{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:03:24Z","timestamp":1760609004699,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2018,9,1]],"date-time":"2018-09-01T00:00:00Z","timestamp":1535760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"National Ministry of Science and Technology","award":["MOST 105-2221-E-011-046","MOST 105-2221-E-011-117"],"award-info":[{"award-number":["MOST 105-2221-E-011-046","MOST 105-2221-E-011-117"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/tcsvt.2017.2730258","type":"journal-article","created":{"date-parts":[[2017,7,21]],"date-time":"2017-07-21T18:29:55Z","timestamp":1500661795000},"page":"2261-2275","source":"Crossref","is-referenced-by-count":14,"title":["Improved Object Detection With Iterative Localization Refinement in Convolutional Neural Networks"],"prefix":"10.1109","volume":"28","author":[{"given":"Kai-Wen","family":"Cheng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7221-1603","authenticated-orcid":false,"given":"Yie-Tarng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Wen-Hsien","family":"Fang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"redmon","year":"2016","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/34.655647"},{"key":"ref32","first-page":"340","article-title":"SSD: Single shot MultiBox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref30","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.28"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540226"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.144"},{"key":"ref34","first-page":"3626","article-title":"Pedestrian detection with unsupervised multi-stage feature learning","author":"sermanet","year":"2013","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref28","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref29","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref20","first-page":"886","article-title":"Histograms of oriented gradients for human detection","author":"dalal","year":"2005","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref24","first-page":"469","article-title":"Face recognition with local binary patterns","author":"ahonen","year":"2004","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref26","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref25","first-page":"1440","article-title":"Fast R-CNN","author":"girshick","year":"2015","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref50","first-page":"3158","article-title":"Sketch tokens: A learned mid-level representation for contour and object detection","author":"lim","year":"2013","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"journal-title":"Discriminatively trained deformable part models release 5","year":"2016","author":"girshick","key":"ref51"},{"key":"ref57","first-page":"340","article-title":"Diagnosing error in object detectors","author":"hoiem","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref56","first-page":"299","article-title":"Towards unified object detection and semantic segmentation","author":"dong","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref55","first-page":"297","article-title":"Simultaneous detection and segmentation","author":"hariharan","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref54","article-title":"Deformable part models with CNN features","author":"savalle","year":"2014","journal-title":"Proc Eur Conf Comput Vis Parts Attributes Workshop"},{"key":"ref53","article-title":"Generic object detection with dense neural patterns and regionlets","author":"zou","year":"2014","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref52","first-page":"3246","article-title":"Histograms of sparse codes for object detection","author":"ren","year":"2013","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref10","first-page":"2553","article-title":"Deep neural networks for object detection","author":"szegedy","year":"2013","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref11","first-page":"845","article-title":"HyperNet: Towards accurate region proposal generation and joint object detection","author":"kong","year":"2016","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref40","first-page":"1316","article-title":"Real-time grasp detection using convolutional neural networks","author":"redmon","year":"2015","journal-title":"Proc Int Conf Robot Autom"},{"key":"ref12","first-page":"2155","article-title":"Scalable object detection using deep neural networks","author":"erhan","year":"2014","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/34.1000236"},{"journal-title":"Fundamentals of Probability and Statistics for Engineers","year":"2004","author":"soong","key":"ref15"},{"key":"ref16","first-page":"3643","article-title":"Iterative localization refinement in convolutional neural networks for improved object detection","author":"cheng","year":"2016","journal-title":"Proc IEEE Int Conf Image Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2522968.2522978"},{"journal-title":"R-FCN Object Detection via Region-based Fully Convolutional Networks[J]","year":"2016","author":"dai","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0095-3"},{"key":"ref4","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"girshick","year":"2014","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref6","first-page":"2403","article-title":"DeepID-Net: Multi-stage and deformable deep convolutional neural networks for object detection","author":"ouyang","year":"2015","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref5","article-title":"OverFeat: Integrated recognition, localization and detection using convolutional networks","author":"mathieu","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref8","first-page":"731","article-title":"Adaptive region pooling for object detection","author":"tsai","year":"2015","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref7","first-page":"1","article-title":"Going deeper with convolutions","author":"szegedy","year":"2015","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465908"},{"key":"ref9","first-page":"4703","article-title":"segDeepM: Exploiting segmentation and context in deep neural networks for object detection","author":"zhu","year":"2015","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"journal-title":"An Introduction to Optimization","year":"2013","author":"chong","key":"ref46"},{"journal-title":"The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results","year":"2016","author":"everingham","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248065"},{"journal-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results","year":"2016","author":"everingham","key":"ref47"},{"key":"ref42","first-page":"2569","article-title":"Box aggregation for proposal decimation: Last mile of object detection","author":"liu","year":"2015","journal-title":"Proc IEEE Conf Comput Vis"},{"key":"ref41","first-page":"249","article-title":"Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction","author":"zhang","year":"2015","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.92"},{"key":"ref43","first-page":"1134","article-title":"Object detection via a multi-region and semantic segmentation-aware CNN model","author":"gidaris","year":"2015","journal-title":"Proc Int Conf Comput Vis"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/8466125\/07987752.pdf?arnumber=7987752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:28:58Z","timestamp":1642004938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7987752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":57,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2017.2730258","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2018,9]]}}}