{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T08:11:11Z","timestamp":1791619871654,"version":"4.3.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Sapienza University of Rome"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/wacvw68408.2026.00185","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:16:27Z","timestamp":1785870987000},"page":"1712-1720","source":"Crossref","is-referenced-by-count":1,"title":["LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments"],"prefix":"10.1109","author":[{"given":"Sara Micol","family":"Ferraina","sequence":"first","affiliation":[{"name":"Sapienza University of Rome","place":["Rome, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michele","family":"Brienza","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome","place":["Rome, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Argenziano","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome","place":["Rome, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emanuele","family":"Musumeci","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome","place":["Rome, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincenzo","family":"Suriani","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome","place":["Rome, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Domenico D.","family":"Bloisi","sequence":"additional","affiliation":[{"name":"International University of Rome UNINT","place":["Rome, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniele","family":"Nardi","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome","place":["Rome, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802251"},{"key":"ref2","article-title":"Dynamic objects relocalization in changing environments with flow matching","author":"Argenziano","year":"2025","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Zamir, Martin Fischer, Jitendra Malik, and Silvio Savarese","volume-title":"3d scene graph: A structure for unified semantics, 3d space, and camera. In Intl. Conf. on Computer Vision (ICCV)","author":"Armeni","year":"2019"},{"key":"ref4","article-title":"Social 3d scene graphs: Modeling human actions and relations for interactive service robots","author":"Bartoli","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MAES.2004.1263228"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref8","article-title":"Opennerf: open set 3d neural scene segmentation with pixelwise features and rendered novel views","author":"Engelmann","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3482169"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2026.3675320"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3441495"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.050"},{"key":"ref14","article-title":"Roboexp: Action-conditioned scene graph via interactive exploration for robotic manipulation","volume-title":"Conf. on Robot Learning (CoRL)","author":"Jiang","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01345"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01084"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127838"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3451395"},{"key":"ref20","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3191"},{"key":"ref22","article-title":"Context matters! relaxing goals with llms for feasible 3d scene planning","author":"Musumeci","year":"2025","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10413"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref26","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning","volume-title":"Conf. on Robot Learning (CoRL)","author":"Rana","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247555"},{"key":"ref28","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_27"},{"key":"ref31","author":"Welch","year":"1995","journal-title":"An introduction to the kalman filter"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.077"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3547643"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0171"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6562-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00782"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.221"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11617369\/11617396\/11617929.pdf?arnumber=11617929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:04:17Z","timestamp":1785909857000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11617929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/wacvw68408.2026.00185","relation":{},"subject":[],"published":{"date-parts":[[2026,3]]}}}