{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:44:46Z","timestamp":1772905486318,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100007162","name":"Guangdong Science and Technology Department","doi-asserted-by":"publisher","award":["2023A0505010004"],"award-info":[{"award-number":["2023A0505010004"]}],"id":[{"id":"10.13039\/501100007162","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/lra.2024.3430156","type":"journal-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T17:25:51Z","timestamp":1721237151000},"page":"7661-7668","source":"Crossref","is-referenced-by-count":12,"title":["Open-Vocabulary Category-Level Object Pose and Size Estimation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1440-0406","authenticated-orcid":false,"given":"Junhao","family":"Cai","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4029-5494","authenticated-orcid":false,"given":"Yisheng","family":"He","sequence":"additional","affiliation":[{"name":"Institute for Intelligent Computing, Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1362-3747","authenticated-orcid":false,"given":"Weihao","family":"Yuan","sequence":"additional","affiliation":[{"name":"Institute for Intelligent Computing, Alibaba Group, Hangzhou, China"}]},{"given":"Siyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-9102","authenticated-orcid":false,"given":"Zilong","family":"Dong","sequence":"additional","affiliation":[{"name":"Institute for Intelligent Computing, Alibaba Group, Hangzhou, China"}]},{"given":"Liefeng","family":"Bo","sequence":"additional","affiliation":[{"name":"Institute for Intelligent Computing, Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2199-3948","authenticated-orcid":false,"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3333693"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2513408"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00066"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00346"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00302"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_18"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref10","first-page":"27469","article-title":"Category-level 6D object pose estimation in the wild: A semi-supervised learning approach and a new dataset","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Ze","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00671"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref16","article-title":"A tale of two features: Stable diffusion complements DINO for zero-shot semantic correspondence","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2024"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref19","article-title":"DINOv2: Learning robust visual features without supervision","volume-title":"Trans. Mach. Learn. Res.","author":"Oquab","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00279"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37331-2_42"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_24"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967967"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00669"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104507"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01199"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811799"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636212"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00277"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00666"},{"key":"ref37","first-page":"1390","article-title":"Generative category-level shape and pose estimation with semantic primitives","volume-title":"Proc. Conf. Robot Learn.","author":"Li","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_9"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3110538"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142441"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3189792"},{"key":"ref42","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref44","article-title":"Objaverse-XL: A universe of 10m+ 3D objects","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"36","author":"Deitke","year":"2024"},{"key":"ref45","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Saharia","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref47","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Schuhmann","year":"2022"},{"key":"ref48","article-title":"Emergent correspondence from image diffusion","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Tang","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04901"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref56","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3415263.3419160"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.46"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01646"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01285"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10601335\/10601309.pdf?arnumber=10601309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T17:34:23Z","timestamp":1721928863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10601309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":64,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3430156","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}