{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:53:39Z","timestamp":1775854419291,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council (ARC) Discovery Project","doi-asserted-by":"publisher","award":["DP240103334"],"award-info":[{"award-number":["DP240103334"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3673267","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:38:29Z","timestamp":1773347909000},"page":"52102-52117","source":"Crossref","is-referenced-by-count":0,"title":["Open-Vocabulary 3-D Segmentation With 3-D-Aware Mask Alignment and Identity Expansion"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4418-3269","authenticated-orcid":false,"given":"Weijie","family":"Lin","sequence":"first","affiliation":[{"name":"School of Computing, Engineering and Mathematical Sciences, La Trobe University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0608-065X","authenticated-orcid":false,"given":"Wei","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Computing, Engineering and Mathematical Sciences, La Trobe University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3913-7683","authenticated-orcid":false,"given":"Lu","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computing, Engineering and Mathematical Sciences, La Trobe University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computing, Engineering and Mathematical Sciences, La Trobe University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3626-7818","authenticated-orcid":false,"given":"Kang","family":"Han","sequence":"additional","affiliation":[{"name":"School of Computing, Engineering and Mathematical Sciences, La Trobe University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref4","first-page":"405","article-title":"Distilled feature fields enable few-shot language-guided manipulation","volume-title":"Proc. 7th Conf. Robot Learn. (CoRL)","author":"Shen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1694"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2325"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32193"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611684"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref26","article-title":"Towards foundation models for 3D: Revisiting data, architectures, and objectives","author":"Alhaija","year":"2023","journal-title":"arXiv:2310.02209"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref28","first-page":"24266","article-title":"Auto-vocabulary semantic segmentation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"\u00dclger"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557719"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01882"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref32","first-page":"20398","article-title":"DeAOT: Decoupling features and classifiers for adaptive online video object segmentation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Chen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00345"},{"key":"ref34","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01948"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_16"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1130"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/s23229225"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11431585.pdf?arnumber=11431585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:00:49Z","timestamp":1775851249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11431585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3673267","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}