{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T22:03:45Z","timestamp":1779141825673,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T00:00:00Z","timestamp":1459468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T00:00:00Z","timestamp":1459468800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T00:00:00Z","timestamp":1459468800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T00:00:00Z","timestamp":1459468800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Human-Centered Cyber- physical Systems Programme at the Advanced Digital Sciences Center from Singapore\u2019s Agency for Science, Technology and Research (A*STAR)"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 61422203"],"award-info":[{"award-number":["No. 61422203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Singapore MoE AcRF Tier-1","award":["RG138\/14"],"award-info":[{"award-number":["RG138\/14"]}]},{"DOI":"10.13039\/100000001","name":"US National Science Foundation (NSF)","doi-asserted-by":"publisher","award":["CCF-1218682"],"award-info":[{"award-number":["CCF-1218682"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US National Science Foundation (NSF)","doi-asserted-by":"publisher","award":["IIS 11-16012"],"award-info":[{"award-number":["IIS 11-16012"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2016,4]]},"DOI":"10.1109\/tip.2016.2531289","type":"journal-article","created":{"date-parts":[[2016,2,19]],"date-time":"2016-02-19T19:09:34Z","timestamp":1455908974000},"page":"1713-1725","source":"Crossref","is-referenced-by-count":163,"title":["Weakly Supervised Fine-Grained Categorization With Part-Based Image Representation"],"prefix":"10.1109","volume":"25","author":[{"given":"Yu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiu-Shen","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfei","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangbo","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viet-Anh","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minh N.","family":"Do","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"3370","article-title":"Beyond spatial pyramids: Receptive field learning for pooled image features","author":"jia","year":"2012","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"key":"ref38","first-page":"2008","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.5"},{"key":"ref32","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2344296"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref34","article-title":"Fisher kernel for deep neural activations","author":"yoo","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.422"},{"key":"ref27","first-page":"494","article-title":"Mid-level visual element discovery as discriminative mode seeking","author":"doersch","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.136"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.259"},{"key":"ref1","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"wah","year":"2011"},{"key":"ref20","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.212"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.115"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.81"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.124"},{"key":"ref25","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 Int Conf Comput Vis Pattern Recognit"},{"key":"ref50","first-page":"1","article-title":"Improved bird species reognition using pose normalized deep convolution nets","author":"branson","year":"2014","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref51","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_28"},{"key":"ref52","first-page":"3131","article-title":"Unsupervised template learning for fine-grained object recognition","author":"yang","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","first-page":"1","article-title":"Fine-grained recognition datasets for biodiversity analysis","author":"rodner","year":"2015","journal-title":"Proc 3rd Workshop Fine-Grained Vis Categorization (FGVC)"},{"key":"ref11","first-page":"1","article-title":"A dataset for vehicle make and model recognition","author":"ben khalifa","year":"2015","journal-title":"Proc 3rd Workshop Fine-Grained Vis Categorization (FGVC)"},{"key":"ref40","first-page":"1","article-title":"Return of the devil in the details: Delving deep into convolutional nets","author":"chatfield","year":"2014","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126238"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248364"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15567-3_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.96"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.215"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.319"},{"key":"ref19","first-page":"834","article-title":"Part-based R-CNNs for fine-grained category detection","author":"zhang","year":"2014","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref4","first-page":"1994","article-title":"Spatial pooling of heterogeneous features for image classification","volume":"23","author":"xie","year":"2013","journal-title":"IEEE Trans Image Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2423557"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.463"},{"key":"ref5","first-page":"1","article-title":"Novel dataset for fine-grained image categorization","author":"khosla","year":"2011","journal-title":"Proc 1st Workshop Fine-Grained Vis Categorization"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref49","first-page":"4749","article-title":"The treasure beneath convolutional layers: Cross-convolutional-layer pooling for image classification","author":"liu","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2290593"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.330"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.121"},{"key":"ref48","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref47","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref41","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref43","first-page":"392","article-title":"Multi-scale orderless pooling of deep convolutional activation features","author":"gong","year":"2014","journal-title":"Proc 13th Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/83\/7406828\/7410088-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/7406828\/07410088.pdf?arnumber=7410088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:48:28Z","timestamp":1649443708000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7410088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4]]},"references-count":53,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tip.2016.2531289","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,4]]}}}