{"id":"https://openalex.org/W4410121147","doi":"https://doi.org/10.1145/3734220","title":"SCAG: Semantic Co-occurring Attention Guided Alignment for Knowledge-based Visual Question Answering","display_name":"SCAG: Semantic Co-occurring Attention Guided Alignment for Knowledge-based Visual Question Answering","publication_year":2025,"publication_date":"2025-05-06","ids":{"openalex":"https://openalex.org/W4410121147","doi":"https://doi.org/10.1145/3734220"},"language":"en","primary_location":{"id":"doi:10.1145/3734220","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3734220","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/A5100423703","display_name":"Zheng Liu","orcid":"https://orcid.org/0000-0002-8522-565X"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Liu","raw_affiliation_strings":["The Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","the Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, China"],"raw_orcid":"https://orcid.org/0000-0002-8522-565X","affiliations":[{"raw_affiliation_string":"The Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"the Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101101909","display_name":"Kunyu Yang","orcid":"https://orcid.org/0009-0007-6004-9147"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunyu Yang","raw_affiliation_strings":["The Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","the Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, China"],"raw_orcid":"https://orcid.org/0009-0007-6004-9147","affiliations":[{"raw_affiliation_string":"The Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"the Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024296105","display_name":"Yu Weng","orcid":"https://orcid.org/0000-0002-0787-550X"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Weng","raw_affiliation_strings":["The Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","the Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, China"],"raw_orcid":"https://orcid.org/0000-0002-0787-550X","affiliations":[{"raw_affiliation_string":"The Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"the Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheng He","orcid":"https://orcid.org/0009-0000-8375-5027"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng He","raw_affiliation_strings":["The Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","the Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, China"],"raw_orcid":"https://orcid.org/0009-0000-8375-5027","affiliations":[{"raw_affiliation_string":"The Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"the Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362313","display_name":"Xuan Liu","orcid":"https://orcid.org/0000-0002-5064-6526"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Liu","raw_affiliation_strings":["The Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","the Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, China"],"raw_orcid":"https://orcid.org/0000-0002-5064-6526","affiliations":[{"raw_affiliation_string":"The Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"the Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087225784","display_name":"Honghao Gao","orcid":"https://orcid.org/0000-0001-6861-9684"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honghao Gao","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China","the School of Computer Engineering and Science, Shanghai University, China"],"raw_orcid":"https://orcid.org/0000-0001-6861-9684","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]},{"raw_affiliation_string":"the School of Computer Engineering and Science, Shanghai University, China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8207539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"21","issue":"7","first_page":"1","last_page":"20"},"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":0.9977999925613403,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9926999807357788,"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":0.8297067880630493},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.6728334426879883},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6187941431999207},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4204120635986328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34277647733688354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33463212847709656},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3296477198600769},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.15371474623680115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297067880630493},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.6728334426879883},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6187941431999207},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4204120635986328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34277647733688354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33463212847709656},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3296477198600769},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.15371474623680115},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3734220","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3734220","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":[],"awards":[{"id":"https://openalex.org/G1209096496","display_name":null,"funder_award_id":"2022YFF0902500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G885349591","display_name":null,"funder_award_id":"Z231100001723002","funder_id":"https://openalex.org/F4320325902","funder_display_name":"Beijing