{"id":"https://openalex.org/W4409657093","doi":"https://doi.org/10.1145/3696410.3714536","title":"Perceiving Urban Inequality from Imagery Using Visual Language Models with Chain-of-Thought Reasoning","display_name":"Perceiving Urban Inequality from Imagery Using Visual Language Models with Chain-of-Thought Reasoning","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409657093","doi":"https://doi.org/10.1145/3696410.3714536"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714536","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714536","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714536","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714536","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072345432","display_name":"Yunke Zhang","orcid":"https://orcid.org/0000-0003-0187-6015"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunke Zhang","raw_affiliation_strings":["Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110475051","display_name":"Ruolong Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruolong Ma","raw_affiliation_strings":["Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042093698","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0002-2506-7370"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355277","display_name":"Yong Li","orcid":"https://orcid.org/0000-0001-5617-1659"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072345432"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.0486,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73967068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5342","last_page":"5351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10226","display_name":"Land Use and Ecosystem Services","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10226","display_name":"Land Use and Ecosystem Services","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11963","display_name":"Impact of Light on Environment and Health","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6076393127441406},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4650629162788391},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.431530624628067},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.42624717950820923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40908199548721313},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.36858922243118286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3413727879524231},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2844102382659912},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20488110184669495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6076393127441406},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4650629162788391},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.431530624628067},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.42624717950820923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40908199548721313},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.36858922243118286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3413727879524231},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2844102382659912},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20488110184669495},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696410.3714536","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714536","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714536","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714536","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714536","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714536","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3614744892","display_name":null,"funder_award_id":"U23B2030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409657093.pdf","grobid_xml":"https://content.openalex.org/works/W4409657093.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W1968147892","https://openalex.org/W2030787275","https://openalex.org/W2058336014","https://openalex.org/W2513506629","https://openalex.org/W2769397026","https://openalex.org/W2799003896","https://openalex.org/W2898714626","https://openalex.org/W2927205097","https://openalex.org/W2938085152","https://openalex.org/W2966755844","https://openalex.org/W2990138404","https://openalex.org/W3036037648","https://openalex.org/W3080345162","https://openalex.org/W3080604000","https://openalex.org/W3132455321","https://openalex.org/W3159033417","https://openalex.org/W3174075674","https://openalex.org/W3181398063","https://openalex.org/W3198431721","https://openalex.org/W3215673897","https://openalex.org/W4224317403","https://openalex.org/W4244467125","https://openalex.org/W4288101107","https://openalex.org/W4288317357","https://openalex.org/W4290659920","https://openalex.org/W4293485839","https://openalex.org/W4298205916","https://openalex.org/W4308430910","https://openalex.org/W4317234419","https://openalex.org/W4328127395","https://openalex.org/W4361222057","https://openalex.org/W4367046979","https://openalex.org/W4382138521","https://openalex.org/W4388787344","https://openalex.org/W4390725622","https://openalex.org/W4390755152","https://openalex.org/W4390873312","https://openalex.org/W4391899061","https://openalex.org/W4393160910","https://openalex.org/W4396735245","https://openalex.org/W4399670345","https://openalex.org/W4400092332","https://openalex.org/W4401856724","https://openalex.org/W4401856734","https://openalex.org/W4402716288","https://openalex.org/W4402727885","https://openalex.org/W4404644558","https://openalex.org/W4406481696","https://openalex.org/W6600175564","https://openalex.org/W6604197512"],"related_works":["https://openalex.org/W1507224217","https://openalex.org/W2919725718","https://openalex.org/W975131587","https://openalex.org/W4246879551","https://openalex.org/W2166398115","https://openalex.org/W1519569635","https://openalex.org/W2966707038","https://openalex.org/W4312055991","https://openalex.org/W1511319782","https://openalex.org/W2126857550"],"abstract_inverted_index":{"The":[0,214],"rapid":[1],"pace":[2],"of":[3,27,126,181,206],"urbanization":[4],"has":[5],"led":[6],"to":[7,68,79,140,150],"unequal":[8],"benefits":[9],"for":[10,34,110],"residents,":[11],"creating":[12],"significant":[13],"inequality":[14,28,134,155],"issues":[15],"and":[16,23,48,66,102,163,202,216],"discussions":[17],"around":[18],"Sustainable":[19],"Development":[20],"Goals":[21],"10":[22],"11.":[24],"Accurate":[25],"measurement":[26],"within":[29,72,100,199],"urban":[30,82,127,133,200,211],"areas":[31],"is":[32,108],"essential":[33,153],"effective":[35],"mitigation":[36],"strategies.":[37],"Traditional":[38],"methods":[39,61],"rely":[40],"on":[41],"survey-based":[42],"census":[43],"data,":[44],"which":[45,84],"are":[46,62,218],"time-consuming":[47],"delayed,":[49],"while":[50],"some":[51],"studies":[52],"use":[53],"coarse":[54],"proxies":[55],"like":[56],"nighttime":[57],"lights.":[58],"However,":[59],"these":[60,115],"limited":[63],"by":[64,137,189],"resolution":[65],"fail":[67],"capture":[69],"fine-grained":[70],"disparities":[71],"communities.":[73],"To":[74,113],"address":[75,114],"this,":[76],"we":[77,117],"aim":[78],"leverage":[80],"accessible":[81],"imagery,":[83],"offers":[85,193],"detailed":[86],"visual":[87,129,147],"features.":[88],"Two":[89],"key":[90],"challenges":[91],"must":[92],"be":[93],"addressed:":[94],"1)":[95],"accurately":[96],"perceiving":[97],"micro-level":[98,176],"inequalities":[99,198],"neighborhoods,":[101],"2)":[103],"ensuring":[104],"that":[105,122,170],"this":[106],"perception":[107],"interpretable":[109],"policy":[111],"guidance.":[112],"gaps,":[116],"propose":[118],"UI-CoT,":[119],"a":[120,146],"framework":[121],"leverages":[123],"the":[124,157,179,186,204],"power":[125],"imagery-based":[128],"language":[130,148],"models":[131],"in":[132,209],"perceiving,":[135],"enhanced":[136],"Chain-of-Thought":[138,182],"prompting":[139],"improve":[141],"reasoning":[142,183],"capabilities.":[143],"We":[144],"fine-tune":[145],"model":[149,172],"predict":[151],"three":[152],"neighborhood":[154],"indicators:":[156],"income":[158,165],"Gini":[159],"coefficient,":[160],"dominant":[161],"race,":[162],"racial":[164],"ratio.":[166],"Extensive":[167],"experiments":[168],"show":[169],"our":[171],"can":[173],"effectively":[174],"perceive":[175],"inequalities,":[177],"with":[178],"incorporation":[180],"further":[184],"improving":[185],"model's":[187],"performance":[188],"17.2%.":[190],"This":[191],"research":[192],"valuable":[194],"insights":[195],"into":[196],"addressing":[197],"environments":[201],"demonstrates":[203],"potential":[205],"web":[207],"resources":[208],"empowering":[210],"sustainable":[212],"development.":[213],"code":[215],"data":[217],"available":[219],"at":[220],"https://github.com/tsinghua-fib-lab/UI-CoT.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}