"key":"ref122","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref123","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9940447\/09609630.pdf?arnumber=9609630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:11:56Z","timestamp":1670281916000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9609630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":214,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3126648","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}