{"id":"https://openalex.org/W4293523262","doi":"https://doi.org/10.1109/icme52920.2022.9859865","title":"Modality-Specific Multimodal Global Enhanced Network for Text-Based Visual Question Answering","display_name":"Modality-Specific Multimodal Global Enhanced Network for Text-Based Visual Question Answering","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293523262","doi":"https://doi.org/10.1109/icme52920.2022.9859865"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859865","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5061764261","display_name":"Zhi Yang","orcid":"https://orcid.org/0000-0003-1046-8654"},"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":"Zhi Yang","raw_affiliation_strings":["School of Computer Science & Engineering, South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075858925","display_name":"Jun Xuan","orcid":"https://orcid.org/0000-0002-7975-7852"},"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":"Jun Xuan","raw_affiliation_strings":["School of Computer Science & Engineering, South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345229","display_name":"Qing Liu","orcid":"https://orcid.org/0000-0002-9719-8556"},"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":"Qing Liu","raw_affiliation_strings":["School of Computer Science & Engineering, South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014555076","display_name":"Aihua Mao","orcid":"https://orcid.org/0000-0001-6861-9414"},"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":"Aihua Mao","raw_affiliation_strings":["School of Computer Science & Engineering, South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6723411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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":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":0.9980000257492065,"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":0.993399977684021,"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":0.7975087761878967},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.672774612903595},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6441636681556702},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6311290264129639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5860012173652649},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5455881357192993},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5396260619163513},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5243791937828064},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5141289830207825},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.471698522567749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4551912844181061},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35421401262283325},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34267574548721313},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16759896278381348}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975087761878967},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.672774612903595},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6441636681556702},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6311290264129639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5860012173652649},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5455881357192993},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5396260619163513},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5243791937828064},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5141289830207825},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.471698522567749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4551912844181061},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35421401262283325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34267574548721313},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16759896278381348},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859865","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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":33,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2053317383","https://openalex.org/W2418349398","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2928555987","https://openalex.org/W2963626623","https://openalex.org/W2965512000","https://openalex.org/W2966683369","https://openalex.org/W2979382951","https://openalex.org/W2988326850","https://openalex.org/W3034336960","https://openalex.org/W3035497460","https://openalex.org/W3093385053","https://openalex.org/W3108319047","https://openalex.org/W3110661548","https://openalex.org/W3115287481","https://openalex.org/W3175344799","https://openalex.org/W3181159501","https://openalex.org/W3205050305","https://openalex.org/W3205209899","https://openalex.org/W3215381707","https://openalex.org/W4288083516","https://openalex.org/W4385245566","https://openalex.org/W6717487601","https://openalex.org/W6725207838","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6778668228","https://openalex.org/W6781214006","https://openalex.org/W6787228247","https://openalex.org/W6796921589"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Text-based":[0],"visual":[1],"question":[2],"answering":[3],"(T-VQA)":[4],"aims":[5],"to":[6,25,92,118],"answer":[7],"questions":[8],"about":[9],"images":[10],"by":[11],"comprehending":[12],"both":[13],"detected":[14,31],"objects":[15,70],"and":[16,29,33,73,134],"OCR(optical":[17],"character":[18],"recognition)":[19],"tokens.":[20],"Most":[21],"existing":[22],"methods":[23],"fail":[24],"eliminate":[26],"the":[27,35,53,62,78,88,94,97,113,122,132,137,141],"noisy":[28],"redundant":[30],"objects,":[32],"ignore":[34],"modality-specific":[36],"information.":[37],"To":[38],"address":[39],"these":[40],"concerns,":[41],"we":[42,76],"propose":[43],"multimodal":[44],"global":[45,55,80,106],"enhanced":[46,56,81],"network":[47],"(MGEN)":[48],"for":[49],"T-VQA.":[50],"In":[51],"MGEN":[52,139],"multi-modal":[54,79],"OCR":[57,66],"graph":[58],"focus":[59],"on":[60],"modeling":[61],"spatial":[63],"relationships":[64],"between":[65],"tokens":[67],"rather":[68],"than":[69],"with":[71],"noise":[72,123],"redundancy.":[74],"Then,":[75],"introduce":[77],"transformer":[82],"module,":[83],"which":[84],"is":[85],"formed":[86],"using":[87],"proposed":[89,138],"attention":[90,115],"mechanism,":[91],"reflect":[93],"specificity":[95],"in":[96],"various":[98],"modalities.":[99],"The":[100],"preceding":[101],"two":[102],"modules":[103],"can":[104,124],"leverage":[105],"features,":[107],"implying":[108],"that":[109],"not":[110],"only":[111],"will":[112],"model's":[114],"be":[116,126],"directed":[117],"critical":[119],"parts,":[120],"but":[121],"also":[125],"further":[127],"reduced.":[128],"Extensive":[129],"experiments":[130],"demonstrate":[131],"effectiveness":[133],"superiority":[135],"of":[136],"against":[140],"state-of-the-art":[142],"methods.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}