{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:17:20Z","timestamp":1775578640610,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["62472387"],"award-info":[{"award-number":["62472387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20326"],"award-info":[{"award-number":["U23A20326"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372414"],"award-info":[{"award-number":["62372414"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M743403"],"award-info":[{"award-number":["2023M743403"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of Major Program","award":["LDQ24F020001"],"award-info":[{"award-number":["LDQ24F020001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3485907","type":"journal-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:31:09Z","timestamp":1729791069000},"page":"2369-2381","source":"Crossref","is-referenced-by-count":15,"title":["ChatNav: Leveraging LLM to Zero-Shot Semantic Reasoning in Object Navigation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6504-8579","authenticated-orcid":false,"given":"Yong","family":"Zhu","sequence":"first","affiliation":[{"name":"Institute of Cyberspace Security and the College of Information Engineering, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2914-912X","authenticated-orcid":false,"given":"Zhenyu","family":"Wen","sequence":"additional","affiliation":[{"name":"Institute of Cyberspace Security and the College of Information Engineering, Zhejiang University of Technology, Hangzhou, China"}]},{"given":"Xiong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Cyberspace Security and the College of Information Engineering, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2945-8344","authenticated-orcid":false,"given":"Xiufang","family":"Shi","sequence":"additional","affiliation":[{"name":"Institute of Cyberspace Security and the College of Information Engineering, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4845-3159","authenticated-orcid":false,"given":"Xiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Cyberspace Security and the College of Information Engineering, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2178-8795","authenticated-orcid":false,"given":"Hui","family":"Dong","sequence":"additional","affiliation":[{"name":"Institute of Cyberspace Security and the College of Information Engineering, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3155-3145","authenticated-orcid":false,"given":"Jiming","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018","journal-title":"arXiv:1807.06757"},{"key":"ref2","article-title":"ObjectNav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020","journal-title":"arXiv:2006.13171"},{"key":"ref3","article-title":"MINOS: Multimodal indoor simulator for navigation in complex environments","author":"Savva","year":"2017","journal-title":"arXiv:1712.03931"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3324380"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291131"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161157"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160259"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341827"},{"key":"ref9","article-title":"DD-PPO: Learning near-perfect PointGoal navigators from 2.5 billion frames","author":"Wijmans","year":"2019","journal-title":"arXiv:1911.00357"},{"key":"ref10","article-title":"Learning to navigate in complex environments","author":"Mirowski","year":"2016","journal-title":"arXiv:1611.03673"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341652"},{"key":"ref13","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chaplot"},{"key":"ref14","article-title":"Learning to explore using active neural SLAM","author":"Singh Chaplot","year":"2020","journal-title":"arXiv:2004.05155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref21","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref22","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"arXiv:2203.02155"},{"key":"ref23","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1169595"},{"key":"ref25","first-page":"1","article-title":"ChatGPT-powered hierarchical comparisons for image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ren"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3349567"},{"key":"ref27","first-page":"1","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref29","article-title":"ESC: Exploration with soft commonsense constraints for zero-shot object navigation","author":"Zhou","year":"2023","journal-title":"arXiv:2301.13166"},{"key":"ref30","article-title":"DeBERTaV3: Improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing","author":"He","year":"2021","journal-title":"arXiv:2111.09543"},{"key":"ref31","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wei"},{"key":"ref32","article-title":"A prompt pattern catalog to enhance prompt engineering with ChatGPT","author":"White","year":"2023","journal-title":"arXiv:2302.11382"},{"key":"ref33","article-title":"Prompt engineering for chatGPT: A quick guide to techniques, tips, and best practices","author":"Ekin","year":"2023","journal-title":"TechRxiv"},{"key":"ref34","first-page":"2683","article-title":"Navigation with large language models: Semantic guesswork as a heuristic for planning","volume-title":"Proc. Conf. Robot Learn.","author":"Shah"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9298-8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.93.4.1591"},{"key":"ref38","first-page":"1","article-title":"Improving context understanding in multimodal large language models via multimodal composition learning","volume-title":"Proc. 40st Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref39","article-title":"Prompt-aware adapter: Towards learning adaptive visual tokens for multimodal large language models","author":"Zhang","year":"2024","journal-title":"arXiv:2405.15684"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235704"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3395352"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01778"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3228908"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10734363.pdf?arnumber=10734363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:52:14Z","timestamp":1741373534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10734363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":43,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3485907","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}