{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:00:58Z","timestamp":1783530058868,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["62073245"],"award-info":[{"award-number":["62073245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018550","name":"Shanghai Science and Technology Innovation Action Plan","doi-asserted-by":"publisher","award":["22511104900"],"award-info":[{"award-number":["22511104900"]}],"id":[{"id":"10.13039\/501100018550","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3397997","type":"journal-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T17:41:09Z","timestamp":1715190069000},"page":"9125-9138","source":"Crossref","is-referenced-by-count":25,"title":["CLIPose: Category-Level Object Pose Estimation With Pre-Trained Vision-Language Knowledge"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9989-8233","authenticated-orcid":false,"given":"Xiao","family":"Lin","sequence":"first","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0291-5841","authenticated-orcid":false,"given":"Minghao","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1176-3735","authenticated-orcid":false,"given":"Ronghao","family":"Dang","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7845-7068","authenticated-orcid":false,"given":"Guangliang","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7343-1782","authenticated-orcid":false,"given":"Shaolong","family":"Shu","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6831-4458","authenticated-orcid":false,"given":"Feng","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7543-0855","authenticated-orcid":false,"given":"Chengju","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5644-1188","authenticated-orcid":false,"given":"Qijun","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2513408"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref3","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","author":"Tremblay","year":"2018","journal-title":"arXiv:1809.10790"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00346"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561475"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3138129"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00302"},{"key":"ref9","article-title":"TransPose: 6D object pose estimation with geometry-aware transformer","author":"Lin","year":"2023","journal-title":"arXiv:2310.16279"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327430"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.206"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.366"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_32"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00163"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00666"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01285"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3309902"},{"key":"ref20","first-page":"3809","article-title":"Revisiting point cloud shape classification with a simple and effective baseline","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Goyal"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref24","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref25","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref26","article-title":"InstructDET: Diversifying referring object detection with generalized instructions","author":"Dang","year":"2023","journal-title":"arXiv:2310.05136"},{"key":"ref27","article-title":"VT-CLIP: Enhancing vision-language models with visual-guided texts","author":"Qiu","year":"2021","journal-title":"arXiv:2112.02399"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref29","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"arXiv:2201.03546"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658050"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636212"},{"key":"ref35","first-page":"16779","article-title":"Sparse steerable convolutions: An efficient learning of Se (3)-equivariant features for estimation and tracking of object poses in 3D space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lin"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00277"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01646"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01199"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233554"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326373"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611932"},{"key":"ref49","article-title":"PointCLIP v2: Prompting CLIP and GPT for powerful 3D open-world learning","author":"Zhu","year":"2022","journal-title":"arXiv:2211.11682"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3549201"},{"key":"ref51","article-title":"ULIP-2: Towards scalable multimodal pre-training for 3D understanding","author":"Xue","year":"2023","journal-title":"arXiv:2305.08275"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811367"},{"key":"ref53","article-title":"LanPose: Language-instructed 6D object pose estimation for robotic assembly","author":"Fu","year":"2023","journal-title":"arXiv:2310.13819"},{"key":"ref54","article-title":"Open-vocabulary object 6D pose estimation","author":"Corsetti","year":"2023","journal-title":"arXiv:2312.00690"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref56","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref57","article-title":"Notes on noise contrastive estimation and negative sampling","author":"Dyer","year":"2014","journal-title":"arXiv:1410.8251"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref59","first-page":"380","article-title":"Des lois g\u00e9om\u00e9triques qui r\u00e9gissent les d\u00e9placements d\u2019un syst\u00e8me solide dans l\u2019espace, et de la variation des coordonn\u00e9es provenant de ces d\u00e9placements consid\u00e9r\u00e9s ind\u00e9pendamment des causes qui peuvent les produire","volume":"5","author":"Rodrigues","year":"1840","journal-title":"J. de math\u00e9matiques pures et appliqu\u00e9es"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00354"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981506"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_38"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341552"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00659"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00187"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10739868\/10522755.pdf?arnumber=10522755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:13:31Z","timestamp":1736453611000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10522755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":65,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3397997","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}