{"id":"https://openalex.org/W4399207470","doi":"https://doi.org/10.1109/lra.2024.3408075","title":"PlaceFormer: Transformer-Based Visual Place Recognition Using Multi-Scale Patch Selection and Fusion","display_name":"PlaceFormer: Transformer-Based Visual Place Recognition Using Multi-Scale Patch Selection and Fusion","publication_year":2024,"publication_date":"2024-05-31","ids":{"openalex":"https://openalex.org/W4399207470","doi":"https://doi.org/10.1109/lra.2024.3408075"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3408075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3408075","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5081044092","display_name":"Shyam Sundar Kannan","orcid":"https://orcid.org/0000-0002-8099-8434"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shyam Sundar Kannan","raw_affiliation_strings":["Department of Computer and Information Technology, SMART Lab, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-8099-8434","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, SMART Lab, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076467173","display_name":"Byung\u2010Cheol Min","orcid":"https://orcid.org/0000-0001-6458-4365"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byung-Cheol Min","raw_affiliation_strings":["Department of Computer and Information Technology, SMART Lab, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-6458-4365","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, SMART Lab, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":2.5709,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90669393,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"9","issue":"7","first_page":"6552","last_page":"6559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9990000128746033,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.991100013256073,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7675608992576599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7584328651428223},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6077147722244263},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5286075472831726},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49396783113479614},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46901363134384155},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41920116543769836},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08607611060142517}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7675608992576599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7584328651428223},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6077147722244263},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5286075472831726},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49396783113479614},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46901363134384155},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41920116543769836},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08607611060142517},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3408075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3408075","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/W1491719799","https://openalex.org/W2073761981","https://openalex.org/W2103924867","https://openalex.org/W2119605622","https://openalex.org/W2124386111","https://openalex.org/W2284029970","https://openalex.org/W2342383553","https://openalex.org/W2544587078","https://openalex.org/W2737075200","https://openalex.org/W2740418457","https://openalex.org/W2884148180","https://openalex.org/W2902101981","https://openalex.org/W2951019013","https://openalex.org/W2963588253","https://openalex.org/W2997164612","https://openalex.org/W3034213661","https://openalex.org/W3034275286","https://openalex.org/W3081509258","https://openalex.org/W3095367607","https://openalex.org/W3110536152","https://openalex.org/W3128099838","https://openalex.org/W3173736705","https://openalex.org/W4312336574","https://openalex.org/W4312597490","https://openalex.org/W4312854990","https://openalex.org/W4313887343","https://openalex.org/W4319300119","https://openalex.org/W4366208220","https://openalex.org/W4386066001","https://openalex.org/W6636494156","https://openalex.org/W6784333009","https://openalex.org/W6790570412","https://openalex.org/W6851800889"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W4293226380","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2077542787","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2070401501","https://openalex.org/W2121496884"],"abstract_inverted_index":{"Visual":[0],"place":[1,26,34,49,69,100],"recognition":[2,35,50,70],"is":[3,74,185],"a":[4,22,25,94,179],"challenging":[5],"task":[6],"in":[7,32,60,151,210],"the":[8,45,48,53,61,65,68,79,83,107,123,128,132,139,168,190],"field":[9],"of":[10,55,67,82,212],"computer":[11],"vision,":[12],"and":[13,16,40,57,214,220],"autonomous":[14],"robotics":[15],"vehicles,":[17],"which":[18,114],"aims":[19],"to":[20,76,109,134,148,177,188],"identify":[21],"location":[23],"or":[24],"from":[27,106,131,171],"visual":[28,33,99],"inputs.":[29],"Contemporary":[30],"methods":[31,209],"employ":[36],"convolutional":[37],"neural":[38],"networks":[39],"utilize":[41],"every":[42],"region":[43],"within":[44],"image":[46,62,84,112,119,196],"for":[47,85,98,118],"task.":[51],"However,":[52],"presence":[54],"dynamic":[56],"distracting":[58],"elements":[59],"can":[63],"impact":[64],"effectiveness":[66],"process.":[71],"Therefore,":[72],"it":[73,143],"meaningful":[75],"focus":[77],"on":[78,200],"task-relevant":[80,149],"regions":[81],"improved":[86],"recognition.":[87,101],"In":[88],"this":[89],"paper,":[90],"we":[91],"present":[92],"PlaceFormer,":[93],"novel":[95],"transformer-based":[96],"approach":[97],"PlaceFormer":[102,126,205],"uses":[103],"patch":[104,129,165,173],"tokens":[105,130],"transformer":[108,133],"create":[110],"global":[111,195],"descriptors,":[113],"are":[115,175],"then":[116,186],"used":[117,187],"retrieval.":[120],"To":[121],"re-rank":[122,189],"retrieved":[124,193],"images,":[125],"merges":[127],"form":[135],"multi-scale":[136],"patches.":[137],"Utilizing":[138],"transformer's":[140],"self-attention":[141],"mechanism,":[142],"selects":[144],"patches":[145,156],"that":[146,204],"correspond":[147],"areas":[150],"an":[152],"image.":[153],"These":[154],"selected":[155],"undergo":[157],"geometric":[158],"verification,":[159],"generating":[160],"similarity":[161,181],"scores":[162,170],"across":[163],"different":[164],"sizes.":[166],"Subsequently,":[167],"spatial":[169],"each":[172],"size":[174],"fused":[176],"produce":[178],"final":[180],"score.":[182],"This":[183],"score":[184],"images":[191],"initially":[192],"using":[194],"descriptors.":[197],"Extensive":[198],"experiments":[199],"benchmark":[201],"datasets":[202],"demonstrate":[203],"outperforms":[206],"several":[207],"state-of-the-art":[208],"terms":[211],"accuracy":[213],"computational":[215],"efficiency,":[216],"requiring":[217],"less":[218],"time":[219],"memory.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}