{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:48:55Z","timestamp":1780055335790,"version":"3.54.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shanghai Institutions of Higher Learning"},{"name":"JSPS KAKENHI","award":["15K00159"],"award-info":[{"award-number":["15K00159"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/tmm.2019.2942478","type":"journal-article","created":{"date-parts":[[2019,9,19]],"date-time":"2019-09-19T19:51:35Z","timestamp":1568922695000},"page":"1182-1192","source":"Crossref","is-referenced-by-count":31,"title":["Hierarchical Coding of Convolutional Features for Scene Recognition"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1991-9143","authenticated-orcid":false,"given":"Lin","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feifei","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8149-0042","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3079-9207","authenticated-orcid":false,"given":"Qiu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.152"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.144"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref39","first-page":"19","article-title":"Online learning for matrix factorization and sparse coding","volume":"11","author":"mairal","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1214\/009053604000000067","article-title":"Least angle regression","volume":"32","author":"efron","year":"2004","journal-title":"Annals Stat"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2666739"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2675339"},{"key":"ref30","first-page":"1","article-title":"Good practice on deep scene classification: From local supervision to knowledge guided disambiguation","author":"qiao","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit Workshop Scene Understanding LSUN Challenge"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471878"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2511543"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298916"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299007"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2692281"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2700322"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref28","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2629443"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350829"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2544099"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766842"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2599292"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref68","first-page":"7178","article-title":"Dictionary learning inspired deep network for scene recognition","author":"liu","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2328894"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.124"},{"key":"ref22","first-page":"2012","article-title":"CUNet: A compact unsupervised network for image classification","volume":"20","author":"dong","year":"2017","journal-title":"IEEE Trans Multimedia"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.422"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2908448"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.09.025"},{"key":"ref50","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2641020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2702596"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2015.2488681"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2351395"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126403"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248107"},{"key":"ref54","first-page":"57","article-title":"Objects as attributes for scene classification","author":"li","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2567076"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2703130"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2557071"},{"key":"ref14","first-page":"1097","article-title":"Image Net classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CIAPP.2017.8167236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-8614-1"},{"key":"ref17","first-page":"1378","article-title":"Object bank: A high-level image representation for scene classification semantic feature sparsification","author":"li","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995451"},{"key":"ref19","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":"ref4","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1109\/TPAMI.2010.224","article-title":"Centrist: A visual descriptor for scene categorization","volume":"33","author":"wu","year":"2011","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref7","first-page":"1","article-title":"Visual categorization with bags of keypoints","author":"csurka","year":"2004","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539943"},{"key":"ref9","first-page":"1794","article-title":"Linear spatial pyramid matching using sparse coding for image classification","author":"yang","year":"2009","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_25"},{"key":"ref45","first-page":"630","article-title":"Beyond the Euclidean distance: creating effective visual codebooks using the histogram intersection kernel","author":"wu","year":"2009","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33709-3_52"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.476"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248001"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70716"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_26"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9076751\/08844815.pdf?arnumber=8844815","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:55:44Z","timestamp":1651074944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8844815\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":72,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2942478","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}