{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:36:04Z","timestamp":1774539364976,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["61931012"],"award-info":[{"award-number":["61931012"]}],"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":["62301278"],"award-info":[{"award-number":["62301278"]}],"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":["62371254"],"award-info":[{"award-number":["62371254"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province of China","doi-asserted-by":"publisher","award":["BK20230362"],"award-info":[{"award-number":["BK20230362"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,1,1]]},"DOI":"10.1109\/jiot.2024.3470751","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T13:29:47Z","timestamp":1727702987000},"page":"869-880","source":"Crossref","is-referenced-by-count":12,"title":["Hierarchical Local Temporal Network for 2D-to-3D Human Pose Estimation"],"prefix":"10.1109","volume":"12","author":[{"given":"Xin","family":"Yan","sequence":"first","affiliation":[{"name":"College of Automation and Artificial Intelligence, Nanjing University of Posts and Telecommunication, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2336-8521","authenticated-orcid":false,"given":"Jiucheng","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Automation and Artificial Intelligence, Nanjing University of Posts and Telecommunication, Nanjing, China"}]},{"given":"Mengqi","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Automation and Artificial Intelligence, Nanjing University of Posts and Telecommunication, Nanjing, China"}]},{"given":"Haolun","family":"Li","sequence":"additional","affiliation":[{"name":"College of Automation and Artificial Intelligence, Nanjing University of Posts and Telecommunication, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0148-3713","authenticated-orcid":false,"given":"Hao","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Automation and Artificial Intelligence, Nanjing University of Posts and Telecommunication, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01080"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152690"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3131937"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00706"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068645"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01479"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01364"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12012"},{"key":"ref10","first-page":"7745","article-title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Pavllo"},{"key":"ref11","first-page":"2272","article-title":"Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Cai"},{"key":"ref12","first-page":"11636","article-title":"3D human pose estimation with spatial and temporal transformers","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Zheng"},{"key":"ref13","first-page":"13222","article-title":"MixSTE: Seq2seq mixed spatio-temporal encoder for 3D human pose estimation in video","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Zhang"},{"key":"ref14","first-page":"13137","article-title":"MHFormer: Multi-hypothesis transformer for 3D human pose estimation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Li"},{"key":"ref15","first-page":"5137","article-title":"2D\/3D pose estimation and action recognition using multitask deep learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Luvizon"},{"key":"ref16","first-page":"1263","article-title":"Coarse-to-fine volumetric prediction for single-image 3D human pose","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Pavlakos"},{"key":"ref17","first-page":"11179","article-title":"Probabilistic monocular 3D human pose estimation with normalizing flows","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Wehrbein"},{"key":"ref18","first-page":"2659","article-title":"A simple yet effective baseline for 3D human pose estimation","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Martinez"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_30"},{"issue":"1","key":"ref20","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/TCSVT.2021.3057267","article-title":"Anatomy-aware 3D human pose estimation with bone-based pose decomposition","volume":"32","author":"Chen","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref24","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017","journal-title":"arXiv:1609.02907"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01124"},{"key":"ref26","first-page":"16100","article-title":"Graph stacked hourglass networks for 3D human pose estimation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Xu"},{"key":"ref27","first-page":"11457","article-title":"Modulated graph convolutional network for 3D human pose estimation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Zou"},{"key":"ref28","first-page":"3420","article-title":"Semantic graph convolutional networks for 3D human pose regression","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Zhao"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00810"},{"key":"ref30","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. 31st Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"ref33","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"arXiv:2010.11929"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"ref35","first-page":"2902","article-title":"Uplift and upsample: Efficient 3D human pose estimation with uplifting transformers","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis. (WACV)","author":"Einfalt"},{"key":"ref36","first-page":"4790","article-title":"3D human pose estimation with spatio-temporal Criss-cross attention","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Tang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/65"},{"key":"ref38","article-title":"Refined temporal pyramidal compression-and-amplification transformer for 3D human pose estimation","author":"Li","year":"2024","journal-title":"arXiv:2309.01365"},{"key":"ref39","article-title":"Double-chain constraints for 3D human pose estimation in images and videos","author":"Kang","year":"2023","journal-title":"arXiv:2308.05298"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321438"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00603"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342204"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01464"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01356"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126500"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00763"},{"key":"ref50","first-page":"7103","article-title":"Cascaded pyramid network for multi-person pose estimation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Chen"},{"key":"ref51","first-page":"20406","article-title":"GraFormer: Graph-oriented transformer for 3D pose estimation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Zhao"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323874"},{"key":"ref53","article-title":"HSTFormer: Hierarchical spatial-temporal transformers for 3D human pose estimation","author":"Qian","year":"2023","journal-title":"arXiv:2301.07322"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/10811462\/10699344.pdf?arnumber=10699344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T21:09:22Z","timestamp":1771362562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10699344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,1]]},"references-count":53,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2024.3470751","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,1]]}}}