{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:50:16Z","timestamp":1777654216263,"version":"3.51.4"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342093","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"5203-5210","source":"Crossref","is-referenced-by-count":8,"title":["RREx-BoT: Remote Referring Expressions with a Bag of Tricks"],"prefix":"10.1109","author":[{"given":"Gunnar A.","family":"Sigurdsson","sequence":"first","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesse","family":"Thomason","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaurav S.","family":"Sukhatme","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robinson","family":"Piramuthu","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Active visual in-formation gathering for vision-language navigation","author":"Wang","year":"2020","journal-title":"in ECCV"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_37"},{"key":"ref5","volume-title":"Understanding language referring to the visual world","author":"Cirik","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref8","article-title":"Walk the talk: Connecting language, knowledge, and action in route instructions","author":"MacMahon","year":"2006","journal-title":"in AAAI"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7974"},{"key":"ref10","article-title":"Learning to map natural language instructions to physical quadcopter control using simulated flight","author":"Blukis","year":"2019","journal-title":"in CoRL"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093452"},{"key":"ref13","article-title":"Refer360\u00b0: A referring expression recognition dataset in 360\u00b0 images","author":"Cirik","year":"2020","journal-title":"in ACL"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3141150"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01433"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.59"},{"key":"ref17","article-title":"Vision-and-dialog navigation","author":"Thomason","year":"2019","journal-title":"in CoRL"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref20","article-title":"History aware mul-timodal transformer for vision-and-language navigation","author":"Chen","year":"2021","journal-title":"in NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref22","article-title":"Speaker-follower models for vision-and-language navigation","author":"Fried","year":"2018","journal-title":"in NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icra48506.2021.9560736"},{"key":"ref25","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"in NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref29","volume-title":"REVERIE challenge","author":"Qi","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref31","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"Ma","year":"2019","journal-title":"in ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00162"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.332"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01498"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548281"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.026"},{"key":"ref41","volume-title":"SOON challenge","author":"Zhu","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342093.pdf?arnumber=10342093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:15:43Z","timestamp":1703013343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342093","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}