{"id":"https://openalex.org/W4406611421","doi":"https://doi.org/10.1109/smc54092.2024.10831907","title":"CMACC: Cross-Modal Adversarial Contrastive Learning in Visual Question Answering Based on Co-Attention Network","display_name":"CMACC: Cross-Modal Adversarial Contrastive Learning in Visual Question Answering Based on Co-Attention Network","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406611421","doi":"https://doi.org/10.1109/smc54092.2024.10831907"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10831907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5113347937","display_name":"Zepu Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zepu Yi","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048196007","display_name":"Songfeng Lu","orcid":"https://orcid.org/0000-0003-4489-2488"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songfeng Lu","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101790669","display_name":"Xueming Tang","orcid":"https://orcid.org/0000-0003-0806-5100"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueming Tang","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460435","display_name":"Junjun Wu","orcid":"https://orcid.org/0000-0002-9140-2990"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjun Wu","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100523132","display_name":"Zhu Jian-xin","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Zhu","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113347937"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58831808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1957","last_page":"1962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9947999715805054,"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":0.9947999715805054,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9829999804496765,"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":0.9776999950408936,"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":0.7381678223609924},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7328885793685913},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7128407955169678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6511855125427246},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.593690037727356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5653308629989624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7381678223609924},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7328885793685913},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7128407955169678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6511855125427246},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.593690037727356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5653308629989624},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc54092.2024.10831907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":30,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2766774033","https://openalex.org/W2798991696","https://openalex.org/W2807941860","https://openalex.org/W2896902935","https://openalex.org/W2963176022","https://openalex.org/W2963383024","https://openalex.org/W2963717374","https://openalex.org/W2963954913","https://openalex.org/W2966683369","https://openalex.org/W3107273227","https://openalex.org/W3152635550","https://openalex.org/W3157731560","https://openalex.org/W3176713826","https://openalex.org/W3209226499","https://openalex.org/W3212336350","https://openalex.org/W4214648142","https://openalex.org/W4224324956","https://openalex.org/W4226424445","https://openalex.org/W4312982094","https://openalex.org/W4385491567","https://openalex.org/W4387676019","https://openalex.org/W4388515789","https://openalex.org/W4399541501","https://openalex.org/W6686207219","https://openalex.org/W6752083267","https://openalex.org/W6766904570","https://openalex.org/W6776700526"],"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/W3204019825"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"as":[4],"a":[5,75,96],"cutting-edge":[6],"domain":[7],"blending":[8],"computer":[9],"vision":[10],"and":[11,27,33,41,86,118,132,134,169,186,188,199],"natural":[12],"language":[13],"processing":[14],"has":[15,194],"garnered":[16],"significant":[17,76,195],"research":[18],"momentum.":[19],"Nev-ertheless,":[20],"latest":[21],"VQA":[22,180,184],"frameworks":[23],"which":[24],"leverage":[25],"CNN":[26],"RNN":[28],"technologies":[29],"to":[30,59,78,145,160,166,203],"extract":[31],"features":[32,48,140],"delve":[34],"into":[35],"the":[36,56,62,66,69,126,142,147,150,163,189],"multimodal":[37,83,138],"interplay":[38],"between":[39,130],"text":[40,119,131],"images,":[42,133],"encounter":[43],"difficulties":[44],"in":[45,141,197],"integrating":[46],"local":[47],"with":[49,114],"global":[50],"dependencies.":[51],"This":[52],"integration":[53],"challenge":[54],"hinders":[55],"models'":[57,79],"ability":[58],"precisely":[60],"grasp":[61],"pivotal":[63],"aspects":[64],"of":[65,71,82,149],"answer.":[67],"Furthermore,":[68],"dearth":[70],"training":[72],"data":[73,155],"poses":[74],"impediment":[77],"effective":[80],"learning":[81,124,136],"information":[84,120],"exchange":[85],"problem":[87,170],"semantics.":[88],"To":[89],"address":[90],"these":[91],"issues,":[92],"our":[93],"model":[94],"introduces":[95],"new":[97],"method":[98],"called":[99],"CMACC":[100,193],"(Cross-Modal":[101],"Adversarial":[102],"Contrastive":[103],"Learning":[104],"Based":[105],"on":[106,176],"Co-Attention).":[107],"Through":[108],"cross-modal":[109],"adversarial":[110],"contrastive":[111,135],"learning,":[112],"combined":[113],"common":[115],"attention,":[116],"image":[117],"are":[121,158],"integrated.":[122],"Adversar-ial":[123],"aligns":[125,137],"latent":[127],"feature":[128],"distribution":[129],"sample":[139],"same":[143],"context":[144],"enhance":[146,162],"adaptability":[148,165],"model.":[151],"In":[152],"addition,":[153],"advanced":[154],"augmentation":[156],"techniques":[157],"integrated":[159],"further":[161],"model's":[164],"different":[167],"scenarios":[168],"types.":[171],"We":[172],"conducted":[173],"experimental":[174],"evaluations":[175],"three":[177],"widely":[178],"used":[179],"datasets":[181],"(VQA":[182],"v1.0,":[183],"v2.0,":[185],"COCO-QA)":[187],"results":[190],"showed":[191],"that":[192],"improvements":[196],"accuracy":[198],"generalization":[200],"performance":[201],"compared":[202],"traditional":[204],"methods.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}