{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T04:56:39Z","timestamp":1781844999823,"version":"3.54.5"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"SNSF PostDoc.Mobility Fellowship during Francis Engelmann's stay at Stanford University"},{"DOI":"10.13039\/501100013348","name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung","doi-asserted-by":"publisher","award":["48727.1 IP-ICT"],"award-info":[{"award-number":["48727.1 IP-ICT"]}],"id":[{"id":"10.13039\/501100013348","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["216260"],"award-info":[{"award-number":["216260"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100022491","name":"Max Planck ETH Center for Learning Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100022491","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/lra.2025.3534523","type":"journal-article","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T19:09:48Z","timestamp":1738177788000},"page":"2558-2565","source":"Crossref","is-referenced-by-count":14,"title":["Search3D: Hierarchical Open-Vocabulary 3D Segmentation"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7834-4565","authenticated-orcid":false,"given":"Ayca","family":"Takmaz","sequence":"first","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandros","family":"Delitzas","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert W.","family":"Sumner","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5745-2137","authenticated-orcid":false,"given":"Francis","family":"Engelmann","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8117-682X","authenticated-orcid":false,"given":"Johanna","family":"Wald","sequence":"additional","affiliation":[{"name":"Google, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5598-5212","authenticated-orcid":false,"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[{"name":"Google, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref4","article-title":"Spot-compose: A framework for open-vocabulary object retrieval and drawer manipulation in point clouds","volume-title":"Proc. IEEE Int. Conf. Robot. Autom. Workshop","author":"Lemke","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01377"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref7","first-page":"68367","article-title":"OpenMask3D: Open-vocabulary 3D instance segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Takmaz","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2023.XIX.066","article-title":"ConceptFusion: Open-set multimodal 3D mapping","volume-title":"Proc. Robot.: Sci. Syst.","author":"Jatavallabhula","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610243"},{"key":"ref11","article-title":"OpenNeRF: Open set 3D neural scene segmentation with pixel-wise features and rendered novel views","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Engelmann","year":"2024"},{"key":"ref12","article-title":"OpenCity3D: 3D urban scene understanding with vision-language models","volume-title":"Proc. Winter Conf. Appl. Comput. Vis.","author":"Bieri","year":"2025"},{"key":"ref13","article-title":"OpenSUN3D: 1st workshop challenge on open-vocabulary 3D scene understanding","author":"Engelmann","year":"2024"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611725"},{"key":"ref16","first-page":"9058","article-title":"MultiScan: Scalable RGBD scanning for 3D environments with articulated objects","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Mao","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref20","first-page":"197","article-title":"N2F2: Hierarchical scene understanding with nested neural feature fields","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Bhalgat","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00125"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02034"},{"key":"ref23","first-page":"278","article-title":"Segment3D: Learning fine-grained class-agnostic 3D segmentation without manual labels","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Huang","year":"2024"},{"key":"ref24","article-title":"AGILE3D: Attention guided interactive multi-object 3D segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yue","year":"2024"},{"key":"ref25","article-title":"Reasoning3D - Grounding and reasoning in 3D: Fine-grained zero-shot open-vocabulary 3D reasoning part segmentation via large vision-language models","author":"Chen","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02082"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01392"},{"key":"ref28","article-title":"Find any part in 3D","author":"Ma","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3451395"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_3"},{"key":"ref34","first-page":"540","article-title":"Scaling open-vocabulary image segmentation with image-level labels","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Ghiasi","year":"2021"},{"key":"ref35","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref41","article-title":"Hierarchical open-vocabulary universal image segmentation","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref42","first-page":"70094","article-title":"OV-PARTS: Towards open-vocabulary part segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wei","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01417"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref47","first-page":"467","article-title":"Semantic-SAM: Segment and recognize anything at any granularity","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Li","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref49","article-title":"SAM3D: Segment anything in 3D scenes","author":"Yang","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10849592\/10857311.pdf?arnumber=10857311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T18:47:27Z","timestamp":1738954047000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10857311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":50,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3534523","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}