{"id":"https://openalex.org/W7123363249","doi":"https://doi.org/10.1109/access.2026.3651636","title":"FD-DeCap: A Front-Door Causal Inference-Based Framework for Debiasing Automatic Audio Captioning","display_name":"FD-DeCap: A Front-Door Causal Inference-Based Framework for Debiasing Automatic Audio Captioning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123363249","doi":"https://doi.org/10.1109/access.2026.3651636"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3651636","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3651636","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3651636","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091211713","display_name":"Jinyun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I137506752","display_name":"North China University of Science and Technology","ror":"https://ror.org/04z4wmb81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137506752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinyun Liu","raw_affiliation_strings":["College of Artificial Intelligence, North China University of Science and Technology, Tangshan, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, North China University of Science and Technology, Tangshan, China","institution_ids":["https://openalex.org/I137506752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122901251","display_name":"Hui Li","orcid":null},"institutions":[{"id":"https://openalex.org/I137506752","display_name":"North China University of Science and Technology","ror":"https://ror.org/04z4wmb81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137506752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["College of Artificial Intelligence, North China University of Science and Technology, Tangshan, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, North China University of Science and Technology, Tangshan, China","institution_ids":["https://openalex.org/I137506752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122859126","display_name":"Mingjun Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I137506752","display_name":"North China University of Science and Technology","ror":"https://ror.org/04z4wmb81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137506752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjun Wei","raw_affiliation_strings":["College of Artificial Intelligence, North China University of Science and Technology, Tangshan, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, North China University of Science and Technology, Tangshan, China","institution_ids":["https://openalex.org/I137506752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030607091","display_name":"Zhanlin Ji","orcid":"https://orcid.org/0000-0003-3527-3773"},"institutions":[{"id":"https://openalex.org/I1284762954","display_name":"Zhejiang A & F University","ror":"https://ror.org/02vj4rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I1284762954"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanlin Ji","raw_affiliation_strings":["College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, China","institution_ids":["https://openalex.org/I1284762954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456227","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0002-2947-1629"},"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":"Haiyang Zhang","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/A5002555209","display_name":"\u0418\u0432\u0430\u043d \u0413\u0430\u043d\u0447\u0435\u0432","orcid":"https://orcid.org/0000-0003-0535-7087"},"institutions":[{"id":"https://openalex.org/I230495080","display_name":"University of Limerick","ror":"https://ror.org/00a0n9e72","country_code":"IE","type":"education","lineage":["https://openalex.org/I230495080"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Ivan Ganchev","raw_affiliation_strings":["TRC/ECE, University of Limerick, Limerick, Ireland"],"affiliations":[{"raw_affiliation_string":"TRC/ECE, University of Limerick, Limerick, Ireland","institution_ids":["https://openalex.org/I230495080"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091211713"],"corresponding_institution_ids":["https://openalex.org/I137506752"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08609816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"6029","last_page":"6042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.4887999892234802,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.4887999892234802,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.17270000278949738,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.06970000267028809,"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/spurious-relationship","display_name":"Spurious