{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:41:37Z","timestamp":1775745697626,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Director of National Intelligence\u00a0(ODNI)"},{"DOI":"10.13039\/100011039","name":"Intelligence Advanced Research Projects Activity\u00a0(IARPA)","doi-asserted-by":"crossref","award":["2014-14071600010"],"award-info":[{"award-number":["2014-14071600010"]}],"id":[{"id":"10.13039\/100011039","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Science Foundation","award":["IIS-1617917"],"award-info":[{"award-number":["IIS-1617917"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2018,6,1]]},"DOI":"10.1109\/tpami.2017.2723400","type":"journal-article","created":{"date-parts":[[2017,7,4]],"date-time":"2017-07-04T18:33:11Z","timestamp":1499193191000},"page":"1309-1322","source":"Crossref","is-referenced-by-count":270,"title":["Bilinear Convolutional Neural Networks for Fine-Grained Visual Recognition"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1332-646X","authenticated-orcid":false,"given":"Tsung-Yu","family":"Lin","sequence":"first","affiliation":[]},{"given":"Aruni","family":"RoyChowdhury","sequence":"additional","affiliation":[]},{"given":"Subhransu","family":"Maji","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.54"},{"key":"ref70","article-title":"Material perceprion: What can you see in a brief glance?","volume":"9","author":"sharan","year":"2009","journal-title":"J Vis"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026553619983"},{"key":"ref33","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref32","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011126920638"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_19"},{"key":"ref34","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.219"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.339"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.136"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.128"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.06.011"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.129"},{"key":"ref66","article-title":"Fine-grained pose prediction, normalization, and recognition","author":"zhang","year":"2016","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref29","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.131"},{"key":"ref68","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref69","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref1","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"wah","year":"2011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126413"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248364"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126238"},{"key":"ref24","first-page":"3","article-title":"Bird species categorization using pose normalized deep convolutional nets","author":"branson","year":"2014","journal-title":"Proc British Mach Vis Conf"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref50","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299035"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref56","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref55","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487591"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_32"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.305"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0911-8"},{"key":"ref17","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref18","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref3","article-title":"Fine-grained visual classification of aircraft","author":"maji","year":"2013","journal-title":"arXiv preprint arXiv 1306 5151"},{"key":"ref6","first-page":"1","article-title":"Visual categorization with bags of keypoints","author":"csurka","year":"2004","journal-title":"Proc ECCV Workshop Statist Learn Comput Vis"},{"key":"ref5","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref49","first-page":"1482","article-title":"Bilinear classifiers for visual recognition","author":"pirsiavash","year":"2009","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0872-3"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4175.001.0001","author":"scholkopf","year":"2001","journal-title":"Learning With Kernels Support Vector Machines Regularization Optimization and Beyond"},{"key":"ref45","article-title":"Texture synthesis using shallow convolutional networks with random filters","author":"ustyuzhaninov","year":"2016","journal-title":"arXiv preprint arXiv 1606 00021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref47","first-page":"3248","article-title":"Discriminative learning of sum-product networks","author":"gens","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref41","article-title":"Cross-convolutional-layer pooling for image recognition","author":"liu","year":"2016","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref43","first-page":"262","article-title":"Texture synthesis and the controlled generation of natural stimuli using convolutional neural networks","author":"gatys","year":"2015","journal-title":"Proc Advances Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/34\/8354864\/7968351-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8354864\/07968351.pdf?arnumber=7968351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T06:38:24Z","timestamp":1750487904000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7968351\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,1]]},"references-count":72,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2017.2723400","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,1]]}}}