{"id":"https://openalex.org/W7168393945","doi":"https://doi.org/10.48550/arxiv.2607.12319","title":"DM-KG: A Novel Method for Boosting Spatial Cognition of Vision-Language Models in Street View Imagery","display_name":"DM-KG: A Novel Method for Boosting Spatial Cognition of Vision-Language Models in Street View Imagery","publication_year":2026,"publication_date":"2026-07-14","ids":{"openalex":"https://openalex.org/W7168393945","doi":"https://doi.org/10.48550/arxiv.2607.12319"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.12319","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12319","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.12319","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140867311","display_name":"Xinyue Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xinyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140768415","display_name":"Zheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140845765","display_name":"Kunyang Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Kunyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140769037","display_name":"Ge Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Ge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140870473","display_name":"Lianshuai Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Lianshuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140902023","display_name":"Lei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140783085","display_name":"Zixuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140809970","display_name":"Yi Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8108000159263611,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8108000159263611,"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.07609999924898148,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.05169999971985817,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/geospatial-analysis","display_name":"Geospatial analysis","score":0.7401000261306763},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5637000203132629},{"id":"https://openalex.org/keywords/spatial-cognition","display_name":"Spatial cognition","score":0.5623999834060669},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.5181000232696533},{"id":"https://openalex.org/keywords/cognitive-map","display_name":"Cognitive map","score":0.46970000863075256},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.42329999804496765},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4117000102996826},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3828999996185303},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.37720000743865967},{"id":"https://openalex.org/keywords/volunteered-geographic-information","display_name":"Volunteered geographic information","score":0.3747999966144562}],"concepts":[{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.7401000261306763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024999856948853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5679000020027161},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C2777371692","wikidata":"https://www.wikidata.org/wiki/Q2178611","display_name":"Spatial cognition","level":3,"score":0.5623999834060669},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C170494330","wikidata":"https://www.wikidata.org/wiki/Q1778434","display_name":"Cognitive map","level":3,"score":0.46970000863075256},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C57380593","wikidata":"https://www.wikidata.org/wiki/Q933625","display_name":"Volunteered geographic information","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C41856607","wikidata":"https://www.wikidata.org/wiki/Q483130","display_name":"Geographic information system","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.12319","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12319","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.12319","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12319","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.45268964767456055,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"vision-language":[1],"models":[2],"(VLMs)":[3],"are":[4,59],"increasingly":[5],"deployed":[6],"in":[7,51,74,192,202,232,250],"geospatial":[8,75],"question":[9,247],"answering":[10,248],"and":[11,49,64,103,149,197,241],"visual":[12,246],"scene":[13],"understanding,":[14],"improving":[15],"their":[16,71],"spatial":[17,92,117,141,173,179,227],"cognition":[18],"capability":[19],"on":[20,177],"street":[21,53,96,233],"view":[22,54,97,234],"imagery":[23],"for":[24,70,95,244],"complex":[25],"logical":[26],"reasoning":[27,118,220],"has":[28],"emerged":[29],"as":[30,166],"a":[31,67,89,109,123,156,210,217,238],"key":[32],"research":[33,223],"priority.":[34],"However,":[35],"existing":[36],"VLMs":[37,121,231],"frequently":[38],"suffer":[39],"from":[40,108],"\"spatial":[41],"semantic":[42],"hallucinations\"":[43],"when":[44],"perceiving":[45],"object":[46],"locations,":[47],"distances,":[48],"directions":[50],"real-world":[52],"scenes.":[55],"Furthermore,":[56],"such":[57],"errors":[58],"often":[60],"recalcitrant":[61],"to":[62,136,171],"tracing":[63],"calibration,":[65],"posing":[66],"critical":[68],"bottleneck":[69],"practical":[72],"deployment":[73],"tasks.":[76],"To":[77],"address":[78],"this":[79,82,113,222],"pressing":[80],"challenge,":[81],"study":[83],"proposes":[84],"DM-KG":[85,185],"(Direction-Metric":[86],"Knowledge":[87],"Graph),":[88],"structurally":[90],"grounded":[91],"representation":[93],"framework":[94,114,243],"imagery.":[98],"By":[99,215],"explicitly":[100],"extracting":[101],"directional":[102],"metric":[104,133],"relationships":[105],"between":[106],"entities":[107],"single":[110],"2D":[111],"image,":[112],"enhances":[115],"the":[116,146,164,187,198,226],"accuracy":[119],"of":[120,152,230],"through":[122],"structured":[124],"knowledge":[125,158],"graph.":[126],"Specifically,":[127],"we":[128,144],"integrate":[129],"panoptic":[130],"segmentation":[131],"with":[132],"depth":[134],"estimation":[135,194],"robustly":[137],"compute":[138],"entity-level":[139],"3D":[140],"coordinates.":[142],"Subsequently,":[143],"encode":[145],"clock":[147],"azimuths":[148],"Euclidean":[150],"distances":[151],"entity":[153],"pairs":[154],"into":[155,163],"JSON-formatted":[157],"graph,":[159],"which":[160],"is":[161],"injected":[162],"VLM":[165],"an":[167],"explicit":[168],"geometric":[169],"prior":[170],"guide":[172],"reasoning.":[174],"Experimental":[175],"results":[176],"public":[178],"question-answering":[180],"(QA)":[181],"benchmarks":[182],"demonstrate":[183],"that":[184],"reduces":[186],"mean":[188,199],"absolute":[189],"error":[190,201],"(MAE)":[191],"distance":[193],"by":[195,205],"31.1%":[196],"angular":[200],"direction":[203],"judgment":[204],"65.8%,":[206],"while":[207],"simultaneously":[208],"maintaining":[209],"high":[211],"QA":[212],"success":[213],"rate.":[214],"establishing":[216],"complete,":[218],"augmented":[219],"pipeline,":[221],"significantly":[224],"improves":[225],"cognitive":[228],"capabilities":[229],"scenarios,":[235],"thereby":[236],"providing":[237],"flexible,":[239],"generalized,":[240],"interpretable":[242],"geographic":[245],"(GeoVQA)":[249],"open":[251],"environments.":[252]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-16T00:00:00"}