relationship","score":0.8737999796867371},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7451000213623047},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5957000255584717},{"id":"https://openalex.org/keywords/debiasing","display_name":"Debiasing","score":0.590499997138977},{"id":"https://openalex.org/keywords/identifiability","display_name":"Identifiability","score":0.46480000019073486},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.42309999465942383},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.41819998621940613},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4025999903678894}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.8737999796867371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080000281333923},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7451000213623047},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5957000255584717},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.590499997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.474700003862381},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3937999904155731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38690000772476196},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3084999918937683},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C175652121","wikidata":"https://www.wikidata.org/wiki/Q4379351","display_name":"Causal consistency","level":5,"score":0.266400009393692},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3651636","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3651636","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3651636","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3651636","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2322810405","display_name":null,"funder_award_id":"2017YFE0135700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320320862","display_name":"University of Limerick","ror":"https://ror.org/00a0n9e72"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2314112549","https://openalex.org/W2506483933","https://openalex.org/W2587741066","https://openalex.org/W2779135360","https://openalex.org/W2885195348","https://openalex.org/W2949376505","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3160577380","https://openalex.org/W3165117809","https://openalex.org/W3171353004","https://openalex.org/W4200622433","https://openalex.org/W4221153784","https://openalex.org/W4248217291","https://openalex.org/W4312095907","https://openalex.org/W4312232840","https://openalex.org/W4312898271","https://openalex.org/W4321374970","https://openalex.org/W4362709188","https://openalex.org/W4387870967","https://openalex.org/W4391358569","https://openalex.org/W4392903210","https://openalex.org/W4392909554","https://openalex.org/W4408352941"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Audio":[1],"Captioning":[2],"(AAC)":[3],"aims":[4],"at":[5],"generating":[6],"natural":[7],"language":[8],"descriptions":[9],"for":[10,44,228],"audio":[11,63],"content.":[12],"However,":[13],"existing":[14],"methods":[15],"are":[16],"often":[17],"affected":[18],"by":[19,209],"latent":[20,210],"confounders":[21,211],"and":[22,32,92,95,104,132,140,163,174,187,212,218,223],"spurious":[23,114,213],"co-occurrence":[24],"patterns":[25],"in":[26,62,232],"the":[27,45,82,86,130,148,153,169,180,188,201,229],"data,":[28],"leading":[29],"to":[30,65,80,126],"bias":[31,207],"semantic":[33,216],"inaccuracies.":[34],"This":[35],"paper":[36],"proposes":[37],"FD-DeCap,":[38],"a":[39,72,77,97,225],"front-door":[40,87,149],"causal":[41,145],"inference-based":[42],"framework,":[43],"AAC":[46,230],"task.":[47],"The":[48],"framework":[49,204],"consists":[50],"of":[51,85,138,147,158,220],"three":[52],"core":[53],"components:":[54],"(1)":[55],"an":[56],"AudioAug":[57],"module":[58,74],"introduces":[59,76],"noise":[60],"perturbations":[61],"features":[64],"enhance":[66],"robustness":[67,219],"against":[68],"environmental":[69],"interference;":[70],"(2)":[71],"MedGate":[73],"explicitly":[75],"mediator":[78,110,181],"variable":[79],"satisfy":[81],"identifiability":[83],"conditions":[84],"criterion,":[88],"thereby":[89],"disentangling":[90],"direct":[91],"indirect":[93],"effects;":[94],"(3)":[96],"MSeCE":[98],"consistency":[99,217],"loss":[100],"jointly":[101],"optimizes":[102],"cross-entropy":[103],"MSE":[105],"constraints,":[106],"encouraging":[107],"reliance":[108],"on":[109,129,152],"representations":[111],"rather":[112],"than":[113],"correlations.":[115],"Experimental":[116],"results":[117],"demonstrate":[118],"that":[119,200],"FD-DeCap":[120,203],"achieves":[121],"stable":[122],"performance":[123],"improvements,":[124],"compared":[125],"state-of-the-art":[127],"frameworks,":[128],"Clotho":[131,154],"AudioCaps":[133],"datasets,":[134],"with":[135],"SPIDEr":[136],"scores":[137],"0.282":[139],"0.429,":[141],"respectively.":[142],"A":[143],"multi-perspective":[144],"validation":[146],"adjustment,":[150],"performed":[151],"dataset,":[155],"includes":[156],"analyzes":[157],"similarity-score":[159],"distributions,":[160,162],"feature":[161,182],"representative":[164,189],"case":[165],"studies.":[166],"After":[167],"debiasing,":[168],"similarity":[170],"between":[171],"generated":[172,221],"captions":[173,176],"reference":[175],"shifts":[177],"upward":[178],"overall,":[179],"distributions":[183],"become":[184],"more":[185,191],"dispersed,":[186],"cases":[190],"accurately":[192],"capture":[193],"true":[194],"acoustic":[195,234],"scenes.":[196],"These":[197],"findings":[198],"indicate":[199],"proposed":[202],"effectively":[205],"alleviates":[206],"caused":[208],"co-occurrence,":[214],"enhances":[215],"captions,":[222],"provides":[224],"novel":[226],"solution":[227],"task":[231],"complex":[233],"scenarios.":[235]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}