{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:24Z","timestamp":1792786944374,"version":"4.5.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NIH","award":["5R01NS135613"],"award-info":[{"award-number":["5R01NS135613"]}]},{"name":"NSF","award":["2124277"],"award-info":[{"award-number":["2124277"]}]},{"name":"IARPA","award":["2022-21102100005"],"award-info":[{"award-number":["2022-21102100005"]}],"id":[{"id":"https:\/\/ror.org\/04hm2xn53","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3701408","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:51:25Z","timestamp":1780948285000},"page":"12631-12643","source":"Crossref","is-referenced-by-count":0,"title":["Transformers With Joint Tokens and Local-Global Attention for Efficient Human Pose Estimation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1994-4816","authenticated-orcid":false,"given":"Kaleab A.","family":"Kinfu","sequence":"first","affiliation":[{"name":"University of Pennsylvania","place":["Philadelphia, PA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1838-0761","authenticated-orcid":false,"given":"Rene","family":"Vidal","sequence":"additional","affiliation":[{"name":"University of Pennsylvania","place":["Philadelphia, PA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008935"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2010.80"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.059"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-813445-0.00005-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3233\/978-1-61499-022-2-320"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17688-3_31"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86365-4_31"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207296"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tbme.2025.3637089"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"ref15","first-page":"7281","article-title":"HRFormer: High-resolution transformer for dense prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2795"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3103980"},{"key":"ref21","first-page":"1799","article-title":"Joint training of a convolutional network and a graphical model for human pose estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tompson","year":"2014"},{"key":"ref22","article-title":"Numerical coordinate regression with convolutional neural networks","author":"Nibali","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icme.2019.00256"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00466"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01112"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00098"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3603618"},{"key":"ref30","article-title":"Efficient vision transformer for human pose estimation via patch selection","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Kinfu","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref36","first-page":"2277","article-title":"Associative Embedding: End-to-end learning for joint detection and grouping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Newell","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01079"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01030"},{"key":"ref42","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref47","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019"},{"key":"ref48","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref49","first-page":"12786","article-title":"TokenLearner: Adaptive space-time tokenization for videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ryoo","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00010"},{"key":"ref51","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rao","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref53","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liang","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR54900.2022.00048"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01199"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/280811.280913"},{"key":"ref57","first-page":"3690","article-title":"PoWER-BERT: Accelerating BERT inference via progressive word-vector elimination","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goyal","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.106"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref62","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Raghu","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref64","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00574"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11554363.pdf?arnumber=11554363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T19:09:52Z","timestamp":1790622592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11554363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":66,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3701408","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}