{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:00:49Z","timestamp":1782576049334,"version":"3.54.5"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122010,61876177"],"award-info":[{"award-number":["62122010,61876177"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/cvpr52688.2022.01501","type":"proceedings-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:56:41Z","timestamp":1664308601000},"page":"15429-15438","source":"Crossref","is-referenced-by-count":40,"title":["Reinforced Structured State-Evolution for Vision-Language Navigation"],"prefix":"10.1109","author":[{"given":"Jinyu","family":"Chen","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erli","family":"Meng","sequence":"additional","affiliation":[{"name":"Xiaomi Inc,Xiaomi AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiaomi Inc,Xiaomi AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2","article-title":"The road to know-where: An object-and-room informed sequential bert for indoor vision-language navigation","author":"wang","year":"2020","journal-title":"ECCV"},{"key":"ref38","first-page":"2","article-title":"Active visual information gathering for vision-language navigation","author":"wang","year":"2020","journal-title":"ECCV"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref30","first-page":"3","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref36","first-page":"6","article-title":"General evaluation for instruction conditioned navigation using dynamic time warping","author":"vihan","year":"2019","journal-title":"NeurIPS"},{"key":"ref35","first-page":"2","article-title":"Know-evolve: Deep temporal reasoning for dynamic knowledge graphs","author":"trivedi","year":"2017","journal-title":"ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.06.024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref13","first-page":"6","article-title":"Language and visual entity relationship graph for agent navigation","author":"hong","year":"2020","journal-title":"NeurIPS"},{"key":"ref14","first-page":"2","article-title":"A recurrent vision-and-language bert for navigation","author":"hong","year":"2021","journal-title":"CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1655"},{"key":"ref16","first-page":"3","article-title":"Bidirectional lstm-crf models for sequence tagging","author":"huang","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref17","first-page":"5","article-title":"General evaluation for instruction conditioned navigation using dynamic time warping","author":"ilharco","year":"2019","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref19","first-page":"2","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"ICLRE"},{"key":"ref28","first-page":"2","article-title":"Deep-walk: Online learning of social representations","author":"perozzi","year":"2014","journal-title":"KDD"},{"key":"ref4","first-page":"2","article-title":"Vision-language navigation with random environmental mixup","author":"chong","year":"2021","journal-title":"ICCV"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref29","first-page":"2","article-title":"Airbert: In-domain pre-training for vision-and-language navigation","author":"pierre-louis","year":"2021","journal-title":"ICCV"},{"key":"ref5","first-page":"2","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref8","first-page":"1","article-title":"Speaker-follower models for vision-and-language navigation","author":"fried","year":"2018","journal-title":"NeurIPS"},{"key":"ref7","first-page":"2","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","author":"deng","year":"2020","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref46","first-page":"6","article-title":"Object-and-action aware model for visual language navigation","author":"yuankai","year":"2020","journal-title":"ECCV"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref21","first-page":"1","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"ma","year":"2019","journal-title":"ICLRE"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref24","first-page":"4","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref41","first-page":"6","article-title":"Look before you leap: Bridging model-free and model-based reinforcement learning for planned-ahead vision-and-language navigation","author":"wang","year":"2018","journal-title":"ECCV"},{"key":"ref23","first-page":"2","article-title":"Improving vision-and-language navigation with image-text pairs from the web","author":"majumdar","year":"2020","journal-title":"ECCV"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67658-2_17"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5984"},{"key":"ref43","first-page":"6","article-title":"Robust navigation with language pretraining and stochastic sampling","author":"xiujun","year":"2019","journal-title":"EMNLP-IJCNLP"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"}],"event":{"name":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"New Orleans, LA, USA","start":{"date-parts":[[2022,6,18]]},"end":{"date-parts":[[2022,6,24]]}},"container-title":["2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/9878378\/9878366\/09878620.pdf?arnumber=9878620","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:56:19Z","timestamp":1665780979000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/9878620\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":47,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/cvpr52688.2022.01501","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}