{"id":"https://openalex.org/W7160316175","doi":"https://doi.org/10.1109/wacv61042.2026.00398","title":"HumanBench: Two Heads, No Legs, But Mostly Human, the State of Generative Capabilities in T2I Models","display_name":"HumanBench: Two Heads, No Legs, But Mostly Human, the State of Generative Capabilities in T2I Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160316175","doi":"https://doi.org/10.1109/wacv61042.2026.00398"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081598659","display_name":"Anubhooti Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anubhooti Jain","raw_affiliation_strings":["Indian Institute of Technology Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050521702","display_name":"Mayank Vatsa","orcid":"https://orcid.org/0000-0001-5952-2274"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mayank Vatsa","raw_affiliation_strings":["Indian Institute of Technology Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135410769","display_name":"Richa Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Richa Singh","raw_affiliation_strings":["Indian Institute of Technology Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154549908"],"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":"4087","last_page":"4096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.1128000020980835,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.1128000020980835,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10803","display_name":"Innovative Human-Technology Interaction","score":0.023600000888109207,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11977","display_name":"Technology Use by Older Adults","score":0.0203000009059906,"subfield":{"id":"https://openalex.org/subfields/3317","display_name":"Demography"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5640000104904175},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.33160001039505005},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32440000772476196},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2718000113964081},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.2705000042915344},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.2630999982357025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5691999793052673},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4659000039100647},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2662999927997589},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W3119150854","https://openalex.org/W3153469116","https://openalex.org/W4313026212","https://openalex.org/W4320063407","https://openalex.org/W4390889801","https://openalex.org/W4391468662","https://openalex.org/W4394597443","https://openalex.org/W4402704640","https://openalex.org/W4402754249","https://openalex.org/W4402916399","https://openalex.org/W4402961748","https://openalex.org/W4403601051","https://openalex.org/W4403780713","https://openalex.org/W4404125029","https://openalex.org/W4406610920","https://openalex.org/W4409262647","https://openalex.org/W7133193597","https://openalex.org/W7160182939"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"rapid":[1],"advances,":[2],"text-to-image":[3],"(T2I)":[4],"models":[5,29,88,97],"still":[6],"struggle":[7],"to":[8,26,54],"generate":[9],"anatomically":[10],"coherent":[11],"and":[12,39,49,56,75,94,109,141,151,163],"semantically":[13],"grounded":[14],"humans.":[15],"We":[16],"present":[17],"HumanBench,":[18],"a":[19,65,99,118,135,156],"large-scale":[20],"benchmark":[21],"of":[22,68,81,127,166],"36K":[23],"images":[24],"designed":[25],"evaluate":[27],"T2I":[28,168],"across":[30,121],"four":[31],"axes:":[32],"template":[33],"consistency,":[34],"spatial":[35],"reasoning,":[36],"action":[37],"understanding,":[38],"texture":[40],"recognition.":[41],"To":[42],"quantify":[43],"alignment,":[44],"we":[45,101],"propose":[46],"two":[47],"metrics\u2014Agreement":[48],"Distinction\u2014that":[50],"capture":[51],"both":[52],"fidelity":[53],"prompts":[55],"separation":[57],"from":[58],"counterfactual":[59],"or":[60],"negated":[61],"variants.":[62],"HumanBench":[63,154],"introduces":[64],"formal":[66],"measure":[67],"prompt":[69,149],"complexity":[70],"based":[71],"on":[72,98],"slot":[73],"counts":[74],"compositional":[76,162],"bindings,":[77],"enabling":[78],"controlled":[79,148],"analysis":[80],"model":[82],"performance.":[83],"Evaluating":[84],"three":[85,95],"publicly":[86],"accessible":[87],"(Midjourney,":[89],"Stable":[90],"Diffusion,":[91],"FLUX)":[92],"comprehensively":[93],"additional":[96],"subset,":[100],"find":[102],"persistent":[103],"failures,":[104],"including":[105],"disfigurements,":[106],"species":[107],"leakage,":[108],"counting":[110],"errors.":[111],"Prompt\u2013image":[112],"consistency":[113],"declines":[114],"monotonically":[115],"with":[116],"complexity,":[117],"trend":[119],"observed":[120],"the":[122,161],"models.":[123,169],"A":[124],"human":[125,142,152],"study":[126],"300":[128],"samples":[129],"further":[130],"corroborates":[131],"these":[132],"findings,":[133],"showing":[134],"strong":[136],"correlation":[137],"between":[138],"Agreement":[139],"scores":[140],"ratings.":[143],"By":[144],"unifying":[145],"automated":[146],"metrics,":[147],"design,":[150],"validation,":[153],"provides":[155],"robust":[157],"foundation":[158],"for":[159],"auditing":[160],"anatomical":[164],"capabilities":[165],"modern":[167],"Dataset":[170],"is":[171],"available":[172],"here.":[173]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}