{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:03:12Z","timestamp":1784905392050,"version":"3.55.0"},"reference-count":40,"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":[{"name":"National Science Fund for Distinguished Young Scholars of China","award":["62125203"],"award-info":[{"award-number":["62125203"]}]},{"name":"Key Program of the National Natural Science Foundation of China","award":["61932013"],"award-info":[{"award-number":["61932013"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276143"],"award-info":[{"award-number":["62276143"]}],"id":[{"id":"10.13039\/501100001809","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.2023.3248144","type":"journal-article","created":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T18:46:21Z","timestamp":1677177981000},"page":"1521-1528","source":"Crossref","is-referenced-by-count":29,"title":["HRNeXt: High-Resolution Context Network for Crowd Pose Estimation"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8034-6030","authenticated-orcid":false,"given":"Qun","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1728-2588","authenticated-orcid":false,"given":"Ziyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1815-2793","authenticated-orcid":false,"given":"Fu","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref35","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018"},{"key":"ref12","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00098"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref11","first-page":"7281","article-title":"HRFormer: High-resolution vision transformer for dense predict","author":"yuan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","article-title":"OpenMMLab pose estimation toolbox and benchmark","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00311"},{"key":"ref32","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","author":"xie","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00712"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_29"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"ref19","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"Proc Int Conf Learn Representation"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref24","first-page":"1305","article-title":"CondConv: Conditionally parameterized convolutions for efficient inference","author":"yang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"1","article-title":"BAM: Bottleneck attention module","author":"park","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref26","article-title":"Visual attention network","author":"guo","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref22","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/153"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01030"},{"key":"ref29","article-title":"Gaussian error linear units (GELUs)","author":"hendrycks","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.395"},{"key":"ref3","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"0","journal-title":"Proc 14th Eur Conf Comput Vis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00574"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10050764.pdf?arnumber=10050764","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:39:34Z","timestamp":1685381974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10050764\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3248144","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}