{"id":"https://openalex.org/W4381744346","doi":"https://doi.org/10.1109/cscwd57460.2023.10152629","title":"Multi-granularity Text Representation and Transformer-Based Fusion Method for Visual Question Answering","display_name":"Multi-granularity Text Representation and Transformer-Based Fusion Method for Visual Question Answering","publication_year":2023,"publication_date":"2023-05-24","ids":{"openalex":"https://openalex.org/W4381744346","doi":"https://doi.org/10.1109/cscwd57460.2023.10152629"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd57460.2023.10152629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd57460.2023.10152629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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/A5026151620","display_name":"Xingang Wang","orcid":"https://orcid.org/0000-0002-6851-0109"},"institutions":[{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingang Wang","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]},{"raw_affiliation_string":"School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092244467","display_name":"Xiaoyu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Liu","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]},{"raw_affiliation_string":"School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042058386","display_name":"Xiaomin Li","orcid":"https://orcid.org/0000-0001-7587-0543"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomin Li","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]},{"raw_affiliation_string":"School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082011464","display_name":"Jinan Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinan Cui","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]},{"raw_affiliation_string":"School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026151620"],"corresponding_institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"],"apc_list":null,"apc_paid":null,"fwci":0.1235,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.386047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"965","last_page":"971"},"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":0.9950000047683716,"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":0.9932000041007996,"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":0.7782757878303528},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6455230712890625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5710124373435974},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5280355215072632},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4554431736469269},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45395368337631226},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4396193027496338},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4306149482727051},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4171101152896881},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41448497772216797},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4043004810810089},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37017425894737244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782757878303528},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6455230712890625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5710124373435974},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5280355215072632},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4554431736469269},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45395368337631226},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4396193027496338},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4306149482727051},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4171101152896881},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41448497772216797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4043004810810089},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37017425894737244},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd57460.2023.10152629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd57460.2023.10152629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2142192571","https://openalex.org/W2560920409","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2916723116","https://openalex.org/W2952003359","https://openalex.org/W2963150162","https://openalex.org/W2963383024","https://openalex.org/W2963477107","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964072591","https://openalex.org/W2964303913","https://openalex.org/W2966683369","https://openalex.org/W2981694290","https://openalex.org/W2997421053","https://openalex.org/W2997591391","https://openalex.org/W3002557610","https://openalex.org/W3107273227","https://openalex.org/W3135705837","https://openalex.org/W4206324769","https://openalex.org/W4312289196","https://openalex.org/W4386071687"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W4381058564","https://openalex.org/W3003945460","https://openalex.org/W2964413124","https://openalex.org/W4288267738"],"abstract_inverted_index":{"The":[0],"Visual":[1,110],"Questions":[2],"and":[3,68,98,146,175],"Answers":[4],"(VQA)":[5],"task":[6],"is":[7,39],"to":[8,12,50,77,139,149,179],"obtain":[9],"the":[10,17,21,28,31,41,48,53,60,63,80,93,107,115,133,151,169,173,182,195,202,205,208],"answer":[11],"a":[13,73,121,160],"question":[14,25],"by":[15],"combining":[16],"image":[18,22,69],"information":[19,96,142,192,197],"with":[20,92],"related":[23],"textual":[24],"information.":[26,58,129],"On":[27,59],"one":[29],"hand,":[30,62],"representation":[32,124],"of":[33,43,56,66,83,95,109,135,153,184,204],"problem":[34,94],"features":[35,70,178],"in":[36,47],"traditional":[37,64],"models":[38],"mostly":[40,71],"extraction":[42],"coarse-grained":[44],"information,":[45],"resulting":[46],"inability":[49],"effectively":[51],"utilize":[52],"deep":[54],"semantics":[55],"text":[57,67,122,141,154,176],"other":[61],"fusion":[65,75,88,163],"adopts":[72],"series":[74],"method":[76,89,134,206],"simply":[78],"splice":[79],"feature":[81,123],"vectors":[82],"different":[84,101,190],"modalities.":[85],"This":[86,156,199],"simple":[87],"cannot":[90],"deal":[91],"redundancy":[97],"conflict":[99],"between":[100,172],"modal":[102,177,186,191],"features,":[103],"which":[104],"ultimately":[105],"affects":[106],"accuracy":[108],"Question":[111],"Answering.":[112],"To":[113],"solve":[114],"above":[116],"problems,":[117],"this":[118],"paper":[119,157,200],"proposes":[120,159],"module":[125,164],"(MGT)":[126],"for":[127],"multi-granularity":[128],"It":[130,166],"mainly":[131,167],"uses":[132,168],"hierarchical":[136],"expansion":[137],"convolution":[138],"preserve":[140],"from":[143],"multiple":[144,147],"levels":[145],"angles":[148],"improve":[150],"utilization":[152],"features.":[155],"also":[158],"Transformer-based":[161],"multimodal":[162],"(BTMF).":[165],"internal":[170],"correlation":[171],"picture":[174],"dynamically":[180],"adjust":[181],"weight":[183],"each":[185],"feature.":[187],"Simultaneously":[188],"learn":[189],"while":[193],"keeping":[194],"contextual":[196],"unchanged.":[198],"verifies":[201],"effectiveness":[203],"on":[207],"VQA2.0":[209],"dataset.":[210]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}