{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:36:34Z","timestamp":1781714194919,"version":"3.54.5"},"reference-count":27,"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\/iros55552.2023.10342439","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"1381-1387","source":"Crossref","is-referenced-by-count":18,"title":["FM-Loc: Using Foundation Models for Improved Vision-Based Localization"],"prefix":"10.1109","author":[{"given":"Reihaneh","family":"Mirjalili","sequence":"first","affiliation":[{"name":"University of Technology,Department of Engineering,Nuremberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Krawez","sequence":"additional","affiliation":[{"name":"University of Technology,Department of Engineering,Nuremberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wolfram","family":"Burgard","sequence":"additional","affiliation":[{"name":"University of Technology,Department of Engineering,Nuremberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989203"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593691"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3007402"},{"key":"ref4","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Devlin"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref6","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref7","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Robotic navigation with large pretrained models of language, vision, and action","author":"Shah","year":"2022","journal-title":"NeurIPS Workshop on Foundation Models for Decision Making"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561936"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref11","article-title":"CLIP-Nav: Using CLIP for zero-shot vision-and-language navigation","author":"Dorbala","year":"2022","journal-title":"CoRL Workshop on Language and Robotics"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02219"},{"key":"ref13","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning (CoRL)","author":"Brohan"},{"key":"ref14","article-title":"Open-vocabulary queryable scene representations for real world planning","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8080209"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref18","article-title":"Scene classification in indoor environments for robots using context based word embeddings","author":"Chen","year":"2019","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139576"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2512936"},{"key":"ref21","article-title":"Relocalization under substantial appearance changes using hashing","author":"Vysotska","year":"2017","journal-title":"9th Workshop on Planning, Perception and Navigation for Intelligent Vehicles"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3107778"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919839761"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref27","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2022","journal-title":"arXiv preprint"}],"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\/10342439.pdf?arnumber=10342439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:19:34Z","timestamp":1703031574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342439","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}