{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T23:12:59Z","timestamp":1784070779086,"version":"3.55.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["61872241"],"award-info":[{"award-number":["61872241"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62077037"],"award-info":[{"award-number":["62077037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["18410750700"],"award-info":[{"award-number":["18410750700"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["17411952600"],"award-info":[{"award-number":["17411952600"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Lin-Gang Area Smart Manufacturing Special Project","award":["ZN2018020202-3"],"award-info":[{"award-number":["ZN2018020202-3"]}]},{"name":"Project of Shanghai Municipal Health Commission","award":["2018ZHYL0230"],"award-info":[{"award-number":["2018ZHYL0230"]}]},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["P0030419"],"award-info":[{"award-number":["P0030419"]}],"id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["P0030929"],"award-info":[{"award-number":["P0030929"]}],"id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["P0035358"],"award-info":[{"award-number":["P0035358"]}],"id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2021.3120873","type":"journal-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T17:57:54Z","timestamp":1634752674000},"page":"50-61","source":"Crossref","is-referenced-by-count":542,"title":["EAPT: Efficient Attention Pyramid Transformer for Image Processing"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8805-7129","authenticated-orcid":false,"given":"Xiao","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Computer Science, Shanghai Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuzhou","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Shanghai Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8510-2556","authenticated-orcid":false,"given":"Bin","family":"Sheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1503-0240","authenticated-orcid":false,"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3381-214X","authenticated-orcid":false,"given":"David Dagan","family":"Feng","sequence":"additional","affiliation":[{"name":"Biomedical and Multimedia Information Technology Research Group, School of Information Technologies, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037496"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2929949"},{"key":"ref4","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3034540"},{"key":"ref6","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref7","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref9","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00915"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965491"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475467"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref17","first-page":"6327","article-title":"Learning to encode position for transformer with continuous dynamical model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xuanqing","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3054509"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2894964"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869277"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2928491"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2669982"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00931"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186066"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref27","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref31","first-page":"1123","article-title":"RepPoints V2: Verification meets regression for object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref37","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref39","first-page":"1","article-title":"RelationNet++ : Bridging visual representations for object detection via transformer decoder","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Chi","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"ref44","first-page":"1","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00685"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_12"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09580642.pdf?arnumber=9580642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:32:54Z","timestamp":1705015974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9580642\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3120873","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}