{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:13:39Z","timestamp":1774541619806,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61373121"],"award-info":[{"award-number":["61373121"]}],"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":["61328205"],"award-info":[{"award-number":["61328205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Sichuan Provincial Science Fund for Distinguished Young Scholars","award":["13QNJJ0149"],"award-info":[{"award-number":["13QNJJ0149"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201507000032"],"award-info":[{"award-number":["201507000032"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1109\/tmm.2017.2648498","type":"journal-article","created":{"date-parts":[[2017,1,5]],"date-time":"2017-01-05T19:19:36Z","timestamp":1483643976000},"page":"1245-1256","source":"Crossref","is-referenced-by-count":364,"title":["Diversified Visual Attention Networks for Fine-Grained Object Classification"],"prefix":"10.1109","volume":"19","author":[{"given":"Bo","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Xiao","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Qiang","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Improved bird species recognition\n using pose normalized deep convolutional nets","author":"branson","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref38","first-page":"2579","article-title":"Bicos: A\n bi-level co-segmentation method for image classification","author":"chai","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref33","article-title":"Learning\n fine-grained features via a CNN tree for large-scale classification","author":"wang","year":"2015","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref31","first-page":"1409","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref30","first-page":"647","article-title":"DECAF: A deep convolutional activation feature\n for generic visual recognition","author":"donahue","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.215"},{"key":"ref36","first-page":"3122","article-title":"Unsupervised template learning for\n fine-grained object recognition","author":"yang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301271"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2495248"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref2","first-page":"3466","article-title":"Novel dataset for\n fine-grained image categorization","author":"khosla","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recog Workshops"},{"key":"ref1","article-title":"The Caltech-UCSD Birds-200-2011 dataset","author":"wah","year":"2011"},{"key":"ref20","first-page":"842","article-title":"The application of two-level attention models\n in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/135062800394667"},{"key":"ref21","article-title":"Fully convolutional attention localization networks:\n Efficient attention localization for fine-grained recognition","author":"liu","year":"2016","journal-title":"CoRR"},{"key":"ref24","article-title":"Action recognition using visual attention","author":"sharma","year":"0","journal-title":"Proc NIPS Time Series Workshop"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2272919"},{"key":"ref26","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with\n visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","first-page":"1","article-title":"Multiple object\n recognition with visual attention","author":"ba","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0741-5"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.06.011"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.15"},{"key":"ref52","first-page":"301","article-title":"The unreasonable effectiveness of noisy data\n for fine-grained recognition","author":"krause","year":"0","journal-title":"Proc IEEE Eur Conf Comput Vis"},{"key":"ref10","article-title":"Simultaneous food localization and recognition","author":"bola\u00f1os","year":"0","journal-title":"Proc Int Conf Pattern Recog"},{"key":"ref11","article-title":"Attention for\n fine-grained categorization","author":"sermanet","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref40","first-page":"438","article-title":"Visual recognition with humans in the loop","author":"branson","year":"0","journal-title":"Proc IEEE Eur Conf Comput Vis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2431496"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491929"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.128"},{"key":"ref15","first-page":"244","article-title":"Kernel descriptors for visual\n recognition","author":"bo","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"1","article-title":"Bird species categorization using pose\n normalized deep convolutional nets","author":"branson","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.47"},{"key":"ref18","first-page":"3466","article-title":"A codebook-free and annotation-free approach for fine-grained image\n categorization","author":"yao","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref19","first-page":"834","article-title":"Part-based R-CNNs for\n fine-grained category detection","author":"zhang","year":"0","journal-title":"Proc Euro Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref3","first-page":"172","article-title":"Dog breed classification using part\n localization","author":"liu","year":"0","journal-title":"In Proc European Conf Comp Vis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2408566"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2279658"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2353624"},{"key":"ref49","article-title":"Return of the devil in the details:\n Delving deep into convolutional nets","author":"chatfield","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2542983"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.136"},{"key":"ref45","article-title":"Recurrent\n neural network regularization","author":"zaremba","year":"2014","journal-title":"CoRR"},{"key":"ref48","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref47","first-page":"1134","article-title":"Picking deep filter responses for fine-grained image recognition","author":"zhang","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.115"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.81"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref43","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/7927810\/07807286.pdf?arnumber=7807286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:14:17Z","timestamp":1642004057000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7807286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":55,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2648498","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6]]}}}