{"id":"https://openalex.org/W4392904190","doi":"https://doi.org/10.1109/icassp48485.2024.10447342","title":"CausalME: Balancing bi-modalities in Visual Question Answering","display_name":"CausalME: Balancing bi-modalities in Visual Question Answering","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904190","doi":"https://doi.org/10.1109/icassp48485.2024.10447342"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5068274462","display_name":"Chenji Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenji Lu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068137955","display_name":"Ge Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Bai","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100725235","display_name":"Shilong Li","orcid":"https://orcid.org/0009-0005-7538-1754"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilong Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414402","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0003-1331-997X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077383364","display_name":"Xiyan Liu","orcid":"https://orcid.org/0000-0002-0102-9636"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiyan Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081360719","display_name":"Zerong Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zerong Zeng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023135578","display_name":"Ruifang Liu","orcid":"https://orcid.org/0000-0003-1801-6759"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifang Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.6427,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66514504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"10556","last_page":"10560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9966999888420105,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9958000183105469,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.81877601146698},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7488632798194885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7318997979164124},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.711189866065979},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5837153196334839},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5593878030776978},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5299248099327087},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.5186880826950073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4826365113258362},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42005494236946106},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41328081488609314},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37730157375335693},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12155359983444214},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0998125672340393}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.81877601146698},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7488632798194885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318997979164124},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.711189866065979},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5837153196334839},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5593878030776978},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5299248099327087},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.5186880826950073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4826365113258362},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42005494236946106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41328081488609314},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37730157375335693},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12155359983444214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0998125672340393},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2745461083","https://openalex.org/W2963644680","https://openalex.org/W2963954913","https://openalex.org/W2970019270","https://openalex.org/W2983256121","https://openalex.org/W3099884329","https://openalex.org/W3104788521","https://openalex.org/W3110575265","https://openalex.org/W3154781046","https://openalex.org/W3177934633","https://openalex.org/W3192587235","https://openalex.org/W3202778561","https://openalex.org/W4210484952","https://openalex.org/W4212774754","https://openalex.org/W4213057961","https://openalex.org/W4312457137","https://openalex.org/W6620707391","https://openalex.org/W6754733129","https://openalex.org/W6763000187","https://openalex.org/W6764756247","https://openalex.org/W6999220822"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Mitigating":[0],"linguistic":[1,64],"bias":[2,65],"and":[3,70,111,119,126,135],"attaining":[4],"modal":[5,45],"equilibrium":[6,46],"in":[7],"Visual":[8],"Question":[9],"Answering":[10],"(VQA)":[11],"tasks":[12],"constitute":[13],"a":[14,26,42,53,58,76],"pivotal":[15],"concern.":[16],"Previous":[17],"work":[18],"has":[19],"mainly":[20],"focused":[21],"on":[22,139],"data":[23],"augmentation":[24],"or":[25],"uni-modal":[27],"approach,":[28],"which":[29],"is":[30],"insufficient":[31],"to":[32,61,86,116],"fully":[33],"utilize":[34],"bi-modal":[35],"information.":[36,121],"In":[37],"this":[38],"work,":[39],"we":[40],"propose":[41],"new":[43],"causal":[44,54,73,89,107],"framework":[47],"CausalME,":[48],"addressing":[49],"the":[50,63,67,88,96,100,106,114,127,140],"issue":[51],"from":[52],"perspective.":[55],"CausalME":[56,82,104,131],"utilizes":[57],"question-only":[59],"branch":[60],"capture":[62],"of":[66,91,99,109],"textual":[68],"modality":[69],"mitigate":[71],"its":[72],"effect":[74,90],"with":[75],"newly":[77],"designed":[78],"adaptive":[79],"paradigm.":[80],"Additionally,":[81],"employs":[83],"counterfactual":[84],"generation":[85],"enhance":[87],"visual":[92],"modality.":[93],"By":[94],"optimizing":[95],"objective":[97],"function":[98],"entire":[101],"VQA":[102],"model,":[103],"balances":[105],"effects":[108],"bi-modalities":[110],"explicitly":[112],"guides":[113],"model":[115],"align":[117],"text":[118],"image":[120],"We":[122],"conducted":[123],"extensive":[124],"experiments":[125],"results":[128],"show":[129],"that":[130],"brings":[132],"significant":[133],"improvements":[134],"achieves":[136],"competitive":[137],"performance":[138],"bias-sensitive":[141],"VQA-CP":[142],"v2":[143],"dataset.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}