{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T17:00:00Z","timestamp":1769187600650,"version":"3.49.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611464","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"463-469","source":"Crossref","is-referenced-by-count":30,"title":["ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers"],"prefix":"10.1109","author":[{"given":"Philipp","family":"Ausserlechner","sequence":"first","affiliation":[{"name":"Automation and Control Institute,Vision for Robotics Laboratory,TU Wien,Austria"}]},{"given":"David","family":"Haberger","sequence":"additional","affiliation":[{"name":"Automation and Control Institute,Vision for Robotics Laboratory,TU Wien,Austria"}]},{"given":"Stefan","family":"Thalhammer","sequence":"additional","affiliation":[{"name":"University of Applied Sciences Technikum Vienna,Industrial Engineering Department,Austria"}]},{"given":"Jean-Baptiste","family":"Weibel","sequence":"additional","affiliation":[{"name":"Automation and Control Institute,Vision for Robotics Laboratory,TU Wien,Austria"}]},{"given":"Markus","family":"Vincze","sequence":"additional","affiliation":[{"name":"Automation and Control Institute,Vision for Robotics Laboratory,TU Wien,Austria"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_34"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00776"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00662"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00288"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00671"},{"key":"ref8","article-title":"Megapose: 6d pose estimation of novel objects via render & compare","author":"Labbe","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00665"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104816"},{"key":"ref11","article-title":"Blenderproc: Reducing the reality gap with photorealistic rendering","volume-title":"International Conference on Robotics: Sciene and Systems, RSS 2020","author":"Denninger"},{"key":"ref12","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"3","key":"ref13","first-page":"4","article-title":"Deep vit features as dense visual descriptors","volume":"2","author":"Amir","year":"2021"},{"key":"ref14","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409116"},{"key":"ref17","first-page":"19","article-title":"Bop: Benchmark for 6d object pose estimation","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Hodan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636489"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562108"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812299"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561237"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160531"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00203"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01172"},{"key":"ref25","article-title":"Pope: 6-dof promptable pose estimation of any object, in any scene, with one reference","author":"Fan","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_30"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540108"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01393"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00227"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","article-title":"Stand-alone self-attention in vision models","volume":"32","author":"Ramachandran","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130296"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.103"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611464.pdf?arnumber=10611464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:11:12Z","timestamp":1723349472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611464","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}