{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T20:17:09Z","timestamp":1774124229188,"version":"3.50.1"},"reference-count":14,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang province","doi-asserted-by":"publisher","award":["LZ19F020001"],"award-info":[{"award-number":["LZ19F020001"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hangzhou Postdoctoral Research Foundation","award":["103126582001"],"award-info":[{"award-number":["103126582001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE MultiMedia"],"published-print":{"date-parts":[[2021,10,1]]},"DOI":"10.1109\/mmul.2021.3058314","type":"journal-article","created":{"date-parts":[[2021,2,10]],"date-time":"2021-02-10T02:57:35Z","timestamp":1612925855000},"page":"55-63","source":"Crossref","is-referenced-by-count":11,"title":["Improved Speaker and Navigator for Vision-and-Language Navigation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8141-1108","authenticated-orcid":false,"given":"Zongkai","family":"Wu","sequence":"first","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihan","family":"Liu","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2679-6556","authenticated-orcid":false,"given":"Ting","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1359-6440","authenticated-orcid":false,"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref11","article-title":"Perceive, transform, and act: Multi-modal attention networks for vision-and-language navigation","author":"landi","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref13","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref5","first-page":"3314","article-title":"Speaker-follower models for vision-and-language navigation","author":"fried","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref8","first-page":"2249","article-title":"A decomposable attention model for natural language inference","author":"a","year":"2016","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref7","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"ma","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref9","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"}],"container-title":["IEEE MultiMedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/93\/9642027\/09351621.pdf?arnumber=9351621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:22Z","timestamp":1652194282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9351621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,1]]},"references-count":14,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/mmul.2021.3058314","relation":{},"ISSN":["1070-986X","1941-0166"],"issn-type":[{"value":"1070-986X","type":"print"},{"value":"1941-0166","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,1]]}}}