{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T20:17:01Z","timestamp":1774124221344,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446850","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8331-8335","source":"Crossref","is-referenced-by-count":5,"title":["Graph-Based Environment Representation for Vision-and-Language Navigation in Continuous Environments"],"prefix":"10.1109","author":[{"given":"Ting","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Zongkai","family":"Wu","sequence":"additional","affiliation":[{"name":"Westlake University,Hangzhou,China"}]},{"given":"Feiyu","family":"Yao","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd,2012 Lab,Beijing,China"}]},{"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University,Hangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref3","first-page":"3314","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"NIPS","volume":"31","author":"Fried"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref5","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","volume-title":"ICLR","author":"Ma"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2021.3058314"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_26"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref13","article-title":"Soat: A scene-and object-aware trans-former for vision-and-language navigation","volume-title":"NIPS","author":"Moudgil"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00646"},{"key":"ref17","article-title":"Few-shot learning with graph neural networks","volume-title":"ICLR","author":"Satorras"},{"key":"ref18","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume-title":"NIPS","volume":"33","author":"Hong"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01501"},{"key":"ref22","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"NIPS Workshop","author":"Chung"},{"key":"ref23","article-title":"Behavior proximal policy optimization","author":"Zhuang","year":"2023"},{"key":"ref24","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume-title":"NIPS","volume":"28","author":"Ren"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref29","article-title":"Visual perception generalization for vision-and-language navigation via meta-learning","author":"Wang","year":"2021","journal-title":"IEEE TNNLS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446850.pdf?arnumber=10446850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:26:33Z","timestamp":1722576393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446850","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}