{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:06:03Z","timestamp":1776978363758,"version":"3.51.4"},"reference-count":54,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"InnoHK Program and the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276256"],"award-info":[{"award-number":["62276256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"InnoHK Program and the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306313"],"award-info":[{"award-number":["62306313"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"InnoHK Program and the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2441251"],"award-info":[{"award-number":["U2441251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"InnoHK Program and the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1836217"],"award-info":[{"award-number":["U1836217"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3683282","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T19:56:00Z","timestamp":1776455760000},"page":"4122-4133","source":"Crossref","is-referenced-by-count":0,"title":["Multi-View Images Suffice 3D Reasoning Through Chain-of-Thought Selection and Question-Guided Fusion"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1465-5553","authenticated-orcid":false,"given":"Boqiang","family":"Xu","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences (CASIA), Institute of Automation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlin","family":"Wu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences (CASIA), Institute of Automation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Su","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3890-1894","authenticated-orcid":false,"given":"Jian","family":"Liang","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition and the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-9935","authenticated-orcid":false,"given":"Zhenan","family":"Sun","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition and the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023","journal-title":"arXiv:2308.01390"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_14"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref7","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"issue":"70","key":"ref9","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00357"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CRV55824.2022.00038"},{"key":"ref13","article-title":"MultiModal-GPT: A vision and language model for dialogue with humans","author":"Gong","year":"2023","journal-title":"arXiv:2305.04790"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00888"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref19","first-page":"20413","article-title":"An embodied generalist agent in 3D world","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icra40945.2020.9197519"},{"key":"ref21","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2016.1277554"},{"key":"ref23","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"arXiv:2201.03546"},{"key":"ref24","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref25","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref26","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01298"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28222"},{"key":"ref32","article-title":"Instruction tuning with GPT-4","author":"Peng","year":"2023","journal-title":"arXiv:2304.03277"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref35","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref37","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","author":"Ramakrishnan","year":"2021","journal-title":"arXiv:2109.08238"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"ref40","article-title":"EVA-CLIP: Improved training techniques for CLIP at scale","author":"Sun","year":"2023","journal-title":"arXiv:2303.15389"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"key":"ref42","article-title":"OmniDrive: A holistic vision-language dataset for autonomous driving with counterfactual reasoning","author":"Wang","year":"2024","journal-title":"arXiv:2405.01533"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557620"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-018-1126-y"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3340679"},{"key":"ref46","first-page":"1039","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yi"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_11"},{"key":"ref51","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref52","article-title":"LLaVA-video: Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv:2410.02713"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref54","first-page":"4295","article-title":"LLaVA-3D: A simple yet effective pathway to empowering LMMs with 3D capabilities","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Zhu"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11483343.pdf?arnumber=11483343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:00:34Z","timestamp":1776974434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11483343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3683282","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}