{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:01:56Z","timestamp":1777888916501,"version":"3.51.4"},"reference-count":44,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372133, 62376074"],"award-info":[{"award-number":["62372133, 62376074"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00736","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7851-7860","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Spatial Reasoning in Multimodal Large Language Models Through Reasoning-Based Segmentation"],"prefix":"10.1109","author":[{"given":"Zhenhua","family":"Ning","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuotao","family":"Tian","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoshuai","family":"Shi","sequence":"additional","affiliation":[{"name":"Voyager Research, Didi Chuxing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangming","family":"Lu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daojing","family":"He","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Pei","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Jiang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00039"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1492"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02496"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_39"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01698"},{"key":"ref9","author":"Chen","year":"2024","journal-title":"Grounded 3d-llm with referent tokens"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_3"},{"key":"ref12","first-page":"7010","article-title":"Pla: Language-driven openvocabulary 3d scene understanding","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Ding","year":"2023"},{"key":"ref13","author":"Dubey","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref14","author":"Guo","year":"2023","journal-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following"},{"key":"ref15","author":"Han","year":"2023","journal-title":"Imagebind-llm: Multi-modality instruction tuning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref17","author":"Huang","year":"2023","journal-title":"Chat-3d v2: Bridging 3d scene and large language models with object identifiers"},{"key":"ref18","author":"Huang","year":"2023","journal-title":"An embodied generalist agent in 3d world"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01508"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01979"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00479"},{"key":"ref25","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref26","author":"Liu","year":"2024","journal-title":"Uni3d-llm: Unifying point cloud perception, generation and editing with large language models"},{"key":"ref27","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref28","author":"Ma","year":"2022","journal-title":"Sqa3d: Situated question answering in 3d scenes"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref32","author":"Takmaz","year":"2023","journal-title":"Openmask3d: Open-vocabulary 3d instance segmentation"},{"key":"ref33","author":"Wang","year":"2023","journal-title":"Chat-3d: Data-efficiently tuning large language model for universal dialogue of 3d scenes"},{"key":"ref34","author":"Wu","year":"2023","journal-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"ref37","author":"Yang","year":"2023","journal-title":"Mm-react: Prompting chatgpt for multimodal reasoning and action"},{"key":"ref38","author":"Ye","year":"2023","journal-title":"mplug-owl: Modularization empowers large language models with multimodality"},{"key":"ref39","author":"Zhang","year":"2022","journal-title":"Opt: Open pre-trained transformer language models"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00292"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_9"},{"key":"ref43","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"}],"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\/11445543.pdf?arnumber=11445543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:23Z","timestamp":1777611743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445543\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00736","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}