{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T12:22:17Z","timestamp":1782562937950,"version":"3.54.5"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2017YFB1300205"],"award-info":[{"award-number":["2017YFB1300205"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702265"],"award-info":[{"award-number":["61702265"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20170856"],"award-info":[{"award-number":["BK20170856"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2020.2996736","type":"journal-article","created":{"date-parts":[[2020,5,30]],"date-time":"2020-05-30T00:40:49Z","timestamp":1590799249000},"page":"7006-7018","source":"Crossref","is-referenced-by-count":69,"title":["Bi-Modal Progressive Mask Attention for Fine-Grained Recognition"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4046-8594","authenticated-orcid":false,"given":"Kaitao","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8200-1845","authenticated-orcid":false,"given":"Xiu-Shen","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3076-1786","authenticated-orcid":false,"given":"Ren-Jie","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9190-507X","authenticated-orcid":false,"given":"Jianfeng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.136"},{"key":"ref38","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 (CVPR)"},{"key":"ref33","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942030"},{"key":"ref31","first-page":"1","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"Proc ICLR"},{"key":"ref30","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"Proc ICLR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.129"},{"key":"ref36","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-5615"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806216"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240579"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref1","article-title":"Caltech-UCSD birds 200","author":"welinder","year":"2010"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.276"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2531289"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.128"},{"key":"ref24","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2688133"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2705122"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301270"},{"key":"ref57","article-title":"Fully convolutional attention localization networks: Efficient attention localization for fine-grained recognition","author":"liu","year":"2016","journal-title":"arXiv 1603 06765"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_35"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.325"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.131"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2631122"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0970-x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_22"},{"key":"ref12","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc NIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/87"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.775"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/145"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2924811"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref4","article-title":"Fine-grained visual classification of aircraft","author":"maji","year":"2013","journal-title":"arXiv 1306 5151"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref5","first-page":"1","article-title":"Bird species categorization using pose normalized deep convolutional nets","author":"branson","year":"2014","journal-title":"Proc BMVC"},{"key":"ref8","article-title":"RPC: A large-scale retail product checkout dataset","author":"wei","year":"2019","journal-title":"arXiv 1901 07249"},{"key":"ref7","first-page":"1","article-title":"Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification","author":"wei","year":"2018","journal-title":"Proc ACCV"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref46","first-page":"1409","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref48","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00335"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01176-2"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/09103943.pdf?arnumber=9103943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:04Z","timestamp":1651070344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9103943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.2996736","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}