{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T20:17:04Z","timestamp":1774124224840,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,12,1]]},"DOI":"10.1109\/tpami.2020.2972281","type":"journal-article","created":{"date-parts":[[2020,2,7]],"date-time":"2020-02-07T21:17:36Z","timestamp":1581110256000},"page":"4205-4216","source":"Crossref","is-referenced-by-count":20,"title":["Vision-Language Navigation Policy Learning and Adaptation"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2605-5504","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuyuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asli","family":"Celikyilmaz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinghan","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan-Fang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William Yang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6926-0538","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1479","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01281"},{"key":"ref33","first-page":"3318","article-title":"Speaker-follower models for vision-and-language navigation","author":"fried","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref31","article-title":"On evaluation of embodied navigation agents","author":"anderson","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref36","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"ma","year":"2019","journal-title":"Proc 7th Int Conf Learn Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1197"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139984"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref2","article-title":"Ai2-thor: An interactive 3d environment for visual ai","author":"kolve","year":"2017"},{"key":"ref1","article-title":"Minos: Multimodal indoor simulator for navigation in complex environments","author":"savva","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref26","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref57","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"Proc 4th Int Conf Learn Representations"},{"key":"ref56","article-title":"A deep reinforced model for abstractive summarization","author":"paulus","year":"2018","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref11","first-page":"6456","article-title":"Turbo learning for captionbot and drawingbot","author":"huang","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1561\/1500000074"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref3","first-page":"1","article-title":"Embodied question answering","author":"das","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1083"},{"key":"ref5","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","first-page":"2422","article-title":"Mind’s eye: A recurrent visual representation for image caption generation","author":"chen","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref49","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref47","first-page":"3878","article-title":"Self-imitation learning","author":"oh","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref42","first-page":"2721","article-title":"Count-based exploration with neural density models","author":"ostrovski","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref41","first-page":"1109","article-title":"Vime: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref44","article-title":"Adaptive confidence and adaptive curiosity","author":"schmidhuber","year":"1991","journal-title":"Institut fur Informatik Technische Universitat Munchen Arcisstr 21 800 Munchen 2"},{"key":"ref43","first-page":"2753","article-title":"# Exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9600479\/08986691.pdf?arnumber=8986691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:12Z","timestamp":1652194152000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8986691\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,1]]},"references-count":59,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.2972281","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":[[2021,12,1]]}}}