{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T23:14:11Z","timestamp":1779318851917,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772527"],"award-info":[{"award-number":["61772527"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1109\/tip.2018.2865280","type":"journal-article","created":{"date-parts":[[2018,8,13]],"date-time":"2018-08-13T18:32:45Z","timestamp":1534185165000},"page":"113-126","source":"Crossref","is-referenced-by-count":149,"title":["Attention CoupleNet: Fully Convolutional Attention Coupling Network for Object Detection"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8544-410X","authenticated-orcid":false,"given":"Yousong","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoyang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyun","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9118-2780","authenticated-orcid":false,"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanqing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"liu","year":"2016","journal-title":"Fully convolutional attention networks for fine-grained recognition"},{"key":"ref38","first-page":"3640","article-title":"Attention to scale: Scale-aware semantic image segmentation","author":"chen","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref33","first-page":"2874","article-title":"Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks","author":"bell","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2308616"},{"key":"ref31","first-page":"2980","article-title":"Mask R-CNN","author":"he","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref37","author":"sharma","year":"2016","journal-title":"Action recognition using visual attention"},{"key":"ref36","first-page":"6450","article-title":"Residual attention network for image classification","author":"wang","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref35","first-page":"354","article-title":"A unified multi-scale deep convolutional neural network for fast object detection","author":"cai","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref34","first-page":"1134","article-title":"Object detection via a multi-region and semantic segmentation-aware CNN model","author":"gidaris","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref10","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.873443"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299080"},{"key":"ref13","first-page":"2881","article-title":"Pyramid scene parsing network","author":"zhao","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref15","first-page":"4146","article-title":"Couplenet: Coupling global structure with local parts for object detection","author":"zhu","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2300479"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2363408"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917362"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2762591"},{"key":"ref4","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"416","article-title":"Scale-adaptive deconvolutional regression network for pedestrian detection","author":"zhu","year":"2016","journal-title":"Proc ACCV"},{"key":"ref3","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 (CVPR)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref29","author":"huang","year":"2015","journal-title":"Densebox Unifying landmark localization with end to end object detection"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref8","article-title":"Neural machine translation by jointly learning to align and translate","volume":"abs 1409","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref7","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","first-page":"1440","article-title":"Fast R-CNN","author":"girshick","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref9","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2609814"},{"key":"ref21","first-page":"770","article-title":"Deep residual learning for image recognition","author":"he","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref24","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","article-title":"Object detectors emerge in deep scene CNNs","volume":"abs 1412","author":"zhou","year":"2014","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713099"},{"key":"ref26","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"redmon","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref43","first-page":"845","article-title":"HyperNet: Towards accurate region proposal generation and joint object detection","author":"kong","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref25","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8468142\/08434341.pdf?arnumber=8434341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:10:53Z","timestamp":1657746653000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8434341\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":43,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tip.2018.2865280","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1]]}}}