{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T04:18:36Z","timestamp":1792729116699,"version":"4.5.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"US National Science Foundation","award":["IIS-0905647"],"award-info":[{"award-number":["IIS-0905647"]}]},{"name":"US National Science Foundation","award":["IIS-1134072"],"award-info":[{"award-number":["IIS-1134072"]}]},{"name":"US National Science Foundation","award":["IIS-1212798"],"award-info":[{"award-number":["IIS-1212798"]}]},{"name":"US National Science Foundation","award":["MURI N000014-10-1-0933"],"award-info":[{"award-number":["MURI N000014-10-1-0933"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2016,1,1]]},"DOI":"10.1109\/tpami.2015.2437384","type":"journal-article","created":{"date-parts":[[2015,5,25]],"date-time":"2015-05-25T14:37:57Z","timestamp":1432564677000},"page":"142-158","source":"Crossref","is-referenced-by-count":2549,"title":["Region-Based Convolutional Networks for Accurate Object Detection and Segmentation"],"prefix":"10.1109","volume":"38","author":[{"given":"Ross","family":"Girshick","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeff","family":"Donahue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jitendra","family":"Malik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","article-title":"Fully convolutional networks for semantic segmentation","author":"long","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref72","article-title":"Conditional random fields as recurrent neural networks","author":"zheng","year":"2015","journal-title":"ArXiv e-prints"},{"key":"ref71","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"chen","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646421"},{"key":"ref74","first-page":"109","article-title":"Efficient inference in fully connected CRFs with Gaussian edge potentials","author":"kr\u00e4henb\u00fchl","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref39","first-page":"640","article-title":"Is learning the n-th thing any easier than learning the first?","author":"thrun","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465908"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.414"},{"key":"ref31","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.326"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref36","first-page":"725","article-title":"Geodesic object proposals","author":"kr\u00e4henb\u00fchl","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.50"},{"key":"ref60","first-page":"2377","article-title":"Fisher and vlad with flair","author":"van de sande","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.417"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.406"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126474"},{"key":"ref28","article-title":"Fast R-CNN","author":"girshick","year":"0","journal-title":"ArXiv e-prints"},{"key":"ref64","first-page":"340","article-title":"Diagnosing error in object detectors","author":"hoiem","year":"0","journal-title":"Proc 12th Eur Conf Comput Vis"},{"key":"ref27","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557011"},{"key":"ref66","article-title":"Crowdsourcing annotations for visual object detection","author":"su","year":"0","journal-title":"Proceedings of the 4th AAAI Workshop on Human Computation"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.107"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248077"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref2","first-page":"886","author":"dalal","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref20","article-title":"Recognition using regions","author":"gu","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.231"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref24","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref23","author":"girshick","year":"0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.237"},{"key":"ref25","first-page":"329","article-title":"Analyzing the performance of multilayer neural networks for object recognition","author":"agrawal","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref50","article-title":"Scalable, high-quality object detection","author":"szegedy","year":"2015","journal-title":"ArXiv e-prints"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.28"},{"key":"ref59","first-page":"430","article-title":"Semantic segmentation with second-order pooling","author":"carreira","year":"0","journal-title":"Proc 12th Eur Conf Comput Vis"},{"key":"ref58","doi-asserted-by":"crossref","DOI":"10.21236\/ADA295738","article-title":"Example-based learning for view-based human face detection","author":"sung","year":"1994"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.423"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.237"},{"key":"ref55","author":"jia","year":"0"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.10"},{"key":"ref53","first-page":"411","article-title":"Mitosis detection in breast cancer histology images with deep neural networks","author":"cire?an","year":"0","journal-title":"Proc Medical Image Comput Comput -Assisted Intervention"},{"key":"ref52","first-page":"575","article-title":"Category independent object proposals","author":"endres","year":"0","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref10","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref12","first-page":"2553","article-title":"Deep neural networks for object detection","author":"szegedy","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.276"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/34.655647"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1049\/ip-vis:19941301"},{"key":"ref16","first-page":"901","article-title":"A convolutional neural network hand tracker","author":"platt","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.465"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref19","article-title":"OverFeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref5","first-page":"318","article-title":"Learning internal representations by error propagation","volume":"1","author":"rumelhart","year":"1986","journal-title":"Parallel Distrib Process"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref49","article-title":"Going deeper with convolutions","author":"szegedy","year":"2014","journal-title":"ArXiv e-prints"},{"key":"ref9","author":"deng","year":"0"},{"key":"ref46","first-page":"345","article-title":"Learning rich features from RGB-D images for object detection and segmentation","author":"gupta","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref45","first-page":"297","article-title":"Simultaneous detection and segmentation","author":"hariharan","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref48","article-title":"ImageNet large scale visual recognition challenge","author":"russakovsky","year":"2014","journal-title":"ArXiv e-prints"},{"key":"ref47","article-title":"On learning to localize objects with minimal supervision","author":"song","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","article-title":"From large-scale object classifiers to large-scale object detectors: An adaptation approach","author":"hoffman","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","article-title":"R-CNNs for pose estimation and action detection","author":"gkioxari","year":"2014","journal-title":"ArXiv e-prints"},{"key":"ref43","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7346524\/7112511.pdf?arnumber=7112511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T14:47:34Z","timestamp":1649429254000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7112511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,1,1]]},"references-count":76,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2015.2437384","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,1,1]]}}}