{"id":"https://openalex.org/W4415708747","doi":"https://doi.org/10.1109/icme59968.2025.11208923","title":"Towards Robust Visual Question Answering via Causal Intervention and Contrastive Learning","display_name":"Towards Robust Visual Question Answering via Causal Intervention and Contrastive Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708747","doi":"https://doi.org/10.1109/icme59968.2025.11208923"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208923","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 Multimedia and Expo (ICME)","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/A5100318413","display_name":"Wei Li","orcid":"https://orcid.org/0000-0003-2548-3486"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Li","raw_affiliation_strings":["Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100701695","display_name":"Zhixin Li","orcid":"https://orcid.org/0000-0002-5313-6134"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Li","raw_affiliation_strings":["Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100318413"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33941934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9883999824523926,"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":0.9883999824523926,"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/T10028","display_name":"Topic Modeling","score":0.002300000051036477,"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":0.0019000000320374966,"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/exploit","display_name":"Exploit","score":0.7369999885559082},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.7127000093460083},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6299999952316284},{"id":"https://openalex.org/keywords/intervention","display_name":"Intervention (counseling)","score":0.6007000207901001},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5968000292778015},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.4223000109195709},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.40049999952316284}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7369999885559082},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7127000093460083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6417999863624573},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6299999952316284},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.6007000207901001},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5478000044822693},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.448199987411499},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43799999356269836},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41530001163482666},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3158000111579895},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.260699987411499}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208923","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 Multimedia and Expo (ICME)","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":22,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2962858109","https://openalex.org/W2963644680","https://openalex.org/W2970019270","https://openalex.org/W2970231061","https://openalex.org/W2997072136","https://openalex.org/W3035517717","https://openalex.org/W3035524453","https://openalex.org/W3106544837","https://openalex.org/W3171353004","https://openalex.org/W3175294706","https://openalex.org/W3177934633","https://openalex.org/W3204222276","https://openalex.org/W4213057961","https://openalex.org/W4385574019","https://openalex.org/W4386065611","https://openalex.org/W4386066382","https://openalex.org/W4400844648","https://openalex.org/W4402979468","https://openalex.org/W4403997808"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"question":[1],"answering":[2],"systems":[3],"are":[4,22],"designed":[5],"to":[6,12,16,24,41,55,92],"integrate":[7],"visual":[8],"and":[9,53,60,117,119],"linguistic":[10,72],"information":[11],"provide":[13],"accurate":[14],"answers":[15],"questions.":[17],"However,":[18],"current":[19],"VQA":[20,128],"models":[21],"susceptible":[23],"shortcut":[25,38,68,80,95],"learning,":[26],"where":[27],"they":[28,74],"exploit":[29],"spurious":[30],"correlations":[31],"rather":[32],"than":[33],"genuine":[34],"multimodal":[35],"interactions.":[36],"This":[37,82],"bias":[39],"leads":[40],"an":[42],"over-reliance":[43],"on":[44,89,109],"a":[45,85,121],"single":[46],"modality,":[47,73],"resulting":[48],"in":[49,97,124],"poor":[50],"generalization":[51],"performance":[52,108],"vulnerability":[54],"distributional":[56],"shifts":[57],"between":[58],"training":[59],"testing":[61],"sets.":[62],"While":[63],"existing":[64],"solutions":[65],"primarily":[66],"address":[67],"learning":[69],"within":[70],"the":[71,110,125],"often":[75],"overlook":[76],"other":[77],"types":[78],"of":[79,127],"biases.":[81],"paper":[83],"introduces":[84],"novel":[86],"approach":[87],"based":[88],"causal":[90],"intervention":[91],"mitigate":[93],"various":[94],"biases":[96],"VQA.":[98],"By":[99],"explicitly":[100],"addressing":[101],"these":[102],"biases,":[103],"our":[104],"method":[105],"achieves":[106],"state-of-the-art":[107],"VQA-CP":[111],"v2":[112],"dataset,":[113],"demonstrating":[114],"its":[115],"effectiveness":[116],"superiority,":[118],"offering":[120],"significant":[122],"advancement":[123],"improvement":[126],"systems.":[129]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}