{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:08Z","timestamp":1778048348905,"version":"3.51.4"},"reference-count":72,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00828","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"8584-8595","source":"Crossref","is-referenced-by-count":0,"title":["VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning"],"prefix":"10.1109","author":[{"given":"Vivek","family":"Madhavaram","sequence":"first","affiliation":[{"name":"IIIT,Machine Learning Lab,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vartika","family":"Sengar","sequence":"additional","affiliation":[{"name":"Fujitsu Research India,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arkadipta","family":"De","sequence":"additional","affiliation":[{"name":"Fujitsu Research India,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charu","family":"Sharma","sequence":"additional","affiliation":[{"name":"IIIT,Machine Learning Lab,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref3","first-page":"46","article-title":"Taskography: Evaluating robot task planning over large 3d scene graphs","volume-title":"Conference on Robot Learning","author":"Agia"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3189785"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630614"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1492"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00526"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01604"},{"key":"ref12","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"ref19","article-title":"Hydra: A real-time spatial perception engine for 3d scene graph construction and optimization","author":"Hughes","year":"2022","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981735"},{"key":"ref21","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341186"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26889-2_14"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00076"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01345"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/GC46384.2019.00015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00351"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref30","article-title":"Instructscene: Instruction-driven 3d indoor scene synthesis with semantic graph prior","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lin"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128059"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3219451"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161212"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28197"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801291"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482218"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3332098"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169065"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref43","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning","author":"Rana","year":"2023"},{"key":"ref44","first-page":"1046","article-title":"Languagerefer: Spatial-language model for 3d visual grounding","volume-title":"Conference on Robot Learning","author":"Roh"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.079"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211056674"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2250"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01333"},{"key":"ref50","article-title":"The Replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475326"},{"key":"ref52","article-title":"Open-mask3d: Open-vocabulary 3d instance segmentation","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Takmaz"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012757468803412"},{"key":"ref54","first-page":"8180","article-title":"3rscan: A reality-based 3d dataset for scene understanding","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wald"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"ref59","article-title":"Vlm-grounder: A vlm agent for zero-shot 3d visual grounding","volume-title":"8th Annual Conference on Robot Learning","author":"Xu"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref61","article-title":"Sam3d: Segment anything in 3d scenes","author":"Yang","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00958"},{"key":"ref68","first-page":"18620","article-title":"Knowledge-inspired 3d scene graph prediction in point cloud","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00184"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_13"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","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 (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492636.pdf?arnumber=11492636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:58:56Z","timestamp":1778047136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00828","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}