{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T12:32:41Z","timestamp":1786192361182,"version":"3.56.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2015,9,1]],"date-time":"2015-09-01T00:00:00Z","timestamp":1441065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2015,9,1]]},"DOI":"10.1109\/tpami.2015.2389824","type":"journal-article","created":{"date-parts":[[2015,1,9]],"date-time":"2015-01-09T19:58:40Z","timestamp":1420833520000},"page":"1904-1916","source":"Crossref","is-referenced-by-count":9853,"title":["Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition"],"prefix":"10.1109","volume":"37","author":[{"given":"Kaiming","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoqing","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389830"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref33","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref32","article-title":"Going deeper with convolutions","author":"szegedy","year":"2014","journal-title":"arXiv 1409 4842"},{"key":"ref31","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref30","first-page":"696","article-title":"Kernel codebooks for scene categorization","author":"gemert","year":"0","journal-title":"Proc 10th Eur Conf Comput Vis"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref36","article-title":"Some improvements on deep convolutional neural network based image classification","author":"howard","year":"2013","journal-title":"ArXiv 1312 5402"},{"key":"ref35","author":"jia","year":"2013"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref40","article-title":"Deep neural networks for object detection","author":"szegedy","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.212"},{"key":"ref12","article-title":"Multi-scale orderless pooling of deep convolutional activation features","author":"gong","year":"2014","journal-title":"arXiv 1403 1840"},{"key":"ref13","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2013","journal-title":"arXiv 1310 1531"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.239"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref17","first-page":"1794","article-title":"Linear spatial pyramid matching using sparse coding for image classification","author":"yang","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref19","first-page":"143","article-title":"Improving the Fisher kernel for large-scale image classification","author":"perronnin","year":"0","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref28","first-page":"921","article-title":"The importance of encoding versus training with sparse coding and vector quantization","author":"coates","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref4","article-title":"Visualizing and understanding convolutional neural networks","author":"zeiler","year":"2013","journal-title":"arXiv 1311 2901"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.76"},{"key":"ref3","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","article-title":"Return of the devil in the details: Delving deep into convolutional nets","author":"chatfield","year":"2014","journal-title":"ArXiv 1405 3531"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref5","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2013","journal-title":"arXiv 1312 6229"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.72"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref2","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"0","journal-title":"Proc Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2005.09.012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref26","article-title":"Imagenet large scale visual recognition challenge","author":"russakovsky","year":"2014","journal-title":"arXiv 1409 0575"},{"key":"ref25","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"0","journal-title":"Proc 10th Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7175116\/07005506.pdf?arnumber=7005506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:52:33Z","timestamp":1642006353000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7005506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9,1]]},"references-count":40,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2015.2389824","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,9,1]]}}}