{"id":"https://openalex.org/W7138831005","doi":"https://doi.org/10.1016/j.neucom.2026.133399","title":"TF-VPR: A novel benchmark for training-free visual place recognition","display_name":"TF-VPR: A novel benchmark for training-free visual place recognition","publication_year":2026,"publication_date":"2026-03-18","ids":{"openalex":"https://openalex.org/W7138831005","doi":"https://doi.org/10.1016/j.neucom.2026.133399"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133399","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133399","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neucom.2026.133399","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063685861","display_name":"C. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxu Wang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China"],"raw_orcid":"https://orcid.org/0009-0005-6139-4327","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129925450","display_name":"Qingtong Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I31595395","display_name":"Chengdu University of Technology","ror":"https://ror.org/05pejbw21","country_code":"CN","type":"education","lineage":["https://openalex.org/I31595395"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingtong Meng","raw_affiliation_strings":["School of Geography Planning, Chengdu University of Technology, Chengdu, Sichuan 610000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Geography Planning, Chengdu University of Technology, Chengdu, Sichuan 610000, China","institution_ids":["https://openalex.org/I31595395"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038323543","display_name":"Bonan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bonan Zhang","raw_affiliation_strings":["Enterprise AI and Data Analytics Hub, RMIT University, Melbourne, VIC 3000, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enterprise AI and Data Analytics Hub, RMIT University, Melbourne, VIC 3000, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122871227","display_name":"Fusen Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Fusen Guo","raw_affiliation_strings":["School of Systems and Computing, UNSW Canberra, Canberra, ACT 2600, Australia"],"raw_orcid":"https://orcid.org/0009-0007-9142-697X","affiliations":[{"raw_affiliation_string":"School of Systems and Computing, UNSW Canberra, Canberra, ACT 2600, Australia","institution_ids":["https://openalex.org/I188329596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5122871227"],"corresponding_institution_ids":["https://openalex.org/I188329596"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":{"value":2470,"currency":"USD","value_usd":2470},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59718119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"681","issue":null,"first_page":"133399","last_page":"133399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.7039999961853027,"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":0.7039999961853027,"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":0.2264000028371811,"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":0.011500000022351742,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7827000021934509},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.713699996471405},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5005999803543091},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49459999799728394},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4893999993801117},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44859999418258667},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.41929998993873596},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4023999869823456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8432000279426575},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7827000021934509},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.713699996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6484000086784363},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4708999991416931},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44859999418258667},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.41929998993873596},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3750999867916107},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3562000095844269},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27639999985694885}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133399","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133399","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.neucom.2026.133399","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133399","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5989390015602112,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1974093076","https://openalex.org/W1989484209","https://openalex.org/W2112669647","https://openalex.org/W2535547924","https://openalex.org/W2558027072","https://openalex.org/W3130365871","https://openalex.org/W3137393880","https://openalex.org/W4375956270","https://openalex.org/W4389819300","https://openalex.org/W4407056550","https://openalex.org/W4408017101","https://openalex.org/W4408780442","https://openalex.org/W4408860302","https://openalex.org/W4409763749","https://openalex.org/W7117304201"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Place":[1],"Recognition":[2],"(VPR)":[3],"is":[4],"essential":[5],"for":[6,109,120,178],"robotics":[7],"and":[8,33,54,60,86,115,139,150,161,171,183],"autonomous":[9],"navigation,":[10],"yet":[11],"most":[12],"methods":[13],"rely":[14],"on":[15],"heavy":[16],"task-specific":[17],"training.":[18],"Existing":[19],"approaches":[20],"fall":[21],"into":[22],"two":[23,141],"main":[24],"paradigms:":[25],"single-stage":[26],"models":[27],"that":[28,36,69,166],"learn":[29],"compact":[30],"global":[31,39],"descriptors,":[32],"two-stage":[34],"pipelines":[35],"combine":[37],"coarse":[38],"retrieval":[40,162],"with":[41],"local":[42],"feature":[43],"or":[44],"geometric":[45],"verification.":[46],"While":[47],"effective,":[48],"both":[49],"require":[50],"large":[51],"annotated":[52],"datasets":[53,134,184],"carefully":[55],"tuned":[56],"optimization,":[57],"limiting":[58],"scalability":[59],"cross-domain":[61],"reuse.":[62],"We":[63],"introduce":[64],"TF-VPR,":[65],"a":[66,71,117],"new":[67,169],"benchmark":[68],"tackles":[70],"more":[72],"challenging":[73],"setting:":[74],"VPR":[75,133],"performed":[76],"entirely":[77],"without":[78,125],"additional":[79],"training,":[80],"where":[81],"descriptors":[82],"are":[83,185],"generated,":[84],"refined":[85],"matched":[87],"only":[88],"at":[89,187],"test":[90],"time.":[91],"Enabled":[92],"by":[93],"recent":[94],"Vision":[95],"Foundation":[96],"Models":[97],"(VFMs),":[98],"TF-VPR":[99,167],"systematically":[100],"evaluates":[101],"how":[102],"far":[103],"pretrained":[104],"VFMs":[105,124,177],"can":[106],"be":[107],"pushed":[108],"place":[110,180],"recognition":[111],"when":[112],"used":[113],"as-is,":[114],"provides":[116],"standardized":[118],"protocol":[119],"fairly":[121],"comparing":[122],"arbitrary":[123],"fine-tuning.":[126],"To":[127],"support":[128],"this,":[129],"we":[130],"unify":[131],"major":[132],"covering":[135],"diverse":[136],"real-world":[137],"conditions":[138],"propose":[140],"lightweight,":[142],"training-free":[143,179],"modules:":[144],"Training-Free":[145,151],"Graph-Attention":[146],"Graph":[147],"Module":[148,153],"(TF-GAM)":[149],"Cross-Attention":[152],"(TF-CAM).":[154],"These":[155],"plug-and-play":[156],"modules":[157],"enhance":[158],"descriptor":[159],"discriminability":[160],"robustness.":[163],"Experiments":[164],"show":[165],"exposes":[168],"challenges":[170],"reveals":[172],"previously":[173],"unexplored":[174],"strengths":[175],"of":[176],"recognition.":[181],"Code":[182],"available":[186],"https://github.com/ddfs430/TF-VPR":[188],".":[189]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-03-20T00:00:00"}