{"id":"https://openalex.org/W4402793079","doi":"https://doi.org/10.1145/3688848","title":"Adversarial Sample Synthesis for Visual Question Answering","display_name":"Adversarial Sample Synthesis for Visual Question Answering","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402793079","doi":"https://doi.org/10.1145/3688848"},"language":"en","primary_location":{"id":"doi:10.1145/3688848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3688848","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5101895689","display_name":"Chuanhao Li","orcid":"https://orcid.org/0000-0002-5769-3739"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanhao Li","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5769-3739","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114233023","display_name":"Chenchen Jing","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenchen Jing","raw_affiliation_strings":["Zhejiang University, Hangzhou, China and Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-5109-2386","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China and Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhen Li","orcid":"https://orcid.org/0009-0008-6422-6056"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Li","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6422-6056","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071656520","display_name":"Yuwei Wu","orcid":"https://orcid.org/0000-0001-6300-6336"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Wu","raw_affiliation_strings":["Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, Shenzhen, China and Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6300-6336","affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, Shenzhen, China and Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683","https://openalex.org/I4388482657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100731042","display_name":"Yunde Jia","orcid":"https://orcid.org/0000-0003-1900-8945"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunde Jia","raw_affiliation_strings":["Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, Shenzhen, China and Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1900-8945","affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, Shenzhen, China and Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683","https://openalex.org/I4388482657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1645,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43687275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"20","issue":"12","first_page":"1","last_page":"24"},"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":0.9994000196456909,"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":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.8540873527526855},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6460810899734497},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5914034247398376},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4683273136615753},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4049155116081238},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.375815212726593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35707587003707886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540873527526855},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6460810899734497},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5914034247398376},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4683273136615753},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4049155116081238},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.375815212726593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35707587003707886},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3688848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3688848","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3333297613","display_name":null,"funder_award_id":"2023M743003","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2250539671","https://openalex.org/W2553418567","https://openalex.org/W2605466790","https://openalex.org/W2613718673","https://openalex.org/W2615497679","https://openalex.org/W2805553723","https://openalex.org/W2890952061","https://openalex.org/W2946299408","https://openalex.org/W2950635152","https://openalex.org/W2964121744","https://openalex.org/W3026376263","https://openalex.org/W3026441479","https://openalex.org/W3099884329","https://openalex.org/W3104788521","https://openalex.org/W3105009590","https://openalex.org/W3113067643","https://openalex.org/W3143835353","https://openalex.org/W3171312896","https://openalex.org/W3185066916","https://openalex.org/W3195963939","https://openalex.org/W3212445569","https://openalex.org/W3213504576","https://openalex.org/W4210836196","https://openalex.org/W4224217283","https://openalex.org/W4281550993","https://openalex.org/W4289421997","https://openalex.org/W4294351586","https://openalex.org/W4297749157","https://openalex.org/W4298276494","https://openalex.org/W4362598331","https://openalex.org/W4375957588","https://openalex.org/W4379136764","https://openalex.org/W4385245566","https://openalex.org/W4386223789","https://openalex.org/W4386875389","https://openalex.org/W4392206049","https://openalex.org/W6739901393","https://openalex.org/W6796729313"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"Language":[0],"prior":[1],"is":[2,29,108],"a":[3,30,45,131,146,218],"major":[4],"block":[5],"to":[6,25,33,94,109,113,122,134,149,182],"improving":[7],"the":[8,53,56,97,120,141,151,154,159,163,167,173,183,188,231],"generalization":[9],"of":[10,48,153,166,221,234],"visual":[11],"question":[12],"answering":[13],"(VQA)":[14],"models.":[15],"Recent":[16],"work":[17],"has":[18],"revealed":[19],"that":[20,55,117,172,217],"synthesizing":[21],"extra":[22,42],"training":[23,27,49,92,152,164,178],"samples":[24,43,86,116,175],"balance":[26],"sets":[28],"promising":[31],"way":[32],"alleviate":[34],"language":[35,57,100],"priors.":[36,101],"However,":[37],"most":[38],"existing":[39],"methods":[40],"synthesize":[41,114],"in":[44,68,230],"manner":[46],"independent":[47],"processes,":[50],"which":[51,82,170],"neglect":[52],"fact":[54],"priors":[58],"memorized":[59,99],"by":[60,87,139],"VQA":[61,142,168,184,193,212],"models":[62,194],"are":[63,180],"changing":[64,98],"during":[65],"training,":[66],"resulting":[67],"insufficient":[69],"synthesized":[70,174],"samples.":[71],"In":[72],"this":[73,127],"article,":[74],"we":[75,129],"propose":[76],"an":[77],"adversarial":[78,85,88,111,115,137],"sample":[79,160],"synthesis":[80,161],"method,":[81,223],"synthesizes":[83],"different":[84,91,177],"masking":[89,112,138],"at":[90,176],"epochs":[93,179],"cope":[95],"with":[96,162],"The":[102],"basic":[103],"idea":[104],"behind":[105],"our":[106,222],"method":[107,190],"use":[110],"will":[118],"cause":[119],"model":[121,143],"make":[123],"wrong":[124],"answers.":[125],"To":[126],"end,":[128],"design":[130],"generative":[132,155],"module":[133],"carry":[135],"out":[136],"attacking":[140],"and":[144,198,200,211],"introduce":[145],"bias-oriented":[147],"objective":[148],"supervise":[150],"module.":[156],"We":[157,186],"couple":[158],"process":[165],"model,":[169],"ensures":[171],"beneficial":[181],"model.":[185],"incorporated":[187],"proposed":[189],"into":[191],"three":[192,204],"including":[195,206],"UpDn,":[196],"LMH,":[197],"LXMERT":[199,229],"conducted":[201],"experiments":[202],"on":[203,228],"datasets":[205],"VQA-CP":[207,209,235],"v1,":[208],"v2,":[210],"v2.":[213,236],"Experimental":[214],"results":[215],"demonstrate":[216],"large":[219],"improvement":[220],"such":[224],"as":[225],"16.22%":[226],"gains":[227],"overall":[232],"accuracy":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}