{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T02:42:36Z","timestamp":1775184156715,"version":"3.50.1"},"reference-count":68,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371353"],"award-info":[{"award-number":["62371353"]}],"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":["62172321"],"award-info":[{"award-number":["62172321"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3329985","type":"journal-article","created":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T18:03:59Z","timestamp":1698948239000},"page":"124833-124844","source":"Crossref","is-referenced-by-count":5,"title":["Transformer-Based Feature Aggregation and Stitching Network for Crowd Counting"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9843-8104","authenticated-orcid":false,"given":"Kehao","family":"Wang","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, Wuhan Technology and Business University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Wuhan University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiqi","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Wuhan University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Civil Engineering, Architecture and Environment, Hubei University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhichao","family":"Shao","sequence":"additional","affiliation":[{"name":"Army Engineering University of PLA, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref57","first-page":"2739","article-title":"Locate, size, and count: Accurately resolving people in dense crowds via detection","volume":"43","author":"sam","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2919139"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13664-8"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04499-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350898"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_45"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00629"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055631"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2935244"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-022-03749-2"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-023-03987-y"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00211"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01302"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00131"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01542-z"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.113"},{"key":"ref45","article-title":"Boosting crowd counting with transformers","author":"sun","year":"2021","journal-title":"arXiv 2105 10926"},{"key":"ref48","first-page":"1595","article-title":"Distribution matching for crowd counting","volume":"33","author":"wang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref42","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020","journal-title":"arXiv 2010 04159"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3445-y"},{"key":"ref43","article-title":"End-to-end object detection with adaptive clustering transformer","author":"zheng","year":"2020","journal-title":"arXiv 2011 09315"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00443"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116688"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DCABES.2011.62"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICPICS50287.2020.9202071"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref3","first-page":"21","article-title":"SSD: Single shot MultiBox detector","volume":"9905","author":"liu","year":"2016","journal-title":"Vision Computer"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459191"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6839"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00334"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00689"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00122"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00465"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2956091"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00550"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CIS.2019.00079"},{"key":"ref39","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Vision Computer"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053761"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.31.4.041214"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.329"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-023-02090-1"},{"key":"ref23","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3268226"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2852481"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_1"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-021-00877-4"},{"key":"ref22","article-title":"On the relationship between self-attention and convolutional layers","author":"cordonnier","year":"2019","journal-title":"arXiv 1911 03584"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.05.013"},{"key":"ref21","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00131"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00186"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1089\/big.2022.0039"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3390\/rs14246363"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107616"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10305591.pdf?arnumber=10305591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T15:31:20Z","timestamp":1701271880000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10305591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3329985","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}