{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T10:06:39Z","timestamp":1769853999410,"version":"3.49.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":["61902204"],"award-info":[{"award-number":["61902204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/smc53992.2023.10394434","type":"proceedings-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:32:04Z","timestamp":1706553124000},"page":"323-328","source":"Crossref","is-referenced-by-count":2,"title":["KTPose: Keypoint-Based Tokens in Vision Transformer for Human Pose Estimation"],"prefix":"10.1109","author":[{"given":"Jiale","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Qingdao University,Qingdao,China,266071"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjia","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Qingdao University,Qingdao,China,266071"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Qingdao University,Qingdao,China,266071"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00584"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref7","article-title":"Vitpose: Simple vision transformer baselines for human pose estimation","author":"Xu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20500-2_46"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"ref10","article-title":"Hrformer: High-resolution transformer for dense prediction","author":"Yuan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00712"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref14","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20185"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.329"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_42"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00198"},{"key":"ref24","first-page":"4784","article-title":"Pose recognition with cascade transformers","volume-title":"Proceedings of the IEEE\/CVF Confer-ence on Computer Vision and Pattern Recognition","author":"Xia"},{"key":"ref25","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (Neu rIPS)","author":"Rao"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.395"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_6"}],"event":{"name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Honolulu, Oahu, HI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,4]]}},"container-title":["2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10391856\/10393862\/10394434.pdf?arnumber=10394434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T13:13:45Z","timestamp":1706793225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10394434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/smc53992.2023.10394434","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}