{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:41:12Z","timestamp":1766061672136,"version":"3.48.0"},"reference-count":41,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011160","name":"State Key Laboratory of Virtual Reality Technology and Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011160","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002358","name":"Beihang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002358","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\/iros60139.2025.11247159","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"5924-5929","source":"Crossref","is-referenced-by-count":0,"title":["3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering"],"prefix":"10.1109","author":[{"given":"Rongtao","family":"Xu","sequence":"first","affiliation":[{"name":"Spatialtemporal AI"}]},{"given":"Han","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}]},{"given":"Mingming","family":"Yu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}]},{"given":"Dong","family":"An","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}]},{"given":"Shunpeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}]},{"given":"Changwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Shandong Computer Science Center,Key Laboratory of Computing Power Network and Information Security, Ministry of Education"}]},{"given":"Li","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,China"}]},{"given":"Shibiao","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102344"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32811"},{"article-title":"Generating context-aware natural answers for questions in 3d scenes","year":"2023","author":"Dwedari","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387838"},{"article-title":"A prompt pattern catalog to enhance prompt engineering with chatgpt","year":"2023","author":"White","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548365"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.47363\/jmca\/2024(3)e121"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3366154"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3340679"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229081"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296889"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"issue":"70","key":"ref17","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103652"},{"key":"ref19","article-title":"Visual instruction tuning","volume-title":"Advances in neural information processing systems","volume":"36","author":"Liu"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref20"},{"key":"ref21","first-page":"1","article-title":"Roberta: A robustly optimized bert pretraining approach (2019)","author":"Yinhan","year":"2019"},{"article-title":"Wic: the word-in-context dataset for evaluating context-sensitive meaning representations","year":"2018","author":"Pilehvar","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proceedings of the Workshop on Text Summarization Branches Out, 2004","author":"Chin-Yew","key":"ref27"},{"key":"ref28","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"article-title":"Opt: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref33"},{"key":"ref34","first-page":"20 482","article-title":"3d-llm: Injecting the 3d world into large language models","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Hong"},{"article-title":"Evaluating zero-shot gpt-4v performance on 3d visual question answering benchmarks","year":"2024","author":"Singh","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW63481.2024.10645462"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"article-title":"Chat-3d v2: Bridging 3d scene and large language models with object identifiers","year":"2023","author":"Huang","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_31"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247159.pdf?arnumber=11247159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:50Z","timestamp":1766061470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247159","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}