{"id":"https://openalex.org/W7141982693","doi":"https://doi.org/10.1145/3805048","title":"Concise Object-word Visuals as Effective Cues for Visual Question Answering","display_name":"Concise Object-word Visuals as Effective Cues for Visual Question Answering","publication_year":2026,"publication_date":"2026-03-28","ids":{"openalex":"https://openalex.org/W7141982693","doi":"https://doi.org/10.1145/3805048"},"language":"en","primary_location":{"id":"doi:10.1145/3805048","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3805048","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/A5130856682","display_name":"Quanxing Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Quanxing Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Macau University of Science and Technology, Macau SAR, China"],"raw_orcid":"https://orcid.org/0009-0008-4354-8371","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau SAR, China","institution_ids":["https://openalex.org/I111950717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130856782","display_name":"Ling Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Ling Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, Macau University of Science and Technology, Macau SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-8313-5749","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau SAR, China","institution_ids":["https://openalex.org/I111950717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128646155","display_name":"Xian Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhong","raw_affiliation_strings":["Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-5242-0467","affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130854207","display_name":"Feifei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifei Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8153-9977","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"last","author":{"id":null,"display_name":"Rubing Huang","orcid":"https://orcid.org/0000-0002-1769-6126"},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Rubing Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Macau University of Science and Technology, Macau SAR, China and Macau University of Science and Technology, Zhuhai MUST Science and Technology Research Institute, Zhuhai, China"],"raw_orcid":"https://orcid.org/0000-0002-1769-6126","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau SAR, China and Macau University of Science and Technology, Zhuhai MUST Science and Technology Research Institute, Zhuhai, China","institution_ids":["https://openalex.org/I111950717"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8969,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97401527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"5","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958000183105469,"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":0.9958000183105469,"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/T10028","display_name":"Topic Modeling","score":0.0005000000237487257,"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":0.0005000000237487257,"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/question-answering","display_name":"Question answering","score":0.8251000046730042},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.629800021648407},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6098999977111816},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5717999935150146},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47049999237060547},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.421099990606308},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4205999970436096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8539999723434448},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8251000046730042},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.629800021648407},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6098999977111816},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5717999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.51910001039505},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4205999970436096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805048","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3805048","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","id":"https://metadata.un.org/sdg/4","score":0.4668070077896118}],"awards":[{"id":"https://openalex.org/G1629549548","display_name":null,"funder_award_id":"62271361","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2745461083","https://openalex.org/W2806070179","https://openalex.org/W2901988662","https://openalex.org/W2947312908","https://openalex.org/W2964213933","https://openalex.org/W2966683369","https://openalex.org/W3170841864","https://openalex.org/W3195963939","https://openalex.org/W3198377975","https://openalex.org/W4297808394","https://openalex.org/W4380201463","https://openalex.org/W4383200124","https://openalex.org/W4384918448","https://openalex.org/W4386076642","https://openalex.org/W4388181804","https://openalex.org/W4391249049","https://openalex.org/W4393033612","https://openalex.org/W4408466421","https://openalex.org/W4411920732"],"related_works":[],"abstract_inverted_index":{"In":[0],"Visual":[1,69],"Question":[2],"Answering":[3],"(VQA)":[4],",":[5],"both":[6],"the":[7,15,21,39,68,77,86,107,124],"image":[8,98],"and":[9,34,41,55,89,131],"its":[10],"accompanying":[11],"question":[12,103],"serve":[13,137],"as":[14,138],"primary":[16],"sources":[17],"of":[18,79],"information":[19,65,113],"for":[20,32],"model.":[22],"Conventional":[23],"approaches":[24],"typically":[25],"rely":[26],"heavily":[27],"on":[28,85],"dense":[29],"visual":[30,40,112,119],"representations":[31],"reasoning":[33],"answer":[35],"prediction.":[36],"However,":[37],"when":[38],"textual":[42,81],"modalities":[43],"are":[44],"imbalanced":[45],"or":[46,114],"semantically":[47],"misaligned,":[48],"such":[49],"disparities":[50],"hinder":[51],"effective":[52,140],"multimodal":[53,64],"learning":[54],"inference.":[56],"To":[57],"address":[58],"this":[59],"issue,":[60],"we":[61],"propose":[62],"a":[63],"adjustment":[66],"method,":[67],"Text":[70],"Information":[71],"Adjuster":[72],"(ViTA)":[73],".":[74,158],"ViTA":[75,105,135],"investigates":[76],"impact":[78],"embedding":[80],"cues":[82,120],"within":[83],"images":[84],"VQA":[87,149],"process":[88],"promotes":[90],"cross-modal":[91],"balance":[92,108],"to":[93],"improve":[94],"accuracy.":[95],"Specifically,":[96],"since":[97],"content":[99],"often":[100],"dominates":[101],"over":[102],"content,":[104],"adjusts":[106],"by":[109],"either":[110],"masking":[111],"augmenting":[115],"it":[116],"with":[117],"object-word":[118],"directly":[121],"embedded":[122],"in":[123],"image.":[125],"Experimental":[126],"results":[127],"validate":[128],"our":[129],"hypothesis":[130],"further":[132],"demonstrate":[133],"that":[134],"can":[136],"an":[139],"data":[141],"augmentation":[142],"strategy,":[143],"yielding":[144],"measurable":[145],"improvements":[146],"across":[147],"multiple":[148],"models.":[150],"The":[151],"code":[152],"will":[153],"be":[154],"released":[155],"at":[156],"https://github.com/xqx23/ViTA":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-29T00:00:00"}
