{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T06:11:41Z","timestamp":1759385501289,"version":"3.37.3"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62022078","62021001","12150007"],"award-info":[{"award-number":["62022078","62021001","12150007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB0804204"],"award-info":[{"award-number":["2018YFB0804204"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Defense Basic Scientific Research Program","award":["JCKY2020903B002"],"award-info":[{"award-number":["JCKY2020903B002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3220055","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T20:34:17Z","timestamp":1668112457000},"page":"7130-7143","source":"Crossref","is-referenced-by-count":7,"title":["Adversarial Transformers for Weakly Supervised Object Localization"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-5754","authenticated-orcid":false,"given":"Meng","family":"Meng","sequence":"first","affiliation":[{"name":"Department of Automation, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Lunar Exploration and Space Engineering Center of CNSA, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00337"},{"key":"ref72","article-title":"Generative adversarial networks","author":"goodfellow","year":"2014","journal-title":"arXiv 1406 2661"},{"key":"ref71","article-title":"Normalized attention without probability cage","author":"richter","year":"2020","journal-title":"arXiv 2005 09561"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref76","first-page":"1","article-title":"In-sample contrastive learning and consistent attention for weakly supervised object localization","author":"ki","year":"2020","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref77","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"journal-title":"The caltech-UCSD birds-200–2011 dataset Computation & neural systems technical report","year":"2011","author":"wah","key":"ref74"},{"key":"ref39","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref38","article-title":"Transtrack: Multiple-object tracking with transformer","author":"sun","year":"2020","journal-title":"arXiv 2012 15460"},{"key":"ref78","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref33","first-page":"549","article-title":"Self-erasing network for integral object attention","author":"hou","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00960"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"ref37","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_17"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00669"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00879"},{"key":"ref60","article-title":"Adversarial machine learning at scale","author":"kurakin","year":"2016","journal-title":"arXiv 1611 01236"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref61","article-title":"Ensemble adversarial training: Attacks and defenses","author":"tram\u00e8r","year":"2017","journal-title":"arXiv 1705 07204"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref28","article-title":"Self-supervised scale equivariant network for weakly supervised semantic segmentation","author":"wang","year":"2019","journal-title":"arXiv 1909 03714"},{"key":"ref64","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2014","journal-title":"arXiv 1412 6572"},{"key":"ref27","article-title":"Comprehensive attention self-distillation for weakly-supervised object detection","author":"huang","year":"2020","journal-title":"arXiv 2010 12023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"ref67","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref69","first-page":"7324","article-title":"Making convolutional networks shift-invariant again","author":"zhang","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00093"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00526"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_29"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093566"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00560"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00706"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01347"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref51","article-title":"TrackFormer: Multi-object tracking with transformers","author":"meinhardt","year":"2021","journal-title":"arXiv 2101 02702"},{"key":"ref59","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2017","journal-title":"arXiv 1706 06083"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00498"},{"key":"ref57","first-page":"6475","article-title":"Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning","author":"mo\u0161ner","year":"2019","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00790"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_17"},{"key":"ref53","article-title":"Do we really need explicit position encodings for vision transformers?","author":"chu","year":"2021","journal-title":"arXiv 2102 10882"},{"key":"ref52","article-title":"TransGAN: Two pure transformers can make one strong GAN, and that can scale up","author":"jiang","year":"2021","journal-title":"arXiv 2102 07074"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01147"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"ref40","article-title":"Reformer: The efficient transformer","author":"kitaev \u00e5 kaiser","year":"2020","journal-title":"arXiv 2001 04451"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00759"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_37"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00732"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00541"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00232"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.381"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.382"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_37"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936111"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941644"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2396361"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112316"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00984"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2987161"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref45","article-title":"Transformer in transformer","author":"han","year":"2021","journal-title":"arXiv 2103 00112"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref47","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020","journal-title":"arXiv 2010 04159"},{"key":"ref42","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2020","journal-title":"arXiv 2012 12877"},{"key":"ref41","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09945986.pdf?arnumber=9945986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:47:14Z","timestamp":1670874434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9945986\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3220055","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2022]]}}}