{"id":"https://openalex.org/W4402353174","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650444","title":"A Multimodal Contrastive Network with Unbiased Distillation for Knowledge-based VQA","display_name":"A Multimodal Contrastive Network with Unbiased Distillation for Knowledge-based VQA","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353174","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650444"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650444","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5002479642","display_name":"Zihan Hu","orcid":"https://orcid.org/0009-0003-1618-9768"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Hu","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077430951","display_name":"Ruoyao Ding","orcid":"https://orcid.org/0000-0001-9282-7846"},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoyao Ding","raw_affiliation_strings":["Guangdong University of Foreign Studies,School of Cyber Security,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Foreign Studies,School of Cyber Security,China","institution_ids":["https://openalex.org/I186272606"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013151488","display_name":"Haoran Xie","orcid":"https://orcid.org/0000-0003-0965-3617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoran Xie","raw_affiliation_strings":["Lingnan University,Department of Computing and Decision Sciences,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lingnan University,Department of Computing and Decision Sciences,Hong Kong,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025919799","display_name":"Zhenguo Yang","orcid":"https://orcid.org/0000-0001-8128-898X"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenguo Yang","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9955999851226807,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9840999841690063,"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":0.7028536200523376},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6287262439727783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3617907464504242},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09792658686637878},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.06418690085411072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7028536200523376},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6287262439727783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3617907464504242},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09792658686637878},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06418690085411072}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650444","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2745461083","https://openalex.org/W2963430933","https://openalex.org/W2966683369","https://openalex.org/W2968124245","https://openalex.org/W2970641574","https://openalex.org/W2991044292","https://openalex.org/W3033188311","https://openalex.org/W3090492056","https://openalex.org/W3099655892","https://openalex.org/W3099884329","https://openalex.org/W3139224848","https://openalex.org/W3139732141","https://openalex.org/W3155855665","https://openalex.org/W3156636935","https://openalex.org/W3161051151","https://openalex.org/W3186953717","https://openalex.org/W3198953397","https://openalex.org/W3199446656","https://openalex.org/W3201302554","https://openalex.org/W4221155360","https://openalex.org/W4283777642","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4298090460","https://openalex.org/W4312971273","https://openalex.org/W4318718936","https://openalex.org/W4319301039","https://openalex.org/W4365800629","https://openalex.org/W4366566341","https://openalex.org/W4385574019","https://openalex.org/W4385574177","https://openalex.org/W4389520282","https://openalex.org/W6752083267","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6779089016","https://openalex.org/W6789374720","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6803645040","https://openalex.org/W6811013733","https://openalex.org/W6839091850","https://openalex.org/W6843405348","https://openalex.org/W6849177959","https://openalex.org/W6852410717"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,55,70,117],"multimodal":[6],"contrastive":[7,19,24,35,77],"network":[8],"with":[9,146],"unbiased":[10,23,50,109,119],"distillation":[11,25,104],"(MCUD)":[12],"for":[13,106],"knowledge-based":[14],"VQA,":[15],"which":[16],"consists":[17],"of":[18,93,157],"sample":[20],"construction":[21],"(CSC),":[22],"(UCD),":[26],"and":[27,42,66,90,108,140,150,155],"hierarchical":[28],"reasoning":[29],"(HR)":[30],"modules.":[31],"Specifically,":[32],"CSC":[33],"constructs":[34],"samples":[36],"by":[37],"transforming":[38],"the":[39,49,63,75,83,87,91,97,112,122,130,134,138,142,153],"knowledge":[40,64,88,135],"corpus":[41,65,89],"adopting":[43],"entropy-adjusted":[44],"answer":[45],"frequencies":[46],"to":[47,60,81,115],"identify":[48],"samples.":[51],"Additionally,":[52],"UCD":[53,101],"employs":[54],"dual-branch":[56],"feature":[57],"extractor":[58],"architecture":[59],"separately":[61],"encode":[62],"image-question":[67,94],"pairs":[68],"into":[69],"shared":[71],"embedding":[72],"space.":[73],"Subsequently,":[74],"knowledge-driven":[76],"learning":[78],"is":[79],"supposed":[80],"bridge":[82],"modality":[84],"gap":[85],"between":[86],"cross-modality":[92],"pairs.":[95],"Furthermore,":[96],"teacher":[98],"model":[99,114],"in":[100,133],"utilizes":[102],"different":[103],"strategies":[105],"biased":[107],"samples,":[110],"guiding":[111],"student":[113],"establish":[116],"generalized":[118],"representation.":[120],"Finally,":[121],"HR":[123],"module":[124],"conducts":[125],"chain-of-thought":[126],"outputs,":[127],"sequentially":[128],"locates":[129],"contextual":[131],"sentences":[132],"corpus,":[136],"generates":[137],"rationale,":[139],"infers":[141],"answer.":[143],"Extensive":[144],"experiments":[145],"two":[147],"datasets,":[148],"E-VQA":[149],"ScienceQA,":[151],"demonstrate":[152],"effectiveness":[154],"outperformance":[156],"our":[158],"method.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}