{"id":"https://openalex.org/W4389667623","doi":"https://doi.org/10.1109/iros55552.2023.10342439","title":"FM-Loc: Using Foundation Models for Improved Vision-Based Localization","display_name":"FM-Loc: Using Foundation Models for Improved Vision-Based Localization","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667623","doi":"https://doi.org/10.1109/iros55552.2023.10342439"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008927094","display_name":"Reihaneh Mirjalili","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reihaneh Mirjalili","raw_affiliation_strings":["University of Technology,Department of Engineering,Nuremberg,Germany","Department of Engineering, University of Technology, Nuremberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology,Department of Engineering,Nuremberg,Germany","institution_ids":[]},{"raw_affiliation_string":"Department of Engineering, University of Technology, Nuremberg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015392706","display_name":"Michael Krawez","orcid":"https://orcid.org/0000-0002-8735-317X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Krawez","raw_affiliation_strings":["University of Technology,Department of Engineering,Nuremberg,Germany","Department of Engineering, University of Technology, Nuremberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology,Department of Engineering,Nuremberg,Germany","institution_ids":[]},{"raw_affiliation_string":"Department of Engineering, University of Technology, Nuremberg, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084499878","display_name":"Wolfram Burgard","orcid":"https://orcid.org/0000-0002-5680-6500"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wolfram Burgard","raw_affiliation_strings":["University of Technology,Department of Engineering,Nuremberg,Germany","Department of Engineering, University of Technology, Nuremberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology,Department of Engineering,Nuremberg,Germany","institution_ids":[]},{"raw_affiliation_string":"Department of Engineering, University of Technology, Nuremberg, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.4965,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.98103966,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1381","last_page":"1387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8049594163894653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7900656461715698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7761243581771851},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7439880967140198},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.6400079131126404},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.526803731918335},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5080950260162354},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.501859188079834},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4612096846103668},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4381418228149414},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42946138978004456},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4222831428050995},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4122295081615448},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32252100110054016}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8049594163894653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900656461715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7761243581771851},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7439880967140198},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.6400079131126404},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.526803731918335},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5080950260162354},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.501859188079834},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4612096846103668},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4381418228149414},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42946138978004456},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4222831428050995},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4122295081615448},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32252100110054016},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1521752665","https://openalex.org/W1861492603","https://openalex.org/W2281383810","https://openalex.org/W2739423245","https://openalex.org/W2939122829","https://openalex.org/W2950989657","https://openalex.org/W2951019013","https://openalex.org/W2963037989","https://openalex.org/W3040902650","https://openalex.org/W3104842437","https://openalex.org/W3173736705","https://openalex.org/W3195577433","https://openalex.org/W3197105768","https://openalex.org/W3205239453","https://openalex.org/W4224912544","https://openalex.org/W4226352076","https://openalex.org/W4288041558","https://openalex.org/W4292779060","https://openalex.org/W4298201330","https://openalex.org/W4310557634","https://openalex.org/W4383108296","https://openalex.org/W4383108895","https://openalex.org/W4383109478","https://openalex.org/W4386083015","https://openalex.org/W6755207826","https://openalex.org/W6767357932","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6800751262","https://openalex.org/W6811467201","https://openalex.org/W6843382641","https://openalex.org/W6846479934"],"related_works":["https://openalex.org/W2385368906","https://openalex.org/W2626642044","https://openalex.org/W2902924992","https://openalex.org/W2388758053","https://openalex.org/W93537448","https://openalex.org/W2619807045","https://openalex.org/W2949734191","https://openalex.org/W2017333877","https://openalex.org/W4233821346","https://openalex.org/W4387272257"],"abstract_inverted_index":{"Visual":[0],"place":[1,19,43],"recognition":[2,20],"is":[3,34,52,84,180],"essential":[4],"for":[5,192],"vision-based":[6],"robot":[7],"localization":[8,56],"and":[9,92,115,128,147,164,170],"SLAM.":[10],"Despite":[11],"the":[12,65,73,112,120,129,145,168,190],"tremendous":[13],"progress":[14],"made":[15],"in":[16,21,70,89,101,161],"recent":[17],"years,":[18],"changing":[22],"environments":[23],"remains":[24],"challenging.":[25],"A":[26],"promising":[27],"approach":[28,57,63,153],"to":[29,35,77,86,98,105,118,139,182],"cope":[30],"with":[31,72],"appearance":[32],"variations":[33],"leverage":[36],"high-level":[37],"semantic":[38,80],"features":[39],"like":[40],"objects":[41,100],"or":[42,194],"categories.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,137],"propose":[49,119],"FM-Loc":[50],"which":[51],"a":[53,79,141,183],"novel":[54],"image-based":[55],"based":[58,110],"on":[59,111,154],"Foundation":[60],"Models.":[61],"Our":[62],"uses":[64],"Large":[66],"Language":[67],"Model":[68,75],"GPT-3":[69,104],"combination":[71],"Visual-Language":[74],"CLIP":[76,97,116],"construct":[78],"image":[81,134],"descriptor":[82,135],"that":[83,136,157,177],"robust":[85],"severe":[87],"changes":[88,160],"scene":[90,130],"geometry":[91],"camera":[93,162],"viewpoint.":[94],"We":[95,150],"deploy":[96],"detect":[99],"an":[102,133],"image,":[103],"suggest":[106],"potential":[107],"room":[108],"labels":[109,127],"detected":[113],"objects,":[114],"again":[117],"most":[121],"likely":[122],"location":[123],"label.":[124],"The":[125,173],"object":[126,165],"label":[131],"constitute":[132],"use":[138],"calculate":[140],"similarity":[142],"score":[143],"between":[144,167],"query":[146,171],"database":[148,169],"images.":[149],"validate":[151],"our":[152,178],"real-world":[155],"data":[156],"exhibit":[158],"significant":[159],"viewpoints":[163],"placement":[166],"trajectories.":[172],"experimental":[174],"results":[175],"demonstrate":[176],"method":[179],"applicable":[181],"wide":[184],"range":[185],"of":[186],"indoor":[187],"scenarios":[188],"without":[189],"need":[191],"training":[193],"fine-tuning.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}