{"id":"https://openalex.org/W4386390772","doi":"https://doi.org/10.1145/3618301","title":"Cross-modality Multiple Relations Learning for Knowledge-based Visual Question Answering","display_name":"Cross-modality Multiple Relations Learning for Knowledge-based Visual Question Answering","publication_year":2023,"publication_date":"2023-09-02","ids":{"openalex":"https://openalex.org/W4386390772","doi":"https://doi.org/10.1145/3618301"},"language":"en","primary_location":{"id":"doi:10.1145/3618301","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3618301","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/A5100322699","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-4751-0708"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Wang","raw_affiliation_strings":["School of Artificial Intelligence, and Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, and Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, China","institution_ids":["https://openalex.org/I890469752","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102795939","display_name":"Peize Li","orcid":"https://orcid.org/0000-0002-5321-2176"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peize Li","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013535642","display_name":"Qingyi Si","orcid":"https://orcid.org/0000-0001-8433-0215"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyi Si","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332185","display_name":"Hanwen Zhang","orcid":"https://orcid.org/0000-0003-4081-8838"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanwen Zhang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103083206","display_name":"Wenyu Zang","orcid":"https://orcid.org/0000-0002-6369-0681"},"institutions":[{"id":"https://openalex.org/I4210104233","display_name":"China Electronics Corporation (China)","ror":"https://ror.org/00vsv8c52","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210104233"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Zang","raw_affiliation_strings":["China Electronics Corporation, China"],"affiliations":[{"raw_affiliation_string":"China Electronics Corporation, China","institution_ids":["https://openalex.org/I4210104233"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067997634","display_name":"Zheng Lin","orcid":"https://orcid.org/0000-0002-8432-1658"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Lin","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001781730","display_name":"Peng Fu","orcid":"https://orcid.org/0000-0001-9899-8566"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Fu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100322699"],"corresponding_institution_ids":["https://openalex.org/I194450716","https://openalex.org/I890469752"],"apc_list":null,"apc_paid":null,"fwci":1.0697,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79543823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"20","issue":"3","first_page":"1","last_page":"22"},"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":0.9958999752998352,"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":0.991100013256073,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7733446359634399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7326924800872803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5827342867851257},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5682585835456848},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5661623477935791},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5649821162223816},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5014615058898926},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4978611469268799},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.44847509264945984},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4251856207847595}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7733446359634399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326924800872803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827342867851257},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5682585835456848},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5661623477935791},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5649821162223816},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5014615058898926},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4978611469268799},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.44847509264945984},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4251856207847595},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3618301","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3618301","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1064764950","display_name":null,"funder_award_id":"C2001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G128251435","display_name":null,"funder_award_id":"61906187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1433666547","display_name":null,"funder_award_id":"61976207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2241915452","display_name":null,"funder_award_id":"62072212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2507855583","display_name":null,"funder_award_id":"202004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3472539505","display_name":null,"funder_award_id":"202205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3678371314","display_name":null,"funder_award_id":"Nos. 