{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T18:16:12Z","timestamp":1769278572909,"version":"3.49.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650415","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers"],"prefix":"10.1109","author":[{"given":"Jianbin","family":"Jiao","sequence":"first","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xina","family":"Cheng","sequence":"additional","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijie","family":"Chen","sequence":"additional","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoting","family":"Yin","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Laboratory of Extreme Photonics and Instrumentation,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Shi","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Laboratory of Extreme Photonics and Instrumentation,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kailun","family":"Yang","sequence":"additional","affiliation":[{"name":"Hunan University,School of Robotics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref2","first-page":"38571","article-title":"ViTPose: Simple vision transformer baselines for human pose estimation","volume-title":"Proc. NeurIPS","volume":"35","author":"Xu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref5","first-page":"1263","article-title":"Coarse-tofine volumetric prediction for single-image 3D human pose","volume-title":"Proc. CVPR","author":"Pavlakos"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00444"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0273-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3057267"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00794"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref22","article-title":"Rethinking on multi-stage networks for human pose estimation","author":"Li","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"ref28","article-title":"Rethinking event-based human pose estimation with 3D event representations","author":"Yin","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"ref31","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. NeurIPS","volume":"34","author":"Rao"},{"key":"ref32","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. NeurIPS","volume":"34","author":"Xie"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3161141"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00684"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3418497"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01280"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141231"},{"key":"ref38","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236"},{"key":"ref41","first-page":"101","article-title":"Trajectory space factorization for deep videobased 3D human pose estimation","volume-title":"Proc. BMVC","author":"Lin"},{"key":"ref42","first-page":"8161","article-title":"Chirality nets for human pose regression","volume-title":"Proc. NeurIPS","volume":"32","author":"Yeh"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00763"},{"key":"ref46","article-title":"Automatic differentiation in PyTorch","author":"Paszke","year":"2017"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3603618"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650415.pdf?arnumber=10650415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:27:23Z","timestamp":1725946043000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650415","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}