{"id":"https://openalex.org/W4388186932","doi":"https://doi.org/10.1145/3581783.3612536","title":"Deconfounded Visual Question Generation with Causal Inference","display_name":"Deconfounded Visual Question Generation with Causal Inference","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388186932","doi":"https://doi.org/10.1145/3581783.3612536"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612536","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5100459749","display_name":"Jiali Chen","orcid":"https://orcid.org/0000-0001-8064-1577"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiali Chen","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103183906","display_name":"Zhenjun Guo","orcid":"https://orcid.org/0009-0004-0037-3656"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjun Guo","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049131355","display_name":"Jiayuan Xie","orcid":"https://orcid.org/0000-0002-6833-7879"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayuan Xie","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089123257","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-1767-789X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cai","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100459749"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.9629,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78087405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5132","last_page":"5142"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6789895296096802},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6338554620742798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5239084959030151},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.5092081427574158},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.380415678024292},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.18526622653007507},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1385561227798462}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6789895296096802},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6338554620742798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239084959030151},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.5092081427574158},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.380415678024292},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.18526622653007507},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1385561227798462}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612536","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8189774080","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8718620462","display_name":null,"funder_award_id":"2020B0101100002","funder_id":"https://openalex.org/F4320335795","funder_display_name":"Science and Technology Planning Project of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1981119423","https://openalex.org/W2010581936","https://openalex.org/W2122787031","https://openalex.org/W2194775991","https://openalex.org/W2560730294","https://openalex.org/W2561296180","https://openalex.org/W2735156122","https://openalex.org/W2808021740","https://openalex.org/W2898071615","https://openalex.org/W2947312908","https://openalex.org/W2963087285","https://openalex.org/W2963351776","https://openalex.org/W2963976294","https://openalex.org/W3019023591","https://openalex.org/W3035103424","https://openalex.org/W3035651653","https://openalex.org/W3096826274","https://openalex.org/W3206904785","https://openalex.org/W3207071456","https://openalex.org/W4252076394","https://openalex.org/W4285199586","https://openalex.org/W4285280022","https://openalex.org/W4304080600","https://openalex.org/W4304091998","https://openalex.org/W4312516176","https://openalex.org/W4312789226"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Visual":[0,126],"Question":[1,127],"Generation":[2,128],"(VQG)":[3],"task":[4],"aims":[5,153],"to":[6,67,110,131,154,169,189],"generate":[7,84,190],"meaningful":[8],"and":[9,35,51,78,105,198],"logically":[10],"reasonable":[11],"questions":[12,86],"about":[13],"the":[14,25,30,69,75,79,89,107,118,133,177,195],"given":[15],"image":[16,31],"targeting":[17],"an":[18,55,142],"answer.":[19],"Existing":[20],"methods":[21],"mainly":[22],"focus":[23],"on":[24,103,117,194],"visual":[26,73,90,144,157],"concepts":[27],"present":[28],"in":[29,40,58,138,150],"for":[32],"question":[33,59,139],"generation":[34],"have":[36],"shown":[37],"remarkable":[38],"performance":[39],"VQG.":[41],"However,":[42],"these":[43],"models":[44,66],"frequently":[45],"learn":[46],"highly":[47],"co-occurring":[48],"object":[49],"relationships":[50],"attributes,":[52],"which":[53,152],"is":[54,148,167],"inherent":[56],"bias":[57,64],"generation.":[60,140],"This":[61],"previously":[62],"overlooked":[63],"causes":[65],"over-exploit":[68],"spurious":[70,112,136],"correlations":[71,113,137],"among":[72,114],"features,":[74],"target":[76],"answer,":[77],"question.":[80],"Therefore,":[81],"they":[82],"may":[83],"inappropriate":[85],"that":[87,202],"contradict":[88],"content":[91],"or":[92],"facts.":[93],"In":[94],"this":[95],"paper,":[96],"we":[97,120],"first":[98],"introduce":[99],"a":[100,122,162,185],"causal":[101,108],"perspective":[102],"VQG":[104],"adopt":[106],"graph":[109],"analyze":[111],"variables.":[115],"Building":[116],"analysis,":[119],"propose":[121],"Knowledge":[123],"Enhanced":[124],"Causal":[125],"(KECVQG)":[129],"model":[130],"mitigate":[132],"impact":[134],"of":[135],"Specifically,":[141],"interventional":[143],"feature":[145],"extractor":[146,165],"(IVE)":[147],"introduced":[149],"KECVQG,":[151],"obtain":[155],"unbiased":[156,171],"features":[158,172,179],"by":[159],"disentangling.":[160],"Then":[161],"knowledge-guided":[163],"representation":[164],"(KRE)":[166],"employed":[168],"align":[170],"with":[173],"external":[174],"knowledge.":[175],"Finally,":[176],"output":[178],"from":[180],"KRE":[181],"are":[182],"sent":[183],"into":[184],"standard":[186],"transformer":[187],"decoder":[188],"questions.":[191],"Extensive":[192],"experiments":[193],"VQA":[196],"v2.0":[197],"OKVQA":[199],"datasets":[200],"show":[201],"KECVQG":[203],"significantly":[204],"outperforms":[205],"existing":[206],"models.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}