Municipal Science and Technology Commission"}],"funders":[{"id":"https://openalex.org/F4320325902","display_name":"Beijing Municipal Science and Technology Commission","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W2138621090","https://openalex.org/W2613718673","https://openalex.org/W2750779823","https://openalex.org/W2962858109","https://openalex.org/W2966317026","https://openalex.org/W2969862959","https://openalex.org/W2970231061","https://openalex.org/W3016923549","https://openalex.org/W3034972674","https://openalex.org/W3035454069","https://openalex.org/W3101703188","https://openalex.org/W3134284227","https://openalex.org/W3172845486","https://openalex.org/W3174010726","https://openalex.org/W3177654849","https://openalex.org/W3181954312","https://openalex.org/W3182020042","https://openalex.org/W3196798856","https://openalex.org/W3198080531","https://openalex.org/W3202473058","https://openalex.org/W4214824212","https://openalex.org/W4221155360","https://openalex.org/W4226321975","https://openalex.org/W4281653378","https://openalex.org/W4281944818","https://openalex.org/W4311897500","https://openalex.org/W4312971273","https://openalex.org/W4385392862","https://openalex.org/W4385569837","https://openalex.org/W4385569915","https://openalex.org/W4385574177","https://openalex.org/W4386065596","https://openalex.org/W4386065803","https://openalex.org/W4386148430","https://openalex.org/W4386390772","https://openalex.org/W4387954093","https://openalex.org/W4387968292","https://openalex.org/W4388186922","https://openalex.org/W4389140516","https://openalex.org/W4389520525","https://openalex.org/W4390190087","https://openalex.org/W4390873086","https://openalex.org/W4390873421","https://openalex.org/W4391778626","https://openalex.org/W4392746913","https://openalex.org/W4392964660","https://openalex.org/W4394744251","https://openalex.org/W4402793079","https://openalex.org/W4412230188","https://openalex.org/W6858831103"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W2115758952"],"abstract_inverted_index":{"In":[0],"the":[1,9,12,50,58,73,91,116,127,139,161,174,188,192],"realm":[2],"of":[3,11,53,153],"Knowledge-based":[4],"Visual":[5],"Question":[6],"Answering":[7],"(KB-VQA),":[8],"intricacy":[10],"task":[13],"lies":[14],"in":[15,57,65,115,190],"adeptly":[16],"retrieving":[17],"pertinent":[18],"information":[19,55,133],"from":[20,95],"external":[21,36,144],"sources":[22],"and":[23,26,68,100,118,147,163],"seamlessly":[24],"aligning":[25],"amalgamating":[27],"multimodal":[28],"features.":[29],"While":[30],"numerous":[31],"studies":[32],"have":[33],"effectively":[34],"leveraged":[35],"knowledge":[37,74,145,193],"to":[38,48,109,130],"enrich":[39],"factual":[40],"connections":[41],"among":[42],"entities,":[43],"there":[44],"exists":[45],"a":[46,83,183],"tendency":[47],"overlook":[49],"significant":[51],"reservoir":[52],"implicit":[54],"inherent":[56],"visual-textual":[59],"dimension.":[60],"This":[61,88],"oversight":[62],"often":[63],"results":[64],"suboptimal":[66],"alignment":[67,125],"an":[69],"undue":[70],"reliance":[71,142],"on":[72,143,160,173],"base.":[75],"To":[76],"address":[77],"these":[78],"challenges,":[79],"this":[80,124],"article":[81],"introduces":[82],"novel":[84],"strategy":[85],"called":[86],"SCAG.":[87],"approach":[89],"aggregates":[90],"semantic":[92],"co-occurring":[93],"attention":[94],"diverse":[96],"regions":[97],"within":[98,103,138],"images":[99],"various":[101],"tokens":[102],"textual":[104,119],"inputs":[105],"using":[106],"guidance":[107],"weights":[108],"construct":[110],"joint":[111],"probabilistic":[112],"representations":[113],"grounded":[114],"visual":[117],"dimensions,":[120],"respectively.":[121],"By":[122],"employing":[123],"strategy,":[126],"goal":[128],"is":[129,157],"substantially":[131],"mitigate":[132],"loss,":[134],"reinforce":[135],"inter-feature":[136],"constraints":[137],"model,":[140],"reduce":[141],"sources,":[146],"enhance":[148],"self-reasoning":[149],"capabilities.":[150],"The":[151],"efficacy":[152],"our":[154,180],"proposed":[155],"model":[156,181],"comprehensively":[158],"evaluated":[159],"VQAv2":[162],"OK-VQA":[164],"datasets,":[165],"with":[166],"comparative":[167],"analyses":[168],"against":[169],"multiple":[170],"models":[171],"conducted":[172],"Ambiguous":[175],"Knowledge":[176],"(AK)":[177],"dataset.":[178],"Notably,":[179],"exhibits":[182],"noteworthy":[184],"4.62%":[185],"improvement":[186],"over":[187],"state-of-the-art":[189],"addressing":[191],"dependency":[194],"problem.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
