{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T05:31:05Z","timestamp":1776403865768,"version":"3.51.2"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2019R1A2C2006123"],"award-info":[{"award-number":["NRF-2019R1A2C2006123"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation","award":["2020-0-01361"],"award-info":[{"award-number":["2020-0-01361"]}]},{"DOI":"10.13039\/501100002573","name":"Yonsei University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002573","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ICT R&D program of MSIP\/IITP","award":["R7124-16-0004"],"award-info":[{"award-number":["R7124-16-0004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,12,1]]},"DOI":"10.1109\/tpami.2020.2999099","type":"journal-article","created":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T21:59:20Z","timestamp":1591048760000},"page":"4256-4271","source":"Crossref","is-referenced-by-count":86,"title":["Attention-Based Dropout Layer for Weakly Supervised Single Object Localization and Semantic Segmentation"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4726-4436","authenticated-orcid":false,"given":"Junsuk","family":"Choe","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5254-9685","authenticated-orcid":false,"given":"Seungho","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6796-1058","authenticated-orcid":false,"given":"Hyunjung","family":"Shim","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref72","article-title":"Hide-and-seek: A data augmentation technique for weakly-supervised localization and beyond","author":"singh","year":"2018"},{"key":"ref71","first-page":"109","article-title":"Efficient inference in fully connected CRFs with Gaussian edge potentials","author":"kr\u00e4henb\u00fchl","year":"2011","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0977-3"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.770"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref39","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.128"},{"key":"ref38","first-page":"454","article-title":"TS2C: Tight box mining with surrounding segmentation context for weakly supervised object detection","author":"wei","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.535"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.27"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00960"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.382"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00759"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2636150"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref62","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref28","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2014","journal-title":"Proc Workshop Int Conf Learn Representations"},{"key":"ref64","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844853"},{"key":"ref65","article-title":"Network in network","author":"min","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref66","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"chen","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.209"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00733"},{"key":"ref68","article-title":"Tensorpack","author":"wu","year":"2016"},{"key":"ref69","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc USENIX Conf Operating Syst Des Implementation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.381"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2688133"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.204"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.457"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.366"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_15"},{"key":"ref50","first-page":"189","article-title":"Analysis on the dropout effect in convolutional neural networks","author":"park","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/nrn755"},{"key":"ref59","first-page":"4055","article-title":"Image transformer","author":"parmar","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref57","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref56","first-page":"85","article-title":"Image inpainting for irregular holes using partial convolutions","author":"liu","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref54","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"},{"key":"ref53","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.120"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.52"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.382"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.379"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_22"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.631"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123455"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.545"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_28"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_37"},{"key":"ref8","first-page":"1637","article-title":"Weakly-supervised discovery of visual pattern configurations","author":"song","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref7","first-page":"ii-1611","article-title":"On learning to localize objects with minimal supervision","author":"song","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.309"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00232"},{"key":"ref47","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","article-title":"BAM: Bottleneck attention module","author":"park","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref44","article-title":"The Caltech-UCSD Birds-200–2011 dataset","author":"wah","year":"2011"},{"key":"ref43","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9600479\/09105077.pdf?arnumber=9105077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:12Z","timestamp":1652194152000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9105077\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,1]]},"references-count":76,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.2999099","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,1]]}}}