{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:51:54Z","timestamp":1771703514751,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province, China","doi-asserted-by":"publisher","award":["2020J01082"],"award-info":[{"award-number":["2020J01082"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/tcsvt.2022.3213206","type":"journal-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:18:45Z","timestamp":1665433125000},"page":"1697-1709","source":"Crossref","is-referenced-by-count":17,"title":["UformPose: A U-Shaped Hierarchical Multi-Scale Keypoint-Aware Framework for Human Pose Estimation"],"prefix":"10.1109","volume":"33","author":[{"given":"You-Jie","family":"Wang","sequence":"first","affiliation":[{"name":"Key Laboratory for Computer Vision and Pattern Recognition and the College of Computer Science and Technology, Huaqiao University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7596-3299","authenticated-orcid":false,"given":"Yan-Min","family":"Luo","sequence":"additional","affiliation":[{"name":"Key Laboratory for Computer Vision and Pattern Recognition and the College of Computer Science and Technology, Huaqiao University, Xiamen, China"}]},{"given":"Gui-Hu","family":"Bai","sequence":"additional","affiliation":[{"name":"Key Laboratory for Computer Vision and Pattern Recognition and the College of Computer Science and Technology, Huaqiao University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8041-6326","authenticated-orcid":false,"given":"Jing-Ming","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.601"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref9","first-page":"2274","article-title":"Associative embedding: End-to-end learning for joint detection and grouping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Newell"},{"key":"ref10","first-page":"8420","article-title":"Deep network for the integrated 3D sensing of multiple people in natural images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zanfir"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.533"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01225"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2865666"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104198"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-03889-z"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2707477"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref26","article-title":"Human pose estimation with spatial contextual information","author":"Zhang","year":"2019","journal-title":"arXiv:1901.01760"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.137"},{"key":"ref28","first-page":"1","article-title":"CRF-CNN: Modeling structured information in human pose estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref29","article-title":"Anti-confusing: Region-aware network for human pose estimation","author":"Cao","year":"2019","journal-title":"arXiv:1905.00996"},{"key":"ref30","article-title":"TransPose: Towards explainable human pose estimation by transformer","author":"Yang","year":"2019","journal-title":"arXiv:2012.14214"},{"key":"ref31","article-title":"End-to-end trainable multi-instance pose estimation with transformers","author":"Stoffl","year":"2021","journal-title":"arXiv:2103.12115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"ref33","article-title":"HRFormer: High-resolution transformer for dense prediction","author":"Yuan","year":"2021","journal-title":"arXiv:2110.09408"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00311"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.108"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref40","article-title":"MISSFormer: An effective medical image segmentation transformer","author":"Huang","year":"2021","journal-title":"arXiv:2109.07162"},{"key":"ref41","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00712"},{"key":"ref44","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01164"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2952779"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3005522"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3153044"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10091959\/09913935.pdf?arnumber=9913935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:48:05Z","timestamp":1705963685000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9913935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":52,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3213206","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4]]}}}