{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:27:26Z","timestamp":1781587646885,"version":"3.54.5"},"reference-count":63,"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":"am","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\/100023581","name":"National Science Foundation Graduate Research Fellowship Program","doi-asserted-by":"publisher","award":["2141064"],"award-info":[{"award-number":["2141064"]}],"id":[{"id":"10.13039\/100023581","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["214489"],"award-info":[{"award-number":["214489"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MIT Lincoln Laboratory&#x0027;s"},{"name":"ARL DCIST program"},{"name":"ONR RAPID program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/lra.2024.3451395","type":"journal-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T18:06:20Z","timestamp":1724954780000},"page":"8921-8928","source":"Crossref","is-referenced-by-count":46,"title":["<i>Clio:<\/i> Real-Time Task-Driven Open-Set 3D Scene Graphs"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9458-2665","authenticated-orcid":false,"given":"Dominic","family":"Maggio","sequence":"first","affiliation":[{"name":"Laboratory for Information &amp; Decision Systems, Massachusetts Institute of Technology Cambridge, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2829-5256","authenticated-orcid":false,"given":"Yun","family":"Chang","sequence":"additional","affiliation":[{"name":"Laboratory for Information &amp; Decision Systems, Massachusetts Institute of Technology Cambridge, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1201-7032","authenticated-orcid":false,"given":"Nathan","family":"Hughes","sequence":"additional","affiliation":[{"name":"Laboratory for Information &amp; Decision Systems, Massachusetts Institute of Technology Cambridge, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Trang","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory, Lexington, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Griffith","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory, Lexington, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlyn","family":"Dougherty","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory, Lexington, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1712-4600","authenticated-orcid":false,"given":"Eric","family":"Cristofalo","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory, Lexington, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3961-8145","authenticated-orcid":false,"given":"Lukas","family":"Schmid","sequence":"additional","affiliation":[{"name":"Laboratory for Information &amp; Decision Systems, Massachusetts Institute of Technology Cambridge, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1884-5397","authenticated-orcid":false,"given":"Luca","family":"Carlone","sequence":"additional","affiliation":[{"name":"Laboratory for Information &amp; Decision Systems, Massachusetts Institute of Technology Cambridge, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Visual representations: Defining properties and deep approximations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Soatto","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2624754"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2020.XVI.079","article-title":"3D dynamic scene graphs: Actionable spatial perception with places, objects, and humans","volume-title":"Proc. Robot.: Sci. Syst.","author":"Rosinol","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.050"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241229725"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.066"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"ref13","first-page":"368","article-title":"The information bottleneck method","volume-title":"Proc. Allerton Conf. Commun., Control Computation","volume":"49","author":"Tishby","year":"2001"},{"key":"ref14","first-page":"617","article-title":"Agglomerative information bottleneck","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Slonim","year":"1999"},{"key":"ref15","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref16","article-title":"GPT-4 Tech. Rep.","year":"2023"},{"key":"ref17","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref18","article-title":"DINOv2: Learning robust visual features without supervision","volume-title":"Proc. Trans. Mach. Learn. Res.","author":"Oquab","year":"2024"},{"key":"ref19","first-page":"20482","article-title":"3D-LLM: Injecting the 3D world into large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00266"},{"key":"ref21","article-title":"GOAT: GO to any thing","author":"Chang","year":"2023"},{"key":"ref22","article-title":"RoboHop: Segment-based topological map representation for open-world visual navigation","volume-title":"Proc. 2nd Workshop Lang. Robot Learning: Lang. Grounding","author":"Garg","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref24","article-title":"Foundation models in robotics: Applications, challenges, and the future","author":"Firoozi","year":"2023"},{"key":"ref25","first-page":"14410","article-title":"A vision check-up for language models","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Sharma","year":"2024"},{"key":"ref26","first-page":"9568","article-title":"Eyes wide shut? exploring the visual shortcomings of multimodal LLMs","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Tong","year":"2024"},{"key":"ref27","article-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref30","article-title":"Grounding DINO: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"ref31","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref32","first-page":"8090","article-title":"Open-vocabulary universal image segmentation with maskclip","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Zheng Ding","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref34","article-title":"Segment3D: Learning fine-grained class-agnostic 3D segmentation without manual labels","author":"Huang","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1117\/12.919598"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref39","first-page":"20051","article-title":"LangSplat: 3D language Gaussian splatting","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qin","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342275"},{"key":"ref41","first-page":"21530","article-title":"GARField: Group anything with radiance fields","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Kim","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00504"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref44","first-page":"643","article-title":"Semantic abstraction: Open-world 3D scene understanding from 2D vision-language models","volume-title":"Proc. Conf. Robot Learn.","author":"Ha","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3322647"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00076"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610193"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610341"},{"key":"ref49","first-page":"1950","article-title":"Context-aware entity grounding with open-vocabulary 3D scene graphs","volume-title":"Proc. Conf. Robot Learn.","author":"Chang","year":"2023"},{"key":"ref50","article-title":"OpenMask3D: Open-vocabulary 3D instance segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Takmaz","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238368"},{"key":"ref53","first-page":"16009","article-title":"Visual explanations of image-text representations via multi-modal information bottleneck attribution","volume":"36","author":"Wang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3099995"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3003219"},{"key":"ref56","article-title":"Towards visual foundational models of physical scenes","author":"Parameshwara","year":"2023"},{"key":"ref57","article-title":"Selective visual representations improve convergence and generalization for embodied AI","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eftekhar","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160606"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00483"},{"key":"ref60","article-title":"Visual scene representations: Sufficiency, minimality, invariance and deep approximation","volume-title":"Proc. ICLR Workshop","author":"Soatto","year":"2014"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3451395"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.081"},{"key":"ref63","first-page":"405","article-title":"Distilled feature fields enable few-shot language-guided manipulation","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Shen","year":"2023"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/10638067\/10659066-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10638067\/10659066.pdf?arnumber=10659066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:35:15Z","timestamp":1734982515000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10659066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":63,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3451395","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}