{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:36:09Z","timestamp":1780763769542,"version":"3.54.1"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3250946","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T18:27:44Z","timestamp":1677695264000},"page":"5186-5199","source":"Crossref","is-referenced-by-count":12,"title":["Frame-Recurrent Video Crowd Counting"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8097-0001","authenticated-orcid":false,"given":"Yi","family":"Hou","sequence":"first","affiliation":[{"name":"National Engineering Laboratory for Video Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanghang","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Video Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Ma","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Video Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2778-3768","authenticated-orcid":false,"given":"Huizhu","family":"Jia","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Video Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4325-7741","authenticated-orcid":false,"given":"Xiaodong","family":"Xie","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Video Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","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":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.446"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190701"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2016.03.021"},{"key":"ref15","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":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013269"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00443"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00145"},{"key":"ref55","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050059"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682856"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.21"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3051371"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350881"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00334"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref46","article-title":"Joint CNN and transformer network via weakly supervised learning for efficient crowd counting","author":"wang","year":"2022","journal-title":"arXiv 2203 06388"},{"key":"ref45","article-title":"Counting varying density crowds through density guided adaptive selection CNN and transformer estimation","author":"chen","year":"2022","journal-title":"arXiv 2206 10075"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.08.015"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_3"},{"key":"ref47","article-title":"CCTrans: Simplifying and improving crowd counting with transformer","author":"tian","year":"2021","journal-title":"arXiv 2109 14483"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00070"},{"key":"ref86","first-page":"2739","article-title":"Locate, size, and count: Accurately resolving people in dense crowds via detection","volume":"43","author":"sam","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.12.002"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00629"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_15"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00839"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3043122"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/215"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.551"},{"key":"ref9","article-title":"Enhanced 3D convolutional networks for crowd counting","author":"zou","year":"2019","journal-title":"arXiv 1908 04121"},{"key":"ref4","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00319"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053955"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967852"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.04.012"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2857566"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6848"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ISCC55528.2022.9913019"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00545"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00803"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00141"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3056518"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00151"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952083"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00753"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00625"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00342"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-018-0955-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/105"},{"key":"ref76","article-title":"Crowd counting via hierarchical scale recalibration network","author":"zou","year":"2020","journal-title":"arXiv 2003 03545"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"ref1","year":"2019","journal-title":"World population prospects"},{"key":"ref39","first-page":"4340","article-title":"Virtual worlds as proxy for multi-object tracking analysis","author":"gaidon","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00395"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2740160"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00745"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00211"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2919139"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2934989"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00624"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00550"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00524"},{"key":"ref64","year":"2022","journal-title":"UNITY3D"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747070"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2943010"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45103-X_50"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412406"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.071"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_43"},{"key":"ref29","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"arXiv 1511 04119"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2542585"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.270"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10057072.pdf?arnumber=10057072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:41:02Z","timestamp":1695667262000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10057072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":90,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3250946","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}