{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:00:48Z","timestamp":1782576048906,"version":"3.54.5"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Fund","award":["62273054"],"award-info":[{"award-number":["62273054"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3395633","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T13:33:11Z","timestamp":1715693591000},"page":"6738-6751","source":"Crossref","is-referenced-by-count":13,"title":["Self-Supervised 3-D Semantic Representation Learning for Vision-and-Language Navigation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2035-2479","authenticated-orcid":false,"given":"Sinan","family":"Tan","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4447-2953","authenticated-orcid":false,"given":"Kuankuan","family":"Sima","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7537-2570","authenticated-orcid":false,"given":"Dunzheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1301-1323","authenticated-orcid":false,"given":"Mengmeng","family":"Ge","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9816-0103","authenticated-orcid":false,"given":"Di","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4042-6044","authenticated-orcid":false,"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","article-title":"Visual semantic navigation using scene priors","author":"Yang","year":"2018","journal-title":"arXiv:1810.06543"},{"key":"ref3","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Thomason"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01281"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1063"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3122579"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183287"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00586"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1108\/RIA-12-2022-0275"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428422"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref15","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"Ma","year":"2019","journal-title":"arXiv:1901.03035"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1268"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref26","first-page":"1","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref28","first-page":"1","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chaplot"},{"key":"ref29","first-page":"706","article-title":"A persistent spatial semantic representation for high-level natural language instruction execution","volume-title":"Proc. Conf. Robot Learn.","author":"Blukis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref32","article-title":"SASRA: Semantically-aware spatio-temporal reasoning agent for vision-and-language navigation in continuous environments","author":"Irshad","year":"2021","journal-title":"arXiv:2108.11945"},{"key":"ref33","first-page":"1","article-title":"Chasing ghosts: Instruction following as Bayesian state tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Anderson"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref37","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref38","first-page":"1","article-title":"SEAL: Self-supervised embodied active learning using exploration and 3D consistency","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chaplot"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00192"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","article-title":"An image is worth 16\\times16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref45","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref46","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for Vision-and-Language tasks","author":"Lu","year":"2019","journal-title":"arXiv:1908.02265"},{"key":"ref47","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018","journal-title":"arXiv:1807.06757"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_19"},{"key":"ref51","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Deng"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref56","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Hong"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01501"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref60","first-page":"7357","article-title":"SOAT: A scene-and object-aware transformer for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Moudgil"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01498"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"ref63","article-title":"Multimodal attention networks for low-level Vision-and-Language navigation","author":"Landi","year":"2019","journal-title":"arXiv:1911.12377"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548281"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548283"},{"key":"ref66","article-title":"ESceme: Vision-and-language navigation with episodic scene memory","author":"Zheng","year":"2023","journal-title":"arXiv:2303.01032"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1108\/RIA-04-2023-0047"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10530430.pdf?arnumber=10530430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:30Z","timestamp":1764959970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":68,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3395633","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}