{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T23:12:29Z","timestamp":1768086749248,"version":"3.49.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956693","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"4529-4536","source":"Crossref","is-referenced-by-count":5,"title":["End-to-end 3D Human Pose Estimation with Transformer"],"prefix":"10.1109","author":[{"given":"Bowei","family":"Zhang","sequence":"first","affiliation":[{"name":"Guizhou University of Finance and Economics,Novel Computer Architecture Laboratory, School of Information,Guiyang,550025"}]},{"given":"Peng","family":"Cui","sequence":"additional","affiliation":[{"name":"Guizhou University of Finance and Economics,Novel Computer Architecture Laboratory, School of Information,Guiyang,550025"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Orinet: A fully convolutional network for 3d human pose estimation","author":"luo","year":"2018","journal-title":"BMVC"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.284"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.51"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.610"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01096"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.170"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00354"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00551"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.284"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.130"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.84"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.326"},{"key":"ref12","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"ICLRE"},{"key":"ref14","article-title":"Scaling vision transformers","author":"zhai","year":"2021"},{"key":"ref15","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref17","first-page":"6881","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"zheng","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref18","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020"},{"key":"ref19","first-page":"3582","article-title":"Using k-poselets for detecting people and localizing their keypoints","author":"gkioxari","year":"2014","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref4","first-page":"752","article-title":"I2l-meshnet: Image-to-lixel prediction network for accurate 3d human pose and mesh estimation from a single rgb image","author":"moon","year":"2020","journal-title":"Computer Vision–ECCV 2020 16th European Conference Glasgow UK August 23–28 2020 Proceedings Part VII 16"},{"key":"ref27","article-title":"Deep learning-based human pose estimation: A survey","author":"zheng","year":"2020"},{"key":"ref3","first-page":"529","article-title":"Integral human pose regression","author":"sun","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392410"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00444"},{"key":"ref5","first-page":"8163","article-title":"Chirality nets for human pose regression","volume":"32","author":"yeh","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"7291","article-title":"Realtime multi-person 2d pose estimation using part affinity fields","author":"cao","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_33"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00763"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.139"},{"key":"ref20","article-title":"Articulated pose estimation by a graphical model with image dependent pairwise relations","author":"chen","year":"2014","journal-title":"NeurlPS"},{"key":"ref22","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00162"},{"key":"ref24","article-title":"Tf-pose: Direct human pose estimation with transformers","author":"mao","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00797"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00847"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956693.pdf?arnumber=9956693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:06:39Z","timestamp":1671480399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956693","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}