{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:10:09Z","timestamp":1777889409448,"version":"3.51.4"},"reference-count":43,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62495082,62461160331,U21B2025"],"award-info":[{"award-number":["62495082,62461160331,U21B2025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2021ZD0111901,2023YFF1105104"],"award-info":[{"award-number":["2021ZD0111901,2023YFF1105104"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00504","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5305-5314","source":"Crossref","is-referenced-by-count":0,"title":["OV3D-CG: Open-Vocabulary 3D Instance Segmentation with Contextual Guidance"],"prefix":"10.1109","author":[{"given":"Mingquan","family":"Zhou","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language Models are Few-Shot Learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Contrastive localized language-image pre-training","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01518"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3350024"},{"key":"ref5","article-title":"PaLM: Scaling Language Modeling with Pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref7","article-title":"3D-BEVIS: Birds-Eye-View Instance Segmentation","author":"Elich","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00301"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00455"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21831"},{"key":"ref18","article-title":"Language-driven Semantic Segmentation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Li","year":"2022"},{"key":"ref19","article-title":"Visual Instruction Tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref21","first-page":"1610","article-title":"OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data","volume-title":"Proceedings of The 7th Conference on Robot Learning","author":"Lu","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967890"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01302"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref25","article-title":"Gpt-4 technical report","volume-title":"Technical report","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref27","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref28","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref31","article-title":"The Replica Dataset: A Digital Replica of Indoor Spaces","author":"Straub","year":"2019","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"68367","article-title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Takmaz","year":"2024"},{"key":"ref33","article-title":"LLaMA: Open and Efficient Foundation Language Models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","author":"Tschannen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00272"},{"key":"ref38","first-page":"6737","article-title":"Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Yang","year":"2019"},{"key":"ref39","article-title":"SAM3D: Segment Anything in 3D Scenes","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00407"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00317"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00219"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"}],"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\/11444143.pdf?arnumber=11444143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:34Z","timestamp":1777612354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444143\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00504","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}