{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:19:50Z","timestamp":1784204390803,"version":"3.55.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/lra.2024.3354624","type":"journal-article","created":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T18:26:41Z","timestamp":1705429601000},"page":"2144-2151","source":"Crossref","is-referenced-by-count":13,"title":["Panoptic Vision-Language Feature Fields"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1067-7391","authenticated-orcid":false,"given":"Haoran","family":"Chen","sequence":"first","affiliation":[{"name":"Autonomous Systems Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6897-3795","authenticated-orcid":false,"given":"Kenneth","family":"Blomqvist","sequence":"additional","affiliation":[{"name":"Autonomous Systems Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4657-4144","authenticated-orcid":false,"given":"Francesco","family":"Milano","sequence":"additional","affiliation":[{"name":"Autonomous Systems Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2760-7983","authenticated-orcid":false,"given":"Roland","family":"Siegwart","sequence":"additional","affiliation":[{"name":"Autonomous Systems Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342275"},{"key":"ref4","article-title":"Weakly supervised 3d open-vocabulary segmentation","author":"Liu","year":"2023","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00873"},{"key":"ref6","first-page":"11207","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref7","first-page":"4015","article-title":"Segment anything","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Kirillov","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref9","article-title":"The Replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3148457"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3122069"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2923960"},{"key":"ref18","first-page":"8282","article-title":"Panoptic 3D scene reconstruction from a single RGB image","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Dahnert","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967890"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00042"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01253"},{"key":"ref22","article-title":"Contrastive lift: 3D object instance segmentation by slow-fast contrastive fusion","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Bhalgat","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00683"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00444"},{"key":"ref36","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot. Learn.","volume":"205","author":"Ichter","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342071"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00636"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00205"},{"key":"ref41","article-title":"DM-NeRF: 3D scene geometry decomposition and manipulation from 2D images","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bing","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00295"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00422"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10409903\/10400827.pdf?arnumber=10400827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T08:40:09Z","timestamp":1706776809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10400827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3354624","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}