{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T21:25:59Z","timestamp":1761427559715,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9955633","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:34:13Z","timestamp":1669732453000},"page":"535-541","source":"Crossref","is-referenced-by-count":6,"title":["Learning Sequential Contexts using Transformer for 3D Hand Pose Estimation"],"prefix":"10.1109","author":[{"given":"Leyla","family":"Khaleghi","sequence":"first","affiliation":[{"name":"Ingenuity Labs Research Institute Queen’s University,Dept. ECE,Kingston,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua","family":"Marshall","sequence":"additional","affiliation":[{"name":"Ingenuity Labs Research Institute Queen’s University,Dept. ECE,Kingston,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Etemad","sequence":"additional","affiliation":[{"name":"Ingenuity Labs Research Institute Queen’s University,Dept. ECE,Kingston,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.494"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"article-title":"and Qingxiong Yang. 3D hand pose tracking and estimation using stereo matching","year":"2016","author":"zhang","key":"ref31"},{"article-title":"A survey on visual transformer","year":"2020","author":"han","key":"ref30"},{"article-title":"Adaptively multi-view and temporal fusing transformer for 3D human pose estimation","year":"2021","author":"shuai","key":"ref37"},{"article-title":"Mvt: Multi-view vision transformer for 3d object recognition","year":"2021","author":"chen","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"103219","DOI":"10.1016\/j.cviu.2021.103219","article-title":"Skeleton-based action recognition via spatial and temporal transformer networks","volume":"208","author":"plizzari","year":"2021","journal-title":"Computer Vision and Image Understanding"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00244"},{"article-title":"Semi-supervised classification with graph convolutional networks","year":"2016","author":"kipf","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01110"},{"article-title":"Handsformer: Keypoint transformer for monocular 3D pose estimation of hands and object in interaction","year":"2021","author":"hampali","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413775"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00242"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00013"},{"key":"ref18","first-page":"436","article-title":"Using a single rgb frame for real time 3D hand pose estimation in the wild","author":"panteleris","year":"2018","journal-title":"IEEE Winter Conference on Applications of Computer Vision"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093380"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1081-7"},{"key":"ref27","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s20041074"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.525"},{"article-title":"Transformers in vision: A survey","year":"2021","author":"khan","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.04.026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00664"},{"key":"ref7","first-page":"118","article-title":"Hand pose estimation via latent 2.5 d heatmap regression","author":"iqbal","year":"2018","journal-title":"European Conference on Computer Vision"},{"article-title":"Hand pose estimation: A survey","year":"2019","author":"doosti","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01208"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.002.2200022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01109"},{"article-title":"Exploiting learnable joint groups for hand pose estimation","year":"2020","author":"li","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_8"},{"key":"ref26","first-page":"836","article-title":"Mvhm: A large-scale multi-view hand mesh benchmark for accurate 3D hand pose estimation","author":"chen","year":"2021","journal-title":"IEEE Winter Conference on Applications of Computer Vision"},{"article-title":"Multi-view video-based 3D hand pose estimation","year":"2021","author":"khaleghi","key":"ref25"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09955633.pdf?arnumber=9955633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T15:05:13Z","timestamp":1675091113000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9955633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9955633","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}