{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:17:44Z","timestamp":1780762664769,"version":"3.54.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62203184,W2421093"],"award-info":[{"award-number":["62203184,W2421093"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003807","name":"Jilin Province","doi-asserted-by":"publisher","award":["20250205079GH"],"award-info":[{"award-number":["20250205079GH"]}],"id":[{"id":"10.13039\/501100003807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFF0905400"],"award-info":[{"award-number":["2023YFF0905400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2341229"],"award-info":[{"award-number":["U2341229"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00835","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation"],"prefix":"10.1109","author":[{"given":"Runyang","family":"Feng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Jilin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyung Jin","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Birmingham"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tze Ho Elden","family":"Tse","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boeun","family":"Kim","sequence":"additional","affiliation":[{"name":"Dankook University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixing","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00542"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2980194"},{"key":"ref3","first-page":"3027","article-title":"Learning temporal pose estimation from sparsely-labeled videos","volume-title":"Advances in Neural Information Processing Systems","author":"Bertasius","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02029"},{"key":"ref7","article-title":"An image is worth 16\u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01151"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01643"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01365"},{"key":"ref12","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"1474","article-title":"Hippo: Recurrent memory with optimal polynomial projections","volume":"33","author":"Gu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume":"34","author":"Gu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11012-3_17"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00103"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.495"},{"key":"ref20","first-page":"3192","article-title":"Black","volume-title":"Towards understanding action recognition. In Proceedings of the IEEE international conference on computer vision","author":"Jhuang","year":"2013"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00581"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_26"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01225"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"ref26","volume-title":"Vmamba: Visual state space model","author":"Liu","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01073"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00546"},{"key":"ref30","article-title":"Long range language modeling via gated state spaces","author":"Mehta","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Associative embedding: End-to-end learning for joint detection and grouping","author":"Newell","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00704"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_3"},{"key":"ref35","article-title":"Glu variants improve transformer","author":"Shazeer","year":"2020","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Simplified state space layers for sequence modeling","author":"Smith","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.590"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01110"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref43","article-title":"Pose flow: Efficient online pose tracking","author":"Xiu","year":"2018","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2795"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00798"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01030"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11012-3_19"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_35"},{"key":"ref49","article-title":"Fastpose: Towards real-time pose estimation and tracking via scale-normalized multi-task networks","author":"Zhang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_36"},{"key":"ref51","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443310.pdf?arnumber=11443310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:19Z","timestamp":1777613299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00835","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}