{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T04:48:06Z","timestamp":1746679686819,"version":"3.37.3"},"reference-count":84,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3230902","type":"journal-article","created":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T18:38:48Z","timestamp":1671734328000},"page":"1-13","source":"Crossref","is-referenced-by-count":5,"title":["Task-Aware Weakly Supervised Object Localization With Transformer"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-5754","authenticated-orcid":false,"given":"Meng","family":"Meng","sequence":"first","affiliation":[{"name":"School of Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science, University of Science and Technology of China, Hefei, China"}]},{"given":"Zhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Deep Space Exploration Laboratory, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science, University of Science and Technology of China, Hefei, China"}]},{"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"article-title":"Training data-efficient image transformers & distillation through attention","year":"2020","author":"touvron","key":"ref57"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00337"},{"article-title":"Reformer: The efficient transformer","year":"2020","author":"kitaev","key":"ref56"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00879"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.381"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00455"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref55"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00984"},{"article-title":"TransTrack: Multiple-object tracking with transformer","year":"2020","author":"sun","key":"ref54"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00232"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.382"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01386"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01423"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00106"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.10.022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_17"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00669"},{"key":"ref42","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00960"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00706"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093566"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00593"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876304"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2999099"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00541"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","year":"2020","author":"zheng","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2303095"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref81","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc IEEE Int Conf Mach Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_17"},{"article-title":"Explaining and harnessing adversarial examples","year":"2014","author":"goodfellow","key":"ref83"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref35","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","author":"cuturi","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00922"},{"key":"ref34","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_22"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_37"},{"article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","year":"2020","author":"zhu","key":"ref30"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00341"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00020"},{"key":"ref76","first-page":"3","article-title":"In-sample contrastive learning and consistent attention for weakly supervised object localization","author":"ki","year":"2020","journal-title":"Proc IEEE Asian Conf Comput Vis"},{"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":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref70","article-title":"The caltech-ucsd birds-200–2011 dataset. computation & neural systems technical report","author":"wah","year":"2011","journal-title":"California Institute of Technology"},{"article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"howard","key":"ref73"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref72"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01347"},{"article-title":"Unsupervised learning of visual features by contrasting cluster assignments","year":"2020","author":"caron","key":"ref68"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_29"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054600"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00732"},{"article-title":"AAformer: Auto-aligned transformer for person re-identification","year":"2021","author":"zhu","key":"ref69"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01147"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_37"},{"article-title":"Do we really need explicit position encodings for vision transformers?","year":"2021","author":"chu","key":"ref66"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00759"},{"article-title":"TransGAN: Two transformers can make one strong GAN","year":"2021","author":"jiang","key":"ref65"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"ref29","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"article-title":"Transformer in transformer","year":"2021","author":"han","key":"ref60"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"article-title":"Trackformer: Multi-object tracking with transformers","year":"2021","author":"meinhardt","key":"ref61"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09996553.pdf?arnumber=9996553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T22:24:26Z","timestamp":1686090266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9996553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3230902","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2022]]}}}