{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:17:47Z","timestamp":1775578667507,"version":"3.50.1"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T00:00:00Z","timestamp":1742860800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T00:00:00Z","timestamp":1742860800000},"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":[[2025,3,25]]},"DOI":"10.1109\/3dv66043.2025.00112","type":"proceedings-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:14:24Z","timestamp":1756152864000},"page":"1177-1186","source":"Crossref","is-referenced-by-count":3,"title":["Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model"],"prefix":"10.1109","author":[{"given":"Kuan-Chih","family":"Huang","sequence":"first","affiliation":[{"name":"University of California,Merced,USA"}]},{"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"Skywork AI,Singapore"}]},{"given":"Lu","family":"Qi","sequence":"additional","affiliation":[{"name":"University of California,Merced,USA"}]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Skywork AI,Singapore"}]},{"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California,Merced,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref2","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref6","article-title":"Scanrefer: 3d object localization in rgb-d scans using natural language","author":"Zhenyu Chen","year":"2020","journal-title":"ECCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01518"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref10","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref12","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref14","article-title":"Concept-graphs: Open-vocabulary 3d scene graphs for perception and planning","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"3d-llm: Injecting the 3d world into large language models","author":"Hong","year":"2023","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00455"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref18","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Martin","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref19","article-title":"Opt-iml: Scaling language model instruction meta learning through the lens of generalization","author":"Iyer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01979"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00479"},{"key":"ref23","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref28","article-title":"Generalizable entity grounding via assistance of large language model","author":"Qi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02495"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28254"},{"key":"ref32","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02491"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25335"},{"key":"ref37","article-title":"Open-Mask3D: Open-Vocabulary 3D Instance Segmentation","author":"Takmaz","year":"2023","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681257"},{"key":"ref39","article-title":"Gpt-4 technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3592131"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28408"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01243"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01278"},{"key":"ref45","article-title":"Point transformer v2: Grouped vector attention and partition-based pooling","author":"Wu","year":"2022","journal-title":"NeurIPS"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref47","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.521"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref50","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref53","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","author":"Zheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 International Conference on 3D Vision (3DV)","location":"Singapore, Singapore","start":{"date-parts":[[2025,3,25]]},"end":{"date-parts":[[2025,3,28]]}},"container-title":["2025 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11125485\/11125004\/11125649.pdf?arnumber=11125649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T05:21:06Z","timestamp":1756185666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11125649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,25]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/3dv66043.2025.00112","relation":{},"subject":[],"published":{"date-parts":[[2025,3,25]]}}}