{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T05:15:22Z","timestamp":1735276522150,"version":"3.32.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801563","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"7726-7733","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Language-guided Robot Navigation with Panoramic Semantic Depth Perception and Cross-modal Fusion"],"prefix":"10.1109","author":[{"given":"Liuyi","family":"Wang","sequence":"first","affiliation":[]},{"given":"Jiagui","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Zongtao","family":"He","sequence":"additional","affiliation":[]},{"given":"Ronghao","family":"Dang","sequence":"additional","affiliation":[]},{"given":"Chengju","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Qijun","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref5","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Advances in neural information processing systems","volume":"34","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02223"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326373"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342521"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342107"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref19","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Fried"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107487"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547852"},{"article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","year":"2023","author":"Bhat","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"article-title":"Bert: Pre-training of deep bidi-rectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref30","first-page":"7357","article-title":"Soat: A scene-and object-aware transformer for vision-and-language navigation","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Moudgil"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Dd-ppo: Learning near-perfect point-goal navigators from 2.5 billion frames","year":"2019","author":"Wijmans","key":"ref33"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/164"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06074-8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233554"},{"key":"ref40","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Kenton"},{"article-title":"How much can clip benefit vision-and-language tasks?","volume-title":"International Conference on Learning Representations","author":"Shen","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487258"},{"key":"ref45","first-page":"671","article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"Conference on Robot Learning","author":"Anderson"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801563.pdf?arnumber=10801563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:57:34Z","timestamp":1735196254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801563","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}