62072212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6377348181","display_name":null,"funder_award_id":"2022050","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6544468730","display_name":null,"funder_award_id":"202105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7984034579","display_name":null,"funder_award_id":"62072212, 61906187, 61976207, and 61902394","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8681811600","display_name":null,"funder_award_id":"61902394","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"},{"id":"https://openalex.org/F4320322174","display_name":"People's Government of Jilin Province","ror":"https://ror.org/02fzqav45"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1862719289","https://openalex.org/W2016089260","https://openalex.org/W2050398567","https://openalex.org/W2521367263","https://openalex.org/W2552639984","https://openalex.org/W2560730294","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2760103357","https://openalex.org/W2807480793","https://openalex.org/W2888166343","https://openalex.org/W2916723116","https://openalex.org/W2947312908","https://openalex.org/W2962529143","https://openalex.org/W2963717374","https://openalex.org/W2963760481","https://openalex.org/W2964057271","https://openalex.org/W2964072591","https://openalex.org/W2966683369","https://openalex.org/W2969663619","https://openalex.org/W2970231061","https://openalex.org/W2996695408","https://openalex.org/W2999905431","https://openalex.org/W3003260174","https://openalex.org/W3026092005","https://openalex.org/W3034837210","https://openalex.org/W3035454069","https://openalex.org/W3038528491","https://openalex.org/W3044175177","https://openalex.org/W3093006710","https://openalex.org/W3093200502","https://openalex.org/W3105077954","https://openalex.org/W3113204237","https://openalex.org/W3115476810","https://openalex.org/W3128560592","https://openalex.org/W3139224848","https://openalex.org/W3155322285","https://openalex.org/W3155855665","https://openalex.org/W3161051151","https://openalex.org/W3172845486","https://openalex.org/W3173038784","https://openalex.org/W3173220247","https://openalex.org/W3213368993","https://openalex.org/W4214825151","https://openalex.org/W4221155360","https://openalex.org/W6777179611"],"related_works":["https://openalex.org/W2964061310","https://openalex.org/W2231285690","https://openalex.org/W2963477107","https://openalex.org/W3093385053","https://openalex.org/W4390091918","https://openalex.org/W2553418567","https://openalex.org/W4389682534","https://openalex.org/W3045060014","https://openalex.org/W2138707363","https://openalex.org/W4309397398"],"abstract_inverted_index":{"Knowledge-based":[0],"visual":[1,35,76,131,139,169],"question":[2,79,127],"answering":[3],"not":[4],"only":[5],"needs":[6],"to":[7,19,43,70,91,110,128,146,150,176],"answer":[8],"the":[9,23,32,45,116,125,129,138,168,183,187,200,215],"questions":[10],"based":[11],"on":[12,199],"images":[13],"but":[14],"also":[15],"incorporates":[16],"external":[17],"knowledge":[18,100],"study":[20],"reasoning":[21],"in":[22,182],"joint":[24],"space":[25],"of":[26],"vision":[27],"and":[28,37,47,78,96,141,171,186,204],"language.":[29],"To":[30],"bridge":[31],"gap":[33],"between":[34,75],"content":[36],"semantic":[38,155,192],"cues,":[39],"it":[40,68],"is":[41],"important":[42],"capture":[44],"question-related":[46],"semantics-rich":[48],"vision-language":[49,184],"connections.":[50],"Most":[51],"existing":[52],"solutions":[53],"model":[54,72,213],"simple":[55,106],"intra-modality":[56],"relation":[57,61],"or":[58],"represent":[59,115],"cross-modality":[60,85,94,118,122,180],"using":[62],"a":[63,84,105,160],"single":[64],"vector,":[65],"which":[66],"makes":[67],"difficult":[69],"effectively":[71],"complex":[73],"connections":[74],"features":[77],"features.":[80],"Thus,":[81],"we":[82,103,157],"propose":[83],"multiple":[86,112,148,195],"relations":[87,113,123,149,181],"learning":[88],"model,":[89],"aiming":[90],"better":[92,151,190],"enrich":[93],"representations":[95],"construct":[97],"advanced":[98],"multi-modality":[99,134],"triplets.":[101],"First,":[102],"design":[104],"yet":[107],"effective":[108],"method":[109],"generate":[111],"that":[114,211],"rich":[117],"relations.":[119,196],"The":[120,164],"various":[121],"link":[124],"textual":[126,143,173],"related":[130],"objects.":[132],"These":[133],"triplets":[135],"efficiently":[136],"align":[137,152],"objects":[140,170],"corresponding":[142,172],"answers.":[144],"Second,":[145],"encourage":[147],"with":[153],"different":[154],"relations,":[156],"further":[158],"formulate":[159],"novel":[161],"global-local":[162],"loss.":[163],"global":[165],"loss":[166,189],"enables":[167],"answers":[174],"close":[175],"each":[177],"other":[178],"through":[179],"space,":[185],"local":[188],"preserves":[191],"diversity":[193],"among":[194],"Experimental":[197],"results":[198],"Outside":[201],"Knowledge":[202],"VQA":[203],"Knowledge-Routed":[205],"Visual":[206],"Question":[207],"Reasoning":[208],"datasets":[209],"demonstrate":[210],"our":[212],"outperforms":[214],"state-of-the-art":[216],"methods.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
