{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:34:36Z","timestamp":1732041276752,"version":"3.28.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/iccv48922.2021.01145","type":"proceedings-article","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T22:08:02Z","timestamp":1646086082000},"page":"11636-11645","source":"Crossref","is-referenced-by-count":337,"title":["3D Human Pose Estimation with Spatial and Temporal Transformers"],"prefix":"10.1109","author":[{"given":"Ce","family":"Zheng","sequence":"first","affiliation":[{"name":"University of Central Florida,Center for Research in Computer Vision,USA"}]},{"given":"Sijie","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Central Florida,Center for Research in Computer Vision,USA"}]},{"given":"Matias","family":"Mendieta","sequence":"additional","affiliation":[{"name":"University of Central Florida,Center for Research in Computer Vision,USA"}]},{"given":"Taojiannan","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Central Florida,Center for Research in Computer Vision,USA"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Central Florida,Center for Research in Computer Vision,USA"}]},{"given":"Zhengming","family":"Ding","sequence":"additional","affiliation":[{"name":"Tulane University,Department of Computer Science,USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1176"},{"key":"ref38","first-page":"764","article-title":"Motion guided 3d pose estimation from videos","author":"wang","year":"2020","journal-title":"European Conference on Computer Vision"},{"journal-title":"the European Conference on Computer Vision (ECCV)","article-title":"Exploiting temporal information for 3d human pose estimation","year":"2018","author":"hossain","key":"ref33"},{"journal-title":"CVPR","year":"2019","author":"pavllo","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00763"},{"journal-title":"Automatic differentiation in pytorch","year":"2017","author":"paszke","key":"ref30"},{"journal-title":"Attention is all you need","year":"2017","author":"vaswani","key":"ref37"},{"article-title":"Training data-efficient image transformers & distillation through attention","year":"2020","author":"touvron","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0273-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073596"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"journal-title":"ECCV","article-title":"I2l-meshnet: Image-to-lixel prediction network for accurate 3d human pose and mesh estimation from a single rgb image","year":"2020","author":"moon","key":"ref29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236"},{"article-title":"Adaptive input representations for neural language modeling","year":"2018","author":"baevski","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00621"},{"journal-title":"BMVC","article-title":"Trajectory space factorization for deep video-based 3d human pose estimation","year":"2019","author":"lin","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00228"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_19"},{"article-title":"End-to-end human pose and mesh reconstruction with transformers","year":"2020","author":"lin","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00511"},{"article-title":"Deformable detr: Deformable transformers for end-to-end object detection","year":"2020","author":"zhu","key":"ref50"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"ref11","first-page":"668","article-title":"Learning 3d human pose from structure and motion","author":"dabral","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"article-title":"Transpose: Towards explainable human pose estimation by transformer","year":"2020","author":"yang","key":"ref40"},{"journal-title":"ICLRE","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2021","author":"dosovitskiy","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"article-title":"A survey on visual transformer","year":"2020","author":"han","key":"ref14"},{"key":"ref15","first-page":"646","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"article-title":"Transformers in vision: A survey","year":"2021","author":"khan","key":"ref17"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref18"},{"journal-title":"International Conference on Learning Representations (ICLR)","article-title":"Semi-supervised classification with graph convolutional networks","year":"2017","author":"kipf","key":"ref19"},{"key":"ref4","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"journal-title":"IEEE Transactions on Circuits and Systems for Video Technology","article-title":"Anatomy-aware 3d human pose estimation with bone-based pose decomposition","year":"2021","author":"chen","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00081"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.51"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00235"},{"journal-title":"Deep learning-based human pose estimation A survey","year":"2020","author":"zheng","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00354"},{"key":"ref48","first-page":"4917","article-title":"Towards deeper graph neural networks with differentiable group normalization","volume":"33","author":"zhou","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","year":"2020","author":"zheng","key":"ref47"},{"journal-title":"Chirality nets for human pose regression","year":"2019","author":"yeh","key":"ref42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00740"},{"journal-title":"ECCV","article-title":"Srnet: Improving generalization in 3d human pose estimation with a split-and-recombine approach","year":"2020","author":"zeng","key":"ref43"}],"event":{"name":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","start":{"date-parts":[[2021,10,10]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2021,10,17]]}},"container-title":["2021 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9709627\/9709628\/09710244.pdf?arnumber=9710244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T19:39:42Z","timestamp":1658864382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9710244\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv48922.2021.01145","relation":{},"subject":[],"published":{"date-parts":[[2021,10]]}}}
