{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:41:42Z","timestamp":1780054902597,"version":"3.54.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"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 Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2016YFC1400704"],"award-info":[{"award-number":["2016YFC1400704"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1613211"],"award-info":[{"award-number":["U1613211"]}],"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":["61633021"],"award-info":[{"award-number":["61633021"]}],"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":["61502470"],"award-info":[{"award-number":["61502470"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Research Program","award":["JCYJ20160229193541167"],"award-info":[{"award-number":["JCYJ20160229193541167"]}]},{"DOI":"10.13039\/501100002367","name":"External Cooperation Program of BIC, Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["172644KYSB20160033"],"award-info":[{"award-number":["172644KYSB20160033"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2017,4]]},"DOI":"10.1109\/tip.2017.2666739","type":"journal-article","created":{"date-parts":[[2017,2,9]],"date-time":"2017-02-09T19:18:04Z","timestamp":1486667884000},"page":"2028-2041","source":"Crossref","is-referenced-by-count":77,"title":["Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition"],"prefix":"10.1109","volume":"26","author":[{"given":"Zhe","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7718","authenticated-orcid":false,"given":"Limin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yali","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7400-566X","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2548241"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.144"},{"key":"ref71","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc ICML"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0872-3"},{"key":"ref74","article-title":"Deep spatial pyramid: The devil is once again in the details","volume":"abs 1504 5277","author":"gao","year":"2015","journal-title":"CoRR"},{"key":"ref39","article-title":"Knowledge guided disambiguation for large-scale scene classification with multi-resolution CNNs","volume":"abs 1610 1119","author":"wang","year":"2016","journal-title":"CoRR"},{"key":"ref75","article-title":"Places205-VGGNet models for scene recognition","volume":"abs 1508 1667","author":"wang","year":"2015","journal-title":"CoRR"},{"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 ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref31","first-page":"696","article-title":"Kernel codebooks for scene categorization","author":"van gemert","year":"2008","journal-title":"Proc ECCV"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2574748"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471878"},{"key":"ref36","first-page":"660","article-title":"Boosting VLAD with supervised dictionary learning and high-order statistics","author":"peng","year":"2014","journal-title":"Proc ECCV"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.182"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539963"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.03.013"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref61","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc ECCV"},{"key":"ref63","author":"vedaldi","year":"2008","journal-title":"Vlfeat An Open and Portable Library of Computer Vision Algorithms"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2637331"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.102"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2621661"},{"key":"ref65","first-page":"494","article-title":"Mid-level visual element discovery as discriminative mode seeking","author":"doersch","year":"2013","journal-title":"Proc NIPS"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.477"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2544314"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2328894"},{"key":"ref68","first-page":"552","article-title":"Learning discriminative and shareable features for scene classification","author":"zuo","year":"2014","journal-title":"Proc ECCV"},{"key":"ref69","article-title":"Local color contrastive descriptor for image classification","volume":"abs 1610 1119","author":"guo","year":"2015","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref20","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref24","first-page":"141","article-title":"Image classification using super-vector coding of local image descriptors","author":"zhou","year":"2010","journal-title":"Proc ECCV"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2311377"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2591583"},{"key":"ref50","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 NIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0859-0"},{"key":"ref59","first-page":"572","article-title":"A comparative study of encoding, pooling and normalization methods for action recognition","author":"wang","year":"2012","journal-title":"Proc ACCV"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248001"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126383"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.124"},{"key":"ref54","first-page":"73","article-title":"Unsupervised discovery of mid-level discriminative patches","author":"singh","year":"2012","journal-title":"Proc ECCV"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2295753"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.296"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2007.09.014"},{"key":"ref11","first-page":"1","article-title":"Visual categorization with bags of keypoints","author":"csurka","year":"2004","journal-title":"Proc ECC"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2629443"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref13","first-page":"1794","article-title":"Linear spatial pyramid matching using sparse coding for image classification","author":"yang","year":"2009","journal-title":"Proc CVPR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref15","first-page":"143","article-title":"Improving the fisher kernel for large-scale image classification","author":"perronnin","year":"2010","journal-title":"Proc ECCV"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref19","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Proc CVPR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_29"},{"key":"ref3","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proc NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301333"},{"key":"ref5","first-page":"1600","article-title":"Recognize complex events from static images by fusing deep channels","author":"xiong","year":"2015","journal-title":"Proc CVPR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref7","article-title":"Transferring object-scene convolutional neural networks for event recognition in still images","volume":"abs 1609 162","author":"wang","year":"2016","journal-title":"CoRR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.08.006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2032939"},{"key":"ref47","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298916"},{"key":"ref41","article-title":"Hybrid CNN and dictionary-based models for scene recognition and domain adaptation","volume":"abs 1601 7977","author":"xie","year":"2016","journal-title":"CoRR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref43","first-page":"392","article-title":"Multi-scale orderless pooling of deep convolutional activation features","author":"gong","year":"2014","journal-title":"Proc ECCV"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/7864504\/07849229.pdf?arnumber=7849229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:27:11Z","timestamp":1642004831000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7849229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4]]},"references-count":76,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tip.2017.2666739","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,4]]}}}