{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:04:40Z","timestamp":1776679480737,"version":"3.51.2"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2015,5,1]],"date-time":"2015-05-01T00:00:00Z","timestamp":1430438400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"National Basic Research Program (973 Program) of China","award":["2013CB329403"],"award-info":[{"award-number":["2013CB329403"]}]},{"name":"National Basic Research Program (973 Program) of China","award":["2012CB316301"],"award-info":[{"award-number":["2012CB316301"]}]},{"name":"National Basic Research Program (973 Program) of China","award":["2014CB347600"],"award-info":[{"award-number":["2014CB347600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61332007"],"award-info":[{"award-number":["61332007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61273023"],"award-info":[{"award-number":["61273023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61429201"],"award-info":[{"award-number":["61429201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Tsinghua University Initiative Scientific Research Program","award":["20121088071"],"award-info":[{"award-number":["20121088071"]}]},{"name":"NEC Laboratories of America Faculty Research Awards","award":["W911NF-12-1-0057"],"award-info":[{"award-number":["W911NF-12-1-0057"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2015,5]]},"DOI":"10.1109\/tmm.2015.2408566","type":"journal-article","created":{"date-parts":[[2015,3,4]],"date-time":"2015-03-04T14:37:19Z","timestamp":1425479839000},"page":"636-647","source":"Crossref","is-referenced-by-count":73,"title":["Fine-Grained Image Search"],"prefix":"10.1109","volume":"17","author":[{"given":"Lingxi","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"446","article-title":"Food-101?Mining discriminative components with random forests","author":"bossard","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref72","article-title":"Fine-grained visual classification of aircraft","volume":"abs 1306 5151","author":"maji","year":"2013","journal-title":"CoRR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"ref77","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":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2310117"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref75","first-page":"1","article-title":"A theoretical analysis of NDCG ranking measures","author":"wang","year":"2013","journal-title":"Proc 26th Annu Conf Learn Theory"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2329182"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref33","article-title":"Image classification with max-sift descriptors","author":"xie","year":"2015","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref32","first-page":"1","article-title":"Visual categorization with bags of keypoints","volume":"1","author":"csurka","year":"2004","journal-title":"Proc Workshop Statistical Learning in Computer Vision"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1109\/ICME.2004.1394376","article-title":"A new analysis of the value of unlabeled data in semi-supervised learning for image retrieval","volume":"2","author":"tian","year":"2004","journal-title":"Proc 2004 IEEE Int Conf Multimedia Expo"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.12.011"},{"key":"ref37","first-page":"801","article-title":"Efficient sparse coding algorithms","author":"lee","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"143","article-title":"Improving the fisher kernel for large-scale image classification","author":"perronnin","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref60","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref62","author":"miller","year":"1998","journal-title":"WordNet An Electronic Lexical Database"},{"key":"ref61","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7287.001.0001","author":"fellbaum","year":"1998","journal-title":"WordNet"},{"key":"ref63","author":"fellbaum","year":"2005","journal-title":"Encyclopedia of Language and Linguistics"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2046292"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/265563.265573"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2055045"},{"key":"ref65","author":"hyvonen","year":"2003","journal-title":"?Ontology-based image retrieval ?"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2003.1246729"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393378"},{"key":"ref67","first-page":"283","article-title":"High level color similarity retrieval","volume":"10","author":"stanchev","year":"2003","journal-title":"Int J Inst Inf Theories Appl"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.04.045"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072365"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2305072"},{"key":"ref21","first-page":"209","article-title":"Contextual weighting for vocabulary tree based image retrieval","author":"wang","year":"2011","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2279663"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072367"},{"key":"ref26","first-page":"3100","article-title":"Randomized visual phrases for object search","author":"jiang","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995528"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.477"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.47"},{"key":"ref59","first-page":"660","article-title":"Query specific fusion for image retrieval","author":"zhang","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995595"},{"key":"ref57","first-page":"1673","article-title":"Semantic-aware co-indexing for near-duplicate image retrieval","author":"zhang","year":"2013","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.133"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995516"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.215"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2301979"},{"key":"ref40","article-title":"Generalized regular spatial pooling for image classification","author":"xie","year":"2015","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref11","first-page":"9","article-title":"Efficient representation of local geometry for large scale object retrieval","author":"perd?och","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref12","first-page":"304","article-title":"Hamming embedding and weak geometric consistency for large scale image search","author":"jegou","year":"2008","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2231061"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2005.09.012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2187778"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2167224"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2127463"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"ref4","first-page":"404","article-title":"SURF: Speeded up robust features","author":"bay","year":"2006","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7026156"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000027790.02288.f2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2004.02.006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383172"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.206"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.264"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393377"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248364"},{"key":"ref45","first-page":"3474","article-title":"Discovering localized attributes for fine-grained recognition","author":"duan","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.128"},{"key":"ref47","first-page":"3122","article-title":"Unsupervised template learning for fine-grained object recognition","author":"yang","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","author":"wah","year":"2011","journal-title":"?The Caltech-UCSD Birds-200-2011 dataset ?"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738537"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.81"},{"key":"ref43","article-title":"Novel dataset for fine-grained image categorization","author":"khosla","year":"2011","journal-title":"Proc 1st Workshop Fine-Grained Vis Categorization"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/7086387\/07054538.pdf?arnumber=7054538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:51:16Z","timestamp":1641988276000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7054538\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5]]},"references-count":83,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2015.2408566","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,5]]}}}