{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T12:19:51Z","timestamp":1779365991537,"version":"3.53.0"},"reference-count":91,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00534","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5633-5644","source":"Crossref","is-referenced-by-count":2,"title":["Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description"],"prefix":"10.1109","author":[{"given":"Anna-Maria","family":"Halacheva","sequence":"first","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Miao","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan-Nico","family":"Zaech","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danda Pani","family":"Paudel","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ARKitscenes: A diverse real-world dataset for 3d indoor scene understanding using mobile RGB-d data","volume-title":"International Conference on Neural Information Processing Systems (NeurIPS)","author":"Baruch","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01833"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01518"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.124"},{"key":"ref8","article-title":"Occam\u2019s lgs: A simple approach for language gaussian splatting","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0433"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01377"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00677"},{"key":"ref15","article-title":"Are multimodal large language models ready for omnidirectional spatial reasoning?","author":"Dongfang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00066"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref19","article-title":"From scan to action: Leveraging realistic scans for embodied scene understanding","author":"Halacheva","year":"2025","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02494"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.18"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3620"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS60882.2024.10556959"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_24"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00553"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMA59762.2023.10374780"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103624"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00146"},{"key":"ref33","article-title":"Multi-modal situated reasoning in 3d scenes","volume-title":"International Conference on Neural Information Processing Systems (NeurIPS)","author":"Linghu","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00039"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01693"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01439"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00727"},{"key":"ref38","article-title":"Cityloc: 6dof pose distributional localization for text descriptions in largescale scenes with gaussian representation","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref40","article-title":"Multiscan: Scalable rgbd scanning for 3d environments with articulated objects","volume-title":"International Conference on Neural Information Processing Systems (NeurIPS)","author":"Mao","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.050"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611691"},{"key":"ref46","volume-title":"NVIDIA Isaac Sim","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_21"},{"key":"ref48","volume-title":"GPT-4o mini: advancing cost-efficient intelligence","year":"2024"},{"key":"ref49","volume-title":"Hello GPT-4o","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00229"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00165"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02058"},{"key":"ref53","article-title":"Habitat-matterport 3d dataset (HM3d): 1000 large-scale 3d environments for embodied AI","volume-title":"International Conference on Neural Information Processing Systems (NeurIPS)","author":"Ramakrishnan","year":"2021"},{"key":"ref54","article-title":"Sharing key semantics in transformer makes efficient image restoration","volume-title":"International Conference on Neural Information Processing Systems (NeurIPS)","author":"Ren","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0963-5_4"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/app12178429"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01886"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02004"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_5"},{"key":"ref60","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"Computing Research Repository (CoRR)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.272"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14207"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20122"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00515"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00100"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_12"},{"key":"ref68","article-title":"Habitat 2.0: training home assistants to rearrange their habitat","volume-title":"International Conference on Neural Information Processing Systems (NeurIPS)","author":"Szot","year":"2021"},{"key":"ref69","article-title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","volume-title":"International Conference on Neural Information Processing Systems (NeurIPS)","author":"Takmaz","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.492"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012757468803412"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.015"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_27"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00908"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_17"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00477"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356573"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802241"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_11"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636054"},{"key":"ref88","article-title":"Commonscenes: Generating commonsense 3d indoor scenes with scene graphs","volume-title":"International Conference on Neural Information Processing Systems (NeurIPS)","author":"Zhai","year":"2023"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3432348"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3639477.3639740"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446145.pdf?arnumber=11446145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:22Z","timestamp":1777529782000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00534","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}