{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T04:04:00Z","timestamp":1767585840605,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61471206"],"award-info":[{"award-number":["61471206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science Foundation of Ministry of Education-China Mobile Communications Corporation","award":["MCM20150504"],"award-info":[{"award-number":["MCM20150504"]}]},{"name":"Key Research and Development Foundation Project of Jiangsu province","award":["BE2016001-4"],"award-info":[{"award-number":["BE2016001-4"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/tcsvt.2018.2848543","type":"journal-article","created":{"date-parts":[[2018,6,18]],"date-time":"2018-06-18T18:27:21Z","timestamp":1529346441000},"page":"1715-1728","source":"Crossref","is-referenced-by-count":44,"title":["Fusing Object Semantics and Deep Appearance Features for Scene Recognition"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6907-3756","authenticated-orcid":false,"given":"Ning","family":"Sun","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5586-9120","authenticated-orcid":false,"given":"Wenli","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jixin","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5652-0238","authenticated-orcid":false,"given":"Guang","family":"Han","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6844-6496","authenticated-orcid":false,"given":"Cong","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref38","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2666739"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2629443"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2511543"},{"key":"ref37","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"1","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126406"},{"journal-title":"YOLO9000 Better Faster Stronger","year":"2016","author":"redmon","key":"ref34"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2686017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2675339"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2548241"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.249"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.03.003"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IVL.1998.694464"},{"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 Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299007"},{"journal-title":"Deep spatial pyramid The devil is once again in the details","year":"2015","author":"gao","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.152"},{"journal-title":"Fisher kernel for deep neural activations","year":"2014","author":"yoo","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.06.055"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_36"},{"key":"ref58","first-page":"643","article-title":"Learning a representative and discriminative part model with deep convolutional features for scene recognition","author":"liu","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.09.025"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"journal-title":"SUN Database Scene Categorization Benchmark","year":"0","key":"ref55"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref54"},{"journal-title":"Darknet Open source neural networks in c","year":"0","key":"ref53"},{"journal-title":"Darkflow Source Code","year":"0","key":"ref52"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383152"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2013.06.003"},{"journal-title":"Lsun Construction of a large-scale image dataset using deep learning with humans in the loop","year":"2015","author":"yu","key":"ref40"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2046270"},{"key":"ref13","first-page":"95","article-title":"A new approach to probabilistic image modeling with multidimensional hidden Markov models","author":"merialdo","year":"2006","journal-title":"Proc Int Workshop Adaptive Multimedia Retrieval"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref15","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":"ref16","first-page":"345","article-title":"Unsupervised and transfer learning under uncertainty-from object detections to scene categorization","author":"mesnil","year":"2013","journal-title":"Proc ICPR"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2003.1211479"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383198"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref41","first-page":"48","article-title":"Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the ‘echo state network’ approach","author":"jaeger","year":"2002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/8727555\/08387777.pdf?arnumber=8387777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:56:34Z","timestamp":1657745794000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8387777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":60,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2018.2848543","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2019,6]]}}}