{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:00:44Z","timestamp":1760608844161,"version":"3.37.3"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2015,6,1]],"date-time":"2015-06-01T00:00:00Z","timestamp":1433116800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100006129","name":"FCT","doi-asserted-by":"publisher","award":["SFRH\/BPD\/84194\/2012","SFRH\/BD74152\/2010","PTDC\/EEA-CRO\/122812\/2010"],"award-info":[{"award-number":["SFRH\/BPD\/84194\/2012","SFRH\/BD74152\/2010","PTDC\/EEA-CRO\/122812\/2010"]}],"id":[{"id":"10.13039\/100006129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CNCS-UEFISCDI","award":["CT-ERC-2012-1","PCE-2011-3-0438"],"award-info":[{"award-number":["CT-ERC-2012-1","PCE-2011-3-0438"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2015,6,1]]},"DOI":"10.1109\/tpami.2014.2361137","type":"journal-article","created":{"date-parts":[[2014,10,2]],"date-time":"2014-10-02T14:52:32Z","timestamp":1412261552000},"page":"1177-1189","source":"Crossref","is-referenced-by-count":51,"title":["Free-Form Region Description with Second-Order Pooling"],"prefix":"10.1109","volume":"37","author":[{"given":"Joao","family":"Carreira","sequence":"first","affiliation":[]},{"given":"Rui","family":"Caseiro","sequence":"additional","affiliation":[]},{"given":"Jorge","family":"Batista","sequence":"additional","affiliation":[]},{"given":"Cristian","family":"Sminchisescu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Superparsing—scalable nonparametric image parsing with superpixels","author":"tighe","year":"0","journal-title":"Int J Comput Vis"},{"key":"ref38","first-page":"1030","article-title":"Recognition using regions","author":"gu","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"key":"ref33","article-title":"Learning hierarchical features for scene labeling","author":"farabet","year":"1915","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1007\/s11263-007-0109-1"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/ICIP.2011.6116641"},{"key":"ref30","first-page":"143","article-title":"Improving the Fisher kernel for large-scale image classification","author":"perronnin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/CVPR.2008.4587462"},{"key":"ref36","first-page":"2759","article-title":"Rgb-(d) scene labeling: Features and algorithms","author":"ren","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1007\/s11263-011-0449-8"},{"key":"ref34","first-page":"670","article-title":"Class segmentation and object localization with superpixel neighborhoods","author":"fulkerson","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref60","first-page":"178","article-title":"Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories","author":"fei-fei","year":"0","journal-title":"Proc Comput Vis Image Understanding"},{"doi-asserted-by":"publisher","key":"ref62","DOI":"10.1007\/s11263-013-0663-7"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1109\/ICCV.2011.6126445"},{"key":"ref63","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-1904-8","author":"jolliffe","year":"1986","journal-title":"Principal Component Analysis"},{"key":"ref28","first-page":"1","article-title":"A nonparametric Riemannian framework on tensor field with application to foreground segmentation","author":"caseiro","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref64","first-page":"2142","article-title":"Object detection and segmentation from joint embedding of parts and pixels","author":"maire","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/TPAMI.2008.75"},{"doi-asserted-by":"publisher","key":"ref65","DOI":"10.1109\/CVPR.2013.251"},{"key":"ref66","first-page":"2136","article-title":"Codemaps segment, classify and search objects locally","author":"li","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref29","first-page":"2336","article-title":"Global Gaussian approach for scene categorization using information geometry","author":"nakayama","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref67","first-page":"3302","article-title":"Composite statistical inference for semantic segmentation","author":"li","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref68","first-page":"3294","article-title":"Bottom-up segmentation for top-down detection","author":"fidler","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"year":"0","key":"ref69"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/s11263-011-0507-2"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1007\/s11263-009-0275-4"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICCV.2011.6126449"},{"key":"ref22","article-title":"Efficient Match Kernel between Sets of Features for Visual Recognition","author":"bo","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"year":"2005","author":"farquhar","article-title":"Improving ”bag-of-keypoints” image categorisation: Generative models and pdf-kernels","key":"ref21"},{"key":"ref24","first-page":"459","article-title":"Discriminative decorrelation for clustering and classification","author":"hariharan","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1145\/1150402.1150429"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/TIT.1962.1057692"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.5244\/C.25.76"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1016\/j.patrec.2012.07.019"},{"key":"ref51","first-page":"334","article-title":"Coloring local feature extraction","author":"weijer","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"doi-asserted-by":"publisher","key":"ref59","DOI":"10.1109\/CVPR.2010.5540018"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1145\/1961189.1961199"},{"year":"0","key":"ref57"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1109\/ICCV.2011.6126343"},{"doi-asserted-by":"publisher","key":"ref55","DOI":"10.1109\/CVPR.2009.5206707"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1109\/TPAMI.2011.231"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.1109\/CVPR.2001.990517"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1109\/TPAMI.2002.1017623"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICCV.2011.6126555"},{"key":"ref11","first-page":"4","article-title":"Imagenet classification with deep convolutional neural networks.","volume":"1","author":"krizhevsky","year":"0","journal-title":"Proc NIPS"},{"key":"ref40","first-page":"424","article-title":"What, where & how many? Combining object detectors and CRFs","author":"ladicky","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref12","first-page":"328","article-title":"Geometric means in a novel vector space structure on symmetric positive-definite matrices","author":"arsigny","year":"0","journal-title":"SIAM Journal Mat Anal Appl"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TPAMI.2004.1273924"},{"key":"ref15","first-page":"509","article-title":"Shape context: A new descriptor for shape matching and object recognition","author":"belongie","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"424","article-title":"Shape descriptors for non-rigid shapes with a single closed contour","author":"latecki","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1007\/s11263-006-8707-x"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TPAMI.2009.167"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICCV.2005.239"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/CVPR.2012.6248077"},{"key":"ref3","first-page":"40","article-title":"Probabilistic joint segmentation and labeling","author":"ion","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref5","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"girshick","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref7","first-page":"2169","article-title":"Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories","author":"lazebnik","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"key":"ref49","first-page":"430","article-title":"Semantic segmentation with second-order pooling","author":"carreira","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref9","article-title":"A theoretical analysis of feature pooling in vision algorithms","author":"boureau","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1109\/TPAMI.2011.153"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1137\/S0895479802410815"},{"key":"ref48","first-page":"661","article-title":"Spatial coordinate coding to reduce histogram representations, dominant angle and colour pyramid match","author":"koniusz","year":"0","journal-title":"Proc 18th IEEE Int Conf"},{"key":"ref47","article-title":"In defense of nearest-neighbor based image classification","author":"boiman","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1007\/978-1-4757-2201-7"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1109\/ICCV.2013.271"},{"key":"ref44","article-title":"A performance evaluation of exact and approximate match kernels for object recognition","volume":"8","author":"caputo","year":"2010","journal-title":"Electron Lett Comput Vis Image Anal"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1007\/s11263-005-3222-z"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7101897\/06915745.pdf?arnumber=6915745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:30:53Z","timestamp":1641987053000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6915745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,1]]},"references-count":69,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2014.2361137","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"}],"subject":[],"published":{"date-parts":[[2015,6,1]]}}}