{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:53:16Z","timestamp":1780055596579,"version":"3.54.0"},"reference-count":76,"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\/501100012166","name":"National Basic Research Program of China (973 Program)","doi-asserted-by":"crossref","award":["2012CB316302"],"award-info":[{"award-number":["2012CB316302"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002367","name":"Strategic Priority Research Program through the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA06040102"],"award-info":[{"award-number":["XDA06040102"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61403380"],"award-info":[{"award-number":["61403380"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1109\/tcsvt.2015.2511543","type":"journal-article","created":{"date-parts":[[2015,12,22]],"date-time":"2015-12-22T19:14:35Z","timestamp":1450811675000},"page":"1263-1274","source":"Crossref","is-referenced-by-count":142,"title":["Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation"],"prefix":"10.1109","volume":"27","author":[{"given":"Guo-Sen","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu-Yao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0529-4"},{"key":"ref72","first-page":"377","article-title":"OTC: A novel local descriptor for scene classification","author":"margolin","year":"2014","journal-title":"Proc 13th ECCV"},{"key":"ref71","first-page":"359","article-title":"Scene recognition on the semantic manifold","author":"kwitt","year":"2012","journal-title":"Proc 12th ECCV"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2392472"},{"key":"ref76","author":"wang","year":"2015","journal-title":"Places205-VGGNet models for scene recognition"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref39","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"2014","journal-title":"Proc 13th ECCV"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.116"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.476"},{"key":"ref32","first-page":"494","article-title":"Mid-level visual element discovery as discriminative mode seeking","author":"doersch","year":"2013","journal-title":"Proc Adv NIPS"},{"key":"ref31","first-page":"73","article-title":"Unsupervised discovery of mid-level discriminative patches","author":"singh","year":"2012","journal-title":"Proc 12th ECCV"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.124"},{"key":"ref37","first-page":"3286","article-title":"BING: Binarized normed gradients for objectness estimation at 300 fps","author":"cheng","year":"2014","journal-title":"Proc IEEE Conf CVPR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126383"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185597"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref62","first-page":"2586","article-title":"Large margin learning of upstream scene understanding models","author":"zhu","year":"2010","journal-title":"Proc Adv NIPS"},{"key":"ref61","author":"jia","year":"2013","journal-title":"Caffe An Open Source Convolutional Architecture for Fast Feature Embedding"},{"key":"ref63","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":"ref28","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"Proc Adv NIPS"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248001"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299007"},{"key":"ref65","first-page":"172","article-title":"Learning hybrid part filters for scene recognition","author":"zheng","year":"2012","journal-title":"Proc 12th ECCV"},{"key":"ref66","first-page":"228","article-title":"Latent pyramidal regions for recognizing scenes","author":"sadeghi","year":"2012","journal-title":"Proc 12th ECCV"},{"key":"ref29","first-page":"213","article-title":"Adapting visual category models to new domains","author":"saenko","year":"2010","journal-title":"Proc 11th ECCV"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.115"},{"key":"ref68","first-page":"846","article-title":"Max-margin multiple-instance dictionary learning","author":"wang","year":"2013","journal-title":"Proc 30th ICML"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.422"},{"key":"ref2","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv NIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref20","first-page":"141","article-title":"Image classification using super-vector coding of local image descriptors","author":"zhou","year":"2010","journal-title":"Proc 11th ECCV"},{"key":"ref22","author":"donahue","year":"2013","journal-title":"Decaf A Deep Convolutional Activation Feature for Generic Visual Recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref24","first-page":"392","article-title":"Multi-scale orderless pooling of deep convolutional activation features","author":"gong","year":"2014","journal-title":"Proc 13th ECCV"},{"key":"ref23","first-page":"552","article-title":"Learning discriminative and shareable features for scene classification","author":"zuo","year":"2014","journal-title":"Proc 13th ECCV"},{"key":"ref26","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proc Adv NIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref50","article-title":"Fisher kernel for deep neural activations","author":"yoo","year":"2015","journal-title":"Proc CVPRW"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref59","first-page":"628","article-title":"Efficient feature coding based on auto-encoder network for image classification","author":"xie","year":"2014","journal-title":"Proc 12th ACCV"},{"key":"ref58","first-page":"1090","article-title":"Learning convolutional feature hierarchies for visual recognition","author":"kavukcuoglu","year":"2010","journal-title":"Proc Adv NIPS"},{"key":"ref57","first-page":"1378","article-title":"Object bank: A high-level image representation for scene classification and semantic feature sparsification","author":"li","year":"2010","journal-title":"Proc Adv NIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017616"},{"key":"ref55","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":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995354"},{"key":"ref52","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 12th ACCV"},{"key":"ref10","author":"kang","year":"2014","journal-title":"Fully convolutional neural networks for crowd segmentation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126344"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"ref13","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"chen","year":"2015","journal-title":"Proc ICLR"},{"key":"ref14","first-page":"1556","article-title":"Deep semantic ranking based hashing for multi-label image retrieval","author":"zhao","year":"2015","journal-title":"Proc IEEE Conf CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.66"},{"key":"ref16","first-page":"1794","article-title":"Linear spatial pyramid matching using sparse coding for image classification","author":"yang","year":"2009","journal-title":"Proc IEEE Conf CVPR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref19","first-page":"143","article-title":"Improving the Fisher kernel for large-scale image classification","author":"perronnin","year":"2010","journal-title":"Proc 11th ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref3","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref5","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.465"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298854"},{"key":"ref46","author":"long","year":"2015","journal-title":"Learning transferable features with deep adaptation networks"},{"key":"ref45","author":"tzeng","year":"2014","journal-title":"Deep domain confusion Maximizing for domain invariance"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl242"},{"key":"ref47","first-page":"898","article-title":"Domain adaptive neural networks for object recognition","author":"ghifary","year":"2014","journal-title":"Proc 13th PRICAI"},{"key":"ref42","first-page":"222","article-title":"Connecting the dots with landmarks: Discriminatively learning domain-invariant features for unsupervised domain adaptation","author":"gong","year":"2013","journal-title":"Proc 30th ICML"},{"key":"ref41","first-page":"2066","article-title":"Geodesic flow kernel for unsupervised domain adaptation","author":"gong","year":"2012","journal-title":"Proc IEEE Conf CVPR"},{"key":"ref44","first-page":"1","article-title":"DLID: Deep learning for domain adaptation by interpolating between domains","volume":"2","author":"chopra","year":"2013","journal-title":"Proc ICML Workshop on Representation Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.368"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/7938542\/07362156.pdf?arnumber=7362156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T02:34:59Z","timestamp":1633919699000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7362156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":76,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2015.2511543","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6]]}}}