{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:13:06Z","timestamp":1740175986251,"version":"3.37.3"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lra.2024.3511404","type":"journal-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T19:19:21Z","timestamp":1733339961000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Target Localization with Landmark-Aware Positioning for Urban Mobility"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6119-418X","authenticated-orcid":false,"given":"Naoki","family":"Hosomi","sequence":"first","affiliation":[{"name":"Keio University, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1353-4549","authenticated-orcid":false,"given":"Yui","family":"Iioka","sequence":"additional","affiliation":[{"name":"Keio University, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6338-3098","authenticated-orcid":false,"given":"Shumpei","family":"Hatanaka","sequence":"additional","affiliation":[{"name":"Keio University, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6398-9245","authenticated-orcid":false,"given":"Teruhisa","family":"Misu","sequence":"additional","affiliation":[{"name":"Honda Research Institute USA Inc., San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8202-7417","authenticated-orcid":false,"given":"Kentaro","family":"Yamada","sequence":"additional","affiliation":[{"name":"Honda R&D Co., Ltd., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8489-600X","authenticated-orcid":false,"given":"Nanami","family":"Tsukamoto","sequence":"additional","affiliation":[{"name":"Honda R&D Co., Ltd., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6282-0698","authenticated-orcid":false,"given":"Shunsuke","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"SOLIZE Corporation., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0261-0510","authenticated-orcid":false,"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[{"name":"Keio University, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.02.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19952"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636172"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3376957"},{"key":"ref7","first-page":"37511","article-title":"DesCo: Learning Object Recognition with Rich Language Descriptions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2023"},{"key":"ref8","first-page":"1","article-title":"VoLTA: Vision-language transformer with weakly-supervised local-feature alignment","author":"Pramanick","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref9","article-title":"Survey on multimodal transformers for robots","volume-title":"Authorea Preprints","author":"Miyazawa","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref18","first-page":"32942","article-title":"Coarse-to-fine vision-language pre-training with fusion in the backbone","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dou","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01890"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00286"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3224144"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"GPT-4 Technical Report","year":"2023","author":"Achiam","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1220175.1220306"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref32","first-page":"1","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"volume-title":"RoBERTa: A robustly optimized BERT pretraining approach","year":"2019","author":"Liu","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/7339444\/10777394.pdf?arnumber=10777394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T06:29:20Z","timestamp":1734157760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10777394\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3511404","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2024]]}}}