{"id":"https://openalex.org/W4417080480","doi":"https://doi.org/10.1609/aaai.v40i45.41239","title":"MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes","display_name":"MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W4417080480","doi":"https://doi.org/10.1609/aaai.v40i45.41239"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i45.41239","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i45.41239","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41239/45200","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41239/45200","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053927106","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0002-5880-5974"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liu Liu","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120752087","display_name":"Alexandra Kudaeva","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexandra Schild","raw_affiliation_strings":["Hasso Plattner Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049039335","display_name":"Marco Cipriano","orcid":"https://orcid.org/0000-0003-2087-0831"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Cipriano","raw_affiliation_strings":["Hasso Plattner Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120643521","display_name":"Fatimeh Al Ghannam","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatimeh Al Ghannam","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Freya Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Freya Tan","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085818578","display_name":"Gerard de Melo","orcid":"https://orcid.org/0000-0002-2930-2059"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerard De Melo","raw_affiliation_strings":["Hasso Plattner Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055980218","display_name":"Andres Sevtsuk","orcid":"https://orcid.org/0000-0001-5098-9636"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andres Sevtsuk","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5053927106"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00143164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"45","first_page":"38935","last_page":"38942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6223000288009644,"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":0.6223000288009644,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05009999871253967,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.05000000074505806,"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/bounding-overwatch","display_name":"Bounding overwatch","score":0.5604000091552734},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5022000074386597},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.42969998717308044},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4284000098705292},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.40860000252723694},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4059000015258789},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.3619000017642975},{"id":"https://openalex.org/keywords/interpersonal-communication","display_name":"Interpersonal communication","score":0.33649998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6597999930381775},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400000214576721},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.40860000252723694},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C164850336","wikidata":"https://www.wikidata.org/wiki/Q3685487","display_name":"Interpersonal communication","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C130064352","wikidata":"https://www.wikidata.org/wiki/Q853725","display_name":"Social relation","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C180872759","wikidata":"https://www.wikidata.org/wiki/Q874405","display_name":"Social group","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v40i45.41239","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i45.41239","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41239/45200","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2509.13484","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.13484","pdf_url":"https://arxiv.org/pdf/2509.13484","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2509.13484","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.13484","pdf_url":"https://arxiv.org/pdf/2509.13484","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.13484","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.13484","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i45.41239","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i45.41239","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41239/45200","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1353381076","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G1912064254","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2507572247","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G3251540411","display_name":null,"funder_award_id":"Jetstream2","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4006316252","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4676224565","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4968279142","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G509285653","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5173294414","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G6664589177","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G8165146668","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8300691027","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8819975937","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8897435675","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"},{"id":"https://openalex.org/F4320330883","display_name":"Hasso Plattner Foundation","ror":null},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417080480.pdf","grobid_xml":"https://content.openalex.org/works/W4417080480.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"group-level":[1],"social":[2,54,98],"interactions":[3,23],"in":[4],"public":[5],"spaces":[6],"is":[7],"crucial":[8],"for":[9,136],"urban":[10,127],"planning,":[11],"informing":[12],"the":[13,151],"design":[14],"of":[15,125,160],"socially":[16,109,140],"vibrant":[17],"and":[18,35,62,89,100,116,134,139,148,157],"inclusive":[19],"environments.":[20],"Detecting":[21],"such":[22,31],"from":[24,150],"images":[25,129],"involves":[26],"interpreting":[27],"subtle":[28],"visual":[29,65],"cues":[30],"as":[32],"relations,":[33],"proximity":[34],"co-movement":[36],"\u2013":[37],"semantically":[38],"complex":[39],"signals":[40],"that":[41,83],"go":[42],"beyond":[43],"traditional":[44],"object":[45],"detection.":[46],"To":[47,112],"address":[48],"this":[49,114],"challenge,":[50],"we":[51,120],"introduce":[52],"a":[53,79,102,122],"group":[55],"region":[56],"detection":[57,88],"task,":[58],"which":[59],"requires":[60],"inferring":[61],"spatially":[63],"grounding":[64],"regions":[66],"defined":[67],"by":[68],"abstract":[69],"interpersonal":[70],"relations.":[71],"We":[72],"propose":[73],"MINGLE":[74,152],"(Modeling":[75],"INterpersonal":[76],"Group-Level":[77],"Engagement),":[78],"modular":[80],"three-stage":[81],"pipeline":[82],"integrates:":[84],"(1)":[85],"off-the-shelf":[86],"human":[87],"depth":[90],"estimation,":[91],"(2)":[92],"VLM-based":[93],"reasoning":[94],"to":[95,107],"classify":[96],"pairwise":[97],"affiliation,":[99],"(3)":[101],"lightweight":[103],"spatial":[104],"aggregation":[105],"algorithm":[106],"localize":[108],"connected":[110],"groups.":[111,142],"support":[113],"task":[115],"encourage":[117],"future":[118],"research,":[119],"present":[121],"new":[123],"dataset":[124],"100K":[126],"street-view":[128],"annotated":[130],"with":[131],"bounding":[132],"boxes":[133],"labels":[135,147],"both":[137],"individuals":[138],"interacting":[141],"The":[143],"annotations":[144],"combine":[145],"human-created":[146],"outputs":[149],"pipeline,":[153],"ensuring":[154],"semantic":[155],"richness":[156],"broad":[158],"coverage":[159],"real":[161],"world":[162],"scenarios.":[163]},"counts_by_year":[],"updated_date":"2026-05-15T06:05:50.897203","created_date":"2025-10-10T00:00:00"}
