{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:17:07Z","timestamp":1777889827083,"version":"3.51.4"},"reference-count":61,"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\/iccv51701.2025.02303","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24835-24845","source":"Crossref","is-referenced-by-count":0,"title":["All in One: Visual-Description-Guided Unified Point Cloud Segmentation"],"prefix":"10.1109","author":[{"given":"Zongyan","family":"Han","sequence":"first","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence,Abu Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"El Amine Boudjoghra","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahua","family":"Dong","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence,Abu Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence,Abu Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence,Abu Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00056"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01518"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01518"},{"key":"ref5","first-page":"17864","article-title":"Perpixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","first-page":"17864","article-title":"Perpixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref9","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref12","volume-title":"MMDetection3D: OpenMMLab next-generation platform for general 3D object detection","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00677"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00301"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00042"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00455"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00455"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00342"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00353"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01979"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01979"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00935"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01163"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00278"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00278"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01696"},{"key":"ref33","article-title":"Learning gaussian instance segmentation in point clouds","author":"Liu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967890"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01302"},{"key":"ref36","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1685"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25335"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25335"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00062"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref47","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00272"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2415"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_14"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00319"},{"key":"ref56","article-title":"Learning object bounding boxes for 3d instance segmentation on point clouds","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636599"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00407"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00877"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00058"}],"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\/11449030.pdf?arnumber=11449030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:20:59Z","timestamp":1777612859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449030\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02303","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}