{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T06:15:17Z","timestamp":1767766517746,"version":"3.48.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"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":[[2025,7,12]]},"DOI":"10.1109\/indin64977.2025.11279684","type":"proceedings-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:33:35Z","timestamp":1767724415000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["MiTPose: Multi-Granularity Guided Vision Transformer for Human Pose Estimation"],"prefix":"10.1109","author":[{"given":"Yunfeng","family":"Wu","sequence":"first","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"}]},{"given":"Qizhong","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Computer Science,Liverpool,UK"}]},{"given":"Yize","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"}]},{"given":"Jun","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"}]},{"given":"Zhuozhi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"}]},{"given":"Yuhao","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Computer Science,Liverpool,UK"}]},{"given":"Yong","family":"Yue","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"}]},{"given":"Xiaohui","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_33"},{"article-title":"Directpose: Direct end-to-end multi-person pose estimation","year":"2019","author":"Tian","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"issue":"6","key":"ref5","article-title":"Transpose: Towards explainable human pose estimation by transformer","volume":"2","author":"Yang","year":"2020"},{"key":"ref6","first-page":"38571","article-title":"Vitpose: Simple vision transformer baselines for human pose estimation","volume":"35","author":"Xu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"article-title":"Regionvit: Regional-to-local attention for vision transformers","year":"2021","author":"Chen","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_43"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00596"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.512"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01084"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_6"},{"key":"ref16","article-title":"Joint training of a convolutional network and a graphical model for human pose estimation","volume":"27","author":"Tompson","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01030"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00198"},{"article-title":"Hrformer: High-resolution transformer for dense prediction","year":"2021","author":"Yuan","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3175432"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3471928"},{"article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","year":"2015","author":"Ioffe","key":"ref25"},{"article-title":"Gaussian error linear units (gelus)","year":"2016","author":"Hendrycks","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00574"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00554"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"volume-title":"Openmmlab pose estimation toolbox and bench-mark","year":"2020","author":"Contributors","key":"ref32"},{"key":"ref33","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke","year":"2019"}],"event":{"name":"2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)","start":{"date-parts":[[2025,7,12]]},"location":"Kunming, China","end":{"date-parts":[[2025,7,15]]}},"container-title":["2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11278897\/11278845\/11279684.pdf?arnumber=11279684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T06:09:31Z","timestamp":1767766171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11279684\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,12]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/indin64977.2025.11279684","relation":{},"subject":[],"published":{"date-parts":[[2025,7,12]]}}}