{"id":"https://openalex.org/W7131455192","doi":"https://doi.org/10.1109/icdm65498.2025.00053","title":"The Demon is in Ambiguity: Revisiting Situation Recognition with Single Positive Multi-Label Learning","display_name":"The Demon is in Ambiguity: Revisiting Situation Recognition with Single Positive Multi-Label Learning","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7131455192","doi":"https://doi.org/10.1109/icdm65498.2025.00053"},"language":null,"primary_location":{"id":"doi:10.1109/icdm65498.2025.00053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm65498.2025.00053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"},"type":"article","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/A5126783393","display_name":"Yiming Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiming Lin","raw_affiliation_strings":["School of Advanced Technology, Xi'an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090027536","display_name":"Yuchen Niu","orcid":"https://orcid.org/0009-0007-9719-7549"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Niu","raw_affiliation_strings":["School of Advanced Technology, Xi'an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126848351","display_name":"Shang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shang Wang","raw_affiliation_strings":["School of Advanced Technology, Xi'an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103236934","display_name":"Kaizhu Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaizhu Huang","raw_affiliation_strings":["Digital Innovation Research Center, Duke Kunshan University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"Digital Innovation Research Center, Duke Kunshan University,Suzhou,China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101764076","display_name":"Qiufeng Wang","orcid":"https://orcid.org/0000-0002-6196-3092"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiufeng Wang","raw_affiliation_strings":["School of Advanced Technology, Xi'an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113645564","display_name":"Xiao-Bo Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Bo Jin","raw_affiliation_strings":["School of Advanced Technology, Xi'an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5126783393"],"corresponding_institution_ids":["https://openalex.org/I69356397"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85650107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2881999909877777,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.2881999909877777,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.10840000212192535,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.09350000321865082,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/verb","display_name":"Verb","score":0.5676000118255615},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.47850000858306885},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4131999909877777},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3968999981880188},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.39469999074935913},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.3944999873638153},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39430001378059387},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.36800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878999710083008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6692000031471252},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5174999833106995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4925000071525574},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm65498.2025.00053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm65498.2025.00053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5031626224517822,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G5803907755","display_name":null,"funder_award_id":"92370119,62376113","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2423576022","https://openalex.org/W2604673901","https://openalex.org/W2963346996","https://openalex.org/W2963351448","https://openalex.org/W2970641574","https://openalex.org/W3003365594","https://openalex.org/W3035399403","https://openalex.org/W3096682293","https://openalex.org/W3165691894","https://openalex.org/W4221141431","https://openalex.org/W4312407537","https://openalex.org/W4312535972","https://openalex.org/W4312648273","https://openalex.org/W4312900708","https://openalex.org/W4386076454","https://openalex.org/W4386113239","https://openalex.org/W4387969338","https://openalex.org/W4391528875","https://openalex.org/W4406890907","https://openalex.org/W4409883205","https://openalex.org/W4411244520","https://openalex.org/W4415708387"],"related_works":[],"abstract_inverted_index":{"Context":[0],"recognition":[1,285],"(SR)":[2],"is":[3,120,178,258],"a":[4,72,79,122,153,161,170,187],"fundamental":[5],"task":[6],"in":[7,60,91,164,186,271,294],"computer":[8],"vision":[9],"that":[10,82,117,177,228,262],"aims":[11],"to":[12,86,126,148,181,211,218],"extract":[13],"structured":[14],"semantic":[15,50,129],"summaries":[16],"from":[17],"images":[18],"by":[19],"identifying":[20],"key":[21,109],"events":[22,40],"and":[23,48,55,215,249,266,279,289],"their":[24,49],"associated":[25],"entities.":[26],"Specifically,":[27],"given":[28,135],"an":[29],"input":[30],"image,":[31],"the":[32,37,45,61,88,102,127,136,192,199,235,259,263,272],"model":[33,184],"must":[34],"first":[35,260],"classify":[36],"main":[38],"visual":[39,92],"(verb":[41],"classification),":[42],"then":[43],"identify":[44],"participating":[46],"entities":[47,59],"roles":[51],"(semantic":[52,63],"role":[53,64],"labeling),":[54],"finally":[56],"localize":[57],"these":[58],"image":[62],"localization).":[65],"Existing":[66],"methods":[67],"treat":[68],"verb":[69,97,118,132,150,269],"classification":[70,119,151,270],"as":[71,95,152],"single-label":[73],"problem,":[74],"but":[75],"we":[76,112,146,168,196],"show":[77,227],"through":[78,114],"comprehensive":[80,171],"analysis":[81,116],"this":[83],"formulation":[84],"fails":[85],"address":[87,191],"inherent":[89],"ambiguity":[90],"event":[93],"recognition,":[94],"multiple":[96,144],"categories":[98],"may":[99],"reasonably":[100],"describe":[101],"same":[103],"image.":[104],"This":[105],"paper":[106],"makes":[107],"three":[108],"contributions:":[110],"First,":[111],"reveal":[113],"empirical":[115],"inherently":[121],"multilabel":[123],"problem":[124,159],"due":[125],"ubiquitous":[128],"overlap":[130],"between":[131],"categories.":[133],"Second,":[134],"impracticality":[137],"of":[138,194,268],"fully":[139],"annotating":[140],"large-scale":[141],"datasets":[142,226],"with":[143],"labels,":[145],"propose":[147],"reformulate":[149],"single":[154],"positive":[155],"multi-label":[156,172,188,238],"learning":[157],"(SPMLL)":[158],"-":[160],"novel":[162],"perspective":[163],"SR":[165,176],"research.":[166,286],"Third,":[167],"design":[169],"evaluation":[173],"benchmark":[174],"for":[175,282],"carefully":[179],"designed":[180],"fairly":[182],"evaluate":[183],"performance":[185],"setting.":[189],"To":[190,253],"challenges":[193],"SPMLL,":[195],"futher":[197],"develop":[198],"Graph":[200],"Enhanced":[201],"Verb":[202],"Multilayer":[203],"Perceptron":[204],"(GE-VerbMLP),":[205],"which":[206,275],"combines":[207],"graph":[208],"neural":[209],"networks":[210],"capture":[212],"label":[213],"correlations":[214],"adversarial":[216],"training":[217],"optimize":[219],"decision":[220],"boundaries.":[221],"Extensive":[222],"experiments":[223],"on":[224,234,246],"realworld":[225],"our":[229,254,256],"approach":[230],"achieves":[231],"competitive":[232,245],"improvement":[233],"more":[236],"meaningful":[237],"Average":[239],"Precision":[240],"(MAP)":[241],"metric":[242],"while":[243],"remaining":[244],"traditional":[247],"top-1":[248],"top-5":[250],"accuracy":[251],"metrics.":[252],"knowledge,":[255],"research":[257],"work":[261],"formulate,":[264],"solving,":[265],"evaluating":[267],"SPMLL":[273],"fashion,":[274],"provides":[276],"theoretical":[277],"insights":[278],"practical":[280],"tools":[281],"advancing":[283],"situation":[284],"The":[287],"code":[288],"dataset":[290],"will":[291],"be":[292],"available":[293],"https://github.com/JaMesLiMers/Multi_Label_ImSitu.git.":[295]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-02-26T00:00:00"}