{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:58:59Z","timestamp":1783439939529,"version":"3.54.6"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2020AAA0109704"],"award-info":[{"award-number":["2020AAA0109704"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Outstanding Youth Fund","award":["2021B1515020061"],"award-info":[{"award-number":["2021B1515020061"]}]},{"name":"Guangdong Outstanding Youth Fund","award":["M-0461"],"award-info":[{"award-number":["M-0461"]}]},{"name":"Shenzhen Science and Technology Program","award":["GJHZ20220913142600001"],"award-info":[{"award-number":["GJHZ20220913142600001"]}]},{"name":"Nansha Key R&D Program","award":["2022ZD014"],"award-info":[{"award-number":["2022ZD014"]}]},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3407759","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T17:33:38Z","timestamp":1717176818000},"page":"8534-8548","source":"Crossref","is-referenced-by-count":20,"title":["Correctable Landmark Discovery via Large Models for Vision-Language Navigation"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8763-9530","authenticated-orcid":false,"given":"Bingqian","family":"Lin","sequence":"first","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9717-2308","authenticated-orcid":false,"given":"Yunshuang","family":"Nie","sequence":"additional","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5350-7805","authenticated-orcid":false,"given":"Ziming","family":"Wei","sequence":"additional","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5087-895X","authenticated-orcid":false,"given":"Yi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3645-8972","authenticated-orcid":false,"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8340-9762","authenticated-orcid":false,"given":"Shikui","family":"Ma","sequence":"additional","affiliation":[{"name":"Dataa Robotics Company, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7960-9382","authenticated-orcid":false,"given":"Jianzhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"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":"10.1109\/CVPR42600.2020.01000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref7","first-page":"3318","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Fried"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00750"},{"key":"ref12","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma"},{"key":"ref13","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hong"},{"key":"ref14","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Deng"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref16","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref17","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref19","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref20","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.332"},{"key":"ref22","article-title":"LLM-planner: Few-shot grounded planning for embodied agents with large language models","author":"Song","year":"2022"},{"key":"ref23","article-title":"Introducing ChatGPT","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref25","article-title":"Counterfactual vision-and-language navigation via adversarial path sampling","author":"Fu","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref27","first-page":"307","article-title":"Active visual information gathering for vision-language navigation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Wang"},{"key":"ref28","first-page":"6725","article-title":"The regretful agent: Heuristic-aided navigation through progress estimation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Ma"},{"key":"ref29","first-page":"6734","article-title":"Tactical rewind: Self-correction via backtracking in vision-and-language navigation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Ke"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548281"},{"key":"ref33","first-page":"15397","article-title":"HOP: History-and-order aware pre-training for vision-and-language navigation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qiao"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref35","first-page":"7357","article-title":"SOAT: A scene- and object-aware transformer for vision-and-language navigation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Moudgil"},{"key":"ref36","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","author":"Huang","year":"2022"},{"key":"ref37","first-page":"492","article-title":"LM-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Conf. Robot Learn.","author":"Shah"},{"key":"ref38","article-title":"Open-vocabulary queryable scene representations for real world planning","author":"Chen","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.1025"},{"key":"ref40","article-title":"Can an embodied agent find your \u201ccat-shaped mug","author":"Dorbala","year":"2023"},{"key":"ref41","article-title":"Neuro-symbolic procedural planning with commonsense prompting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu"},{"key":"ref42","first-page":"23171","article-title":"Cows on pasture: Baselines and benchmarks for language-driven zero-shot object navigation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Gadre"},{"key":"ref43","first-page":"42829","article-title":"ESC: Exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref44","article-title":"An image is worth 16\u2009\u00d7\u200916 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref48","first-page":"3360","article-title":"Sub-instruction aware vision-and-language navigation","volume-title":"Proc. Conf. Empir. Methods Natural Lang. Process.","author":"Hong"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00646"},{"key":"ref53","first-page":"11975","article-title":"Scaling data generation in vision-and-language navigation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Wang"},{"key":"ref54","article-title":"NavGPT: Explicit reasoning in vision-and-language navigation with large language models","author":"Zhou","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"ref56","article-title":"Perceive, transform, and act: Multi-modal attention networks for vision-and-language navigation","author":"Landi","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.82"},{"key":"ref59","article-title":"spaCy: Industrial-strength natural language processing in Python","author":"Honnibal","year":"2020"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10543121.pdf?arnumber=10543121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:24:11Z","timestamp":1732667051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10543121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":58,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3407759","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}