{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:51:51Z","timestamp":1791352311315,"version":"4.3.1"},"reference-count":46,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/cvpr.2015.7298641","type":"proceedings-article","created":{"date-parts":[[2015,10,15]],"date-time":"2015-10-15T18:42:06Z","timestamp":1444934526000},"page":"437-446","source":"Crossref","is-referenced-by-count":301,"title":["Deformable part models are convolutional neural networks"],"prefix":"10.1109","author":[{"given":"Ross","family":"Girshick","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Forrest","family":"Iandola","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":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref38","article-title":"Joint training of a convolutional network and a graphical model for human pose estimation","author":"tompson","year":"2014","journal-title":"NIPS (To appear)"},{"key":"ref33","article-title":"Learning internal representations by error propagation","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing 1 318–362"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.417"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.257"},{"key":"ref30","article-title":"Do conynets learn correspondence?","author":"long","year":"2014","journal-title":"NIPS (To appear)"},{"key":"ref37","article-title":"Sparselet models for efficient multiclass object detection","author":"song","year":"2012","journal-title":"ECCV"},{"key":"ref36","article-title":"A comparison of statistical significance tests for information retrieval evaluation","author":"smucker","year":"2007","journal-title":"Conf on Information and Knowledge Management"},{"key":"ref35","article-title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","author":"sermanet","year":"2014","journal-title":"ICLRE"},{"key":"ref34","article-title":"Deformable part models with CNN features","author":"savalle","year":"2014","journal-title":"ECCV Workshop on Parts and Attributes"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1049\/ip-vis:19941301"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000042934.15159.49"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.4086\/toc.2012.v008a019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1973.223602"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref16","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"girshick","year":"2013","journal-title":"CoRR abs\/1311 2524"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref18","article-title":"Discriminatively trained deformable part models, release 5","author":"girshick","year":"0"},{"key":"ref19","article-title":"Object detection with grammar models","author":"girshick","year":"2011","journal-title":"NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref4","article-title":"Deep neural networks for object detection","author":"christian szegedy","year":"2013","journal-title":"NIPS"},{"key":"ref27","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref3","article-title":"Bird species categorization using pose normalized deep convolutional nets","author":"branson","year":"2014","journal-title":"BMVC"},{"key":"ref6","article-title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","author":"donahue","year":"2014","journal-title":"ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.406"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref8","article-title":"The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results","author":"everingham","year":"0"},{"key":"ref7","article-title":"Exact acceleration of linear object detectors","author":"dubout","year":"2012","journal-title":"ECCV"},{"key":"ref2","article-title":"A theoretical analysis of feature pooling in visual recognition","author":"boureau","year":"2010","journal-title":"ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.212"},{"key":"ref20","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"ICML"},{"key":"ref45","article-title":"Part-based R-CNNs for fine-grained category detection","author":"zhang","year":"2014","journal-title":"ECCV"},{"key":"ref22","article-title":"Simultaneous detection and segmentation","author":"hariharan","year":"2014","journal-title":"ECCV"},{"key":"ref21","article-title":"Learning fast approximations of sparse coding","author":"gregor","year":"2010","journal-title":"ICML"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.10"},{"key":"ref24","article-title":"Densenet: Implementing efficient con-vnet descriptor pyramids","author":"iandola","year":"2014","journal-title":"arXiv preprint arXiv 1404 1869"},{"key":"ref41","article-title":"End-to-end integration of a convolutional network, deformable parts model and non-maximum suppression","author":"wan","year":"0","journal-title":"arXiv e-prints arXiv 1411 5309 [cs CV]"},{"key":"ref23","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"ECCV"},{"key":"ref44","article-title":"Articulated human detection with flexible mixtures-of-parts","author":"yang","year":"2012","journal-title":"TPAMI"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref43","article-title":"Learning hierarchical pose-lets for human parsing","author":"wang","year":"2011","journal-title":"CVPR"},{"key":"ref25","article-title":"Beyond spatial pyramids: Receptive field learning for pooled image features","author":"jia","year":"2012","journal-title":"CVPR"}],"event":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Boston, MA, USA","start":{"date-parts":[[2015,6,7]]},"end":{"date-parts":[[2015,6,12]]}},"container-title":["2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7293313\/7298593\/07298641.pdf?arnumber=7298641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,24]],"date-time":"2017-03-24T17:31:41Z","timestamp":1490376701000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7298641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2015.7298641","relation":{},"subject":[],"published":{"date-parts":[[2015,6]]}}}