{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T09:05:48Z","timestamp":1784365548431,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3088605","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T21:30:01Z","timestamp":1624915801000},"page":"5920-5932","source":"Crossref","is-referenced-by-count":125,"title":["Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2572-8156","authenticated-orcid":false,"given":"Bin-Bin","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong-Yu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2991527"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2549459"},{"key":"ref33","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref32","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.349"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2545300"},{"key":"ref36","first-page":"13440","article-title":"Orderless recurrent models for multi-label classification","author":"yazici","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002185"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.03.006"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref27","first-page":"937","article-title":"Learning attentional policies for tracking and recognition in video with deep networks","author":"bazzani","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref29","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICLR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299097"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref24","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref26","first-page":"3286","article-title":"BING: Binarized normed gradients for objectness estimation at 300fps","author":"cheng","year":"2014","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.219"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00082"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3025814"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref13","first-page":"6714","article-title":"Order-free RNN with visual attention for multi-label classification","author":"chen","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell (AAAI)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3063496","article-title":"Learning graph convolutional networks for multi-label recognition and applications","author":"chen","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref17","first-page":"197","article-title":"Forest before trees: The precedence of global features in visual perception","volume":"5","author":"navon","year":"1969","journal-title":"Perception Psychophys"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.pneurobio.2007.09.001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.00277"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_41"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.39"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491929"},{"key":"ref8","first-page":"6730","article-title":"Recurrent attentional reinforcement learning for multi-label image recognition","author":"chen","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell (AAAI)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.37"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref46","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00139"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref42","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2011.10.002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00170"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09466402.pdf?arnumber=9466402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T21:15:32Z","timestamp":1672607732000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9466402\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3088605","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}