{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:04Z","timestamp":1777888804353,"version":"3.51.4"},"reference-count":67,"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\/iccv51701.2025.00898","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9627-9637","source":"Crossref","is-referenced-by-count":0,"title":["Details Matter for Indoor Open-Vocabulary 3D Instance Segmentation"],"prefix":"10.1109","author":[{"given":"Sanghun","family":"Jung","sequence":"first","affiliation":[{"name":"University of Washington"}]},{"given":"Jingjing","family":"Zheng","sequence":"additional","affiliation":[{"name":"Amazon Lab126"}]},{"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"Amazon Lab126"}]},{"given":"Nan","family":"Qiao","sequence":"additional","affiliation":[{"name":"Amazon Lab126"}]},{"given":"Albert Y. C.","family":"Chen","sequence":"additional","affiliation":[{"name":"Amazon Lab126"}]},{"given":"Lu","family":"Xia","sequence":"additional","affiliation":[{"name":"Amazon Lab126"}]},{"given":"Chi","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon Lab126"}]},{"given":"Yuyin","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon Lab126"}]},{"given":"Xiao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Amazon Lab126"}]},{"given":"Hsiang-Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Byron","family":"Boots","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Min","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon Lab126"}]},{"given":"Cheng-Hao","family":"Kuo","sequence":"additional","affiliation":[{"name":"Amazon Lab126"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref2","article-title":"Open-yolo 3d: Towards fast and accurate open-vocabulary 3d instance segmentation","author":"El","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Zero-shot semantic segmentation","volume":"32","author":"Bucher","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01518"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01141"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00677"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3410324"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"ref12","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"Ester","year":"1996","journal-title":"kdd"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref15","article-title":"Openvocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"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\/ICCVW60793.2023.00217"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00455"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00297"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00089"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_10"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref24","article-title":"Dynamic filter networks","volume":"29","author":"Jia","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref26","first-page":"15946","article-title":"Multimodal classifiers for open-vocabulary object detection","volume-title":"International Conference on Machine Learning","author":"Kaul"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01979"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00935"},{"key":"ref31","article-title":"Segment any 3d object with language","author":"Lee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00278"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref36","article-title":"Learning gaussian instance segmentation in point clouds","author":"Liu","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"1610","article-title":"Ovir-3d: Open-vocabulary 3d instance retrieval without training on 3d data","volume-title":"Conference on Robot Learning","author":"Lu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01302"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00083"},{"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":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00970"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref46","article-title":"Whitening and coloring batch transform for gans","author":"Siarohin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01237"},{"key":"ref49","article-title":"Openmask3d: Open-vocabulary 3d instance segmentation","author":"Takmaz","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref51","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00272"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02671"},{"key":"ref58","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":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01874"},{"key":"ref60","article-title":"Sam3d: Segment anything in 3d scenes","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00407"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00317"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref67","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11446303.pdf?arnumber=11446303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:51Z","timestamp":1777611531000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00898","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}