{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:41:36Z","timestamp":1730256096672,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611727","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"5198-5204","source":"Crossref","is-referenced-by-count":0,"title":["Guided by the Way: The Role of On-the-route Objects and Scene Text in Enhancing Outdoor Navigation"],"prefix":"10.1109","author":[{"given":"Yanjun","family":"Sun","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Qiu","sequence":"additional","affiliation":[{"name":"Keio University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshimitsu","family":"Aoki","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokatsu","family":"Kataoka","sequence":"additional","affiliation":[{"name":"Keio University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.01075","article-title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","volume-title":"CVPR","author":"Shridhar"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11832"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.findings-emnlp.62","article-title":"Learning to stop: A simple yet effective approach to urban vision-language navigation","volume-title":"EMNLP","author":"Xiang"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.eacl-main.103","article-title":"Multimodal text style transfer for outdoor vision-and-language navigation","volume-title":"EACL","author":"Zhu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.518"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.naacl-main.438","article-title":"Diagnosing vision-and-language navigation: What really matters","volume-title":"NAACL","author":"Zhu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2012.00304"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref13","article-title":"Soat: A scene-and object-aware transformer for vision-and-language navigation","author":"Moudgil","year":"2021","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1655","article-title":"Are you looking? grounding to multiple modalities in vision-and-language navigation","volume-title":"ACL","author":"Hu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/124"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.41"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"article-title":"Cross-lingual vision-language navigation","year":"2019","author":"Yan","key":"ref20"},{"key":"ref21","article-title":"Learning to navigate in cities without a map","author":"Mirowski","year":"2018","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.splu-1.7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6849"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01374-3"},{"article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"NAACL","author":"Devlin","key":"ref25"},{"key":"ref26","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Bidirectional lstm networks for improved phoneme classification and recognition","author":"Graves","year":"2005","journal-title":"Artificial Neural Networks: Formal Models and Their Applications \u2013 ICANN 2005"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep Residual Learning for Image Recognition","volume-title":"CVPR","author":"He"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","volume-title":"MMOCR: A comprehensive toolbox for text detection, recognition and understanding","volume":"abs\/2108.06543","author":"Kuang","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"issue":"7","key":"ref38","first-page":"46","article-title":"Pattern matching: The gestalt approach","volume":"13","author":"Ratcliff","year":"1988","journal-title":"Dr. Dobb\u2019s Journal"},{"key":"ref39","volume":"abs\/1412.6980","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P16-1162","article-title":"Neural machine translation of rare words with subword units","volume-title":"ACL","author":"Sennrich"},{"article-title":"Leveinshtein distance","year":"1965","author":"Levenshtein","key":"ref41"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1181","article-title":"Stay on the path: Instruction fidelity in vision-and-language navigation","volume-title":"ACL","author":"Jain"},{"article-title":"General evaluation for instruction conditioned navigation using dynamic time warping","volume-title":"NeurIPS Visually Grounded Interaction and Language (ViGIL) Workshop","author":"Magalhaes","key":"ref43"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611727.pdf?arnumber=10611727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:20:53Z","timestamp":1723350053000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611727\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611727","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}