{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T07:33:15Z","timestamp":1780990395685,"version":"3.54.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Guangdong Special Support Program","award":["2016TX03X276"],"award-info":[{"award-number":["2016TX03X276"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876176"],"award-info":[{"award-number":["61876176"]}],"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":["U1713208"],"award-info":[{"award-number":["U1713208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Basic Research Program","award":["CXB201104220032 A"],"award-info":[{"award-number":["CXB201104220032 A"]}]},{"name":"Joint Laboratory of CAS-HK"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3028482","type":"journal-article","created":{"date-parts":[[2020,10,2]],"date-time":"2020-10-02T20:14:22Z","timestamp":1601669662000},"page":"3603-3617","source":"Crossref","is-referenced-by-count":35,"title":["Wildfish++: A Comprehensive Fish Benchmark for Multimedia Research"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1724-8980","authenticated-orcid":false,"given":"Peiqin","family":"Zhuang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-7428","authenticated-orcid":false,"given":"Yali","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.42"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2763441"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"ref30","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"0"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298700"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_26"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321392"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref62","first-page":"32767","article-title":"Learning to navigate for fine-grained classification","author":"yang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.775"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Int Conf Learn Represent"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.128"},{"key":"ref22","first-page":"1487","article-title":"Weakly supervised learning of part selection model with spatial constraints for fine-grained image classification","author":"he","year":"0","journal-title":"Proc Assoc Advancement Artif Intell"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298775"},{"key":"ref24","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":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref23","first-page":"1","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2648498"},{"key":"ref50","first-page":"1","article-title":"Skip-thought vectors","author":"kiros","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref58","first-page":"4510","article-title":"Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation","author":"sandler","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/502512.502546"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350974"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref52","first-page":"248","article-title":"Collecting image annotations using amazon's mechanical turk","author":"rashtchian","year":"0","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Workshop"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.259"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1314"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.66"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","first-page":"1542","article-title":"Supporting ground-truth annotation of image datasets using clustering","author":"boom","year":"0","journal-title":"Proc Indian Council Philos Res"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6836084"},{"key":"ref16","article-title":"Imageclef\/lifeclef","author":"challenges","year":"2017"},{"key":"ref17","first-page":"241","article-title":"The fifth workshop on fine-grained visual categorization","author":"competition","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00969"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","first-page":"271?000276","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","author":"khosla","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240616"},{"key":"ref8","article-title":"Fine-grained visual classification of aircraft","author":"maji","year":"2013"},{"key":"ref7","article-title":"The Caltech-UCSD Birds-200-2011 Dataset","author":"wah","year":"2011"},{"key":"ref49","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/957142.957143"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247923"},{"key":"ref48","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014"},{"key":"ref47","first-page":"3128","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref42","first-page":"1","article-title":"A discriminative feature learning approach for deep face recognition","author":"wen","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.54"},{"key":"ref44","first-page":"162","article-title":"Relations between two sets of variates","author":"hotelling","year":"0","journal-title":"Breakthroughs Statistics"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2705068"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09211789.pdf?arnumber=9211789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:20Z","timestamp":1652194280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9211789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3028482","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}