{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:31:11Z","timestamp":1784399471896,"version":"3.55.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611565","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"17380-17387","source":"Crossref","is-referenced-by-count":63,"title":["Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions"],"prefix":"10.1109","author":[{"given":"Yuxing","family":"Long","sequence":"first","affiliation":[{"name":"Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqi","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhe","family":"Cai","sequence":"additional","affiliation":[{"name":"Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Dong","sequence":"additional","affiliation":[{"name":"Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref3","first-page":"652","article-title":"Landmark-rxr: Solving vision-and-language navigation with finegrained alignment supervision","volume":"34","author":"He","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref5","article-title":"Speaker-follower models for vision-and-language navigation","volume":"31","author":"Fried","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref9","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.22062"},{"key":"ref13","article-title":"Meeting report of the who expert consultation on the definition of extensively drug-resistant tuberculosis, 27-29 october 2020","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3168\/jds.2018-14919"},{"key":"ref15","article-title":"Who expert consultation on public health intervention against early childhood caries: report of a meeting, bangkok, thailand, 26-28 january 2016","volume-title":"World Health Organization, Tech. Rep.","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref20","first-page":"5296","article-title":"Counterfactual vision-and-language navigation: Unravelling the unseen","volume":"33","author":"Parvaneh","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01564"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548283"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref29","volume-title":"Vision-and-dialog navigation","author":"Thomason","year":"2019"},{"key":"ref30","volume-title":"Just ask: An interactive learning framework for vision and language navigation","volume":"abs\/1912.00915","author":"Chi","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00162"},{"key":"ref32","volume-title":"Teach: Task-driven embodied agents that chat","volume":"abs\/2110.00534","author":"Padmakumar","year":"2021"},{"key":"ref33","first-page":"492","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Conference on Robot Learning","author":"Shah"},{"key":"ref34","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref35","author":"Gadre","year":"2022","journal-title":"Clip on wheels: Open-vocabulary models are (almost) zero-shot object navigators"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160969"},{"key":"ref37","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref38","article-title":"Introducing chatgpt","year":"2022"},{"key":"ref39","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref40","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","volume":"abs\/2205.11916","author":"Kojima","year":"2022","journal-title":"Large language models are zero-shot reasoners"},{"key":"ref42","volume":"abs\/2211.10435","author":"Gao","year":"2022","journal-title":"PAL: program-aided language models"},{"key":"ref43","volume":"abs\/2203.11171","author":"Wang","year":"2022","journal-title":"Self-consistency improves chain of thought reasoning in language models"},{"key":"ref44","article-title":"Toolformer: Language models can teach themselves to use tools","author":"Schick","year":"2023"},{"key":"ref45","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface","author":"Shen","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref48","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume":"34","author":"Ding","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","volume":"abs\/2305.06500","author":"Dai","year":"2023","journal-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning"},{"key":"ref50","author":"Zhang","year":"2023","journal-title":"Recognize anything: A strong image tagging model"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611565.pdf?arnumber=10611565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:19:04Z","timestamp":1723349944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611565","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}