{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T09:33:12Z","timestamp":1780479192794,"version":"3.54.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0117900"],"award-info":[{"award-number":["2022ZD0117900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322607"],"award-info":[{"award-number":["62322607"]}],"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":["62236010"],"award-info":[{"award-number":["62236010"]}],"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":["62276261"],"award-info":[{"award-number":["62276261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L252033"],"award-info":[{"award-number":["L252033"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Fund of the State Key Laboratory of Multimodal Artificial Intelligence Systems","award":["MAIS2025063"],"award-info":[{"award-number":["MAIS2025063"]}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2025QC1566"],"award-info":[{"award-number":["ZR2025QC1566"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010029","name":"Taishan Scholar Foundation of Shandong Province","doi-asserted-by":"publisher","award":["tsqn202507043"],"award-info":[{"award-number":["tsqn202507043"]}],"id":[{"id":"10.13039\/501100010029","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tpami.2026.3658949","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:23:36Z","timestamp":1769721816000},"page":"6525-6540","source":"Crossref","is-referenced-by-count":1,"title":["Fine-Grained Alignment Supervision Matters in Vision-and-Language Navigation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5136-8444","authenticated-orcid":false,"given":"Keji","family":"He","sequence":"first","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8239-7229","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya","family":"Jing","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3631-256X","authenticated-orcid":false,"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Adelaide, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref5","first-page":"3318","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fried","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref7","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref13","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0193"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110511"},{"key":"ref17","first-page":"49684","article-title":"Everyday object meets vision-and-language navigation agent via backdoor","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.271"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.229"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979989"},{"key":"ref24","article-title":"Curriculum audiovisual learning","author":"Hu","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.516"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3318227"},{"key":"ref27","first-page":"13328","article-title":"Curriculum learning for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref29","article-title":"General evaluation for instruction conditioned navigation using dynamic time warping","volume-title":"Proc. Conf. Neural Inf. Process. Syst. Workshop","author":"Ilharco","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00223"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref34","first-page":"652","article-title":"Landmark-RxR: Solving vision-and-language navigation with fine-grained alignment supervision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2078"},{"key":"ref37","first-page":"32340","article-title":"ZSON: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Majumdar","year":"2022"},{"key":"ref38","first-page":"12054","article-title":"FGPrompt: Fine-grained goal prompting for image-goal navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xinyu","year":"2023"},{"key":"ref39","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","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref44","article-title":"Generative language-grounded policy in vision-and-language navigation with Bayes\u2019 rule","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kurita","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00750"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref48","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI Blog"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01501"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01498"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3097435"},{"key":"ref53","article-title":"$A^{2}$A2Nav: Action-aware zero-shot robot navigation by exploiting vision-and-language ability of foundation models","volume-title":"Proc. Conf. Neural Inf. Process. Syst. Workshop","author":"Chen","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref55","article-title":"CLIP-NAV: Using CLIP for zero-shot vision-and-language navigation","volume-title":"Proc. Conf. Robot Learn. Workshop","author":"Dorbala","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20050"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2764"},{"key":"ref61","article-title":"BEVBert: Multimodal map pre-training for language-guided navigation","author":"An","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3185487"},{"key":"ref64","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref68","article-title":"Query-graph with cross-gating attention model for text-to-audio grounding","author":"Tang","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611736"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11512030\/11367462.pdf?arnumber=11367462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T01:52:36Z","timestamp":1778550756000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11367462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":72,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3658949","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":[[2026,6]]}}}