{"id":"https://openalex.org/W4410986034","doi":"https://doi.org/10.1109/tai.2025.3575553","title":"ICQ-TransE: LLM-Enhanced Image-Caption-Question Translating Embeddings for Knowledge-Based Visual Question Answering","display_name":"ICQ-TransE: LLM-Enhanced Image-Caption-Question Translating Embeddings for Knowledge-Based Visual Question Answering","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4410986034","doi":"https://doi.org/10.1109/tai.2025.3575553"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3575553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3575553","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","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/A5037931738","display_name":"Heng Liu","orcid":"https://orcid.org/0000-0002-0703-6255"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Heng Liu","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091545406","display_name":"Boyue Wang","orcid":"https://orcid.org/0000-0002-2677-8342"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyue Wang","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014727866","display_name":"Xiaoyan Li","orcid":"https://orcid.org/0000-0003-1536-4264"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Li","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082380547","display_name":"Yanfeng Sun","orcid":"https://orcid.org/0000-0002-0872-384X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Sun","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027329007","display_name":"Yongli Hu","orcid":"https://orcid.org/0000-0003-0440-438X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongli Hu","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059859891","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0002-4164-6647"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology,, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037931738"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":1.2784,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80388815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"7","issue":"1","first_page":"412","last_page":"425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9919999837875366,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9794999957084656,"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":0.6327503323554993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5125484466552734},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4710676074028015},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43042975664138794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37037572264671326}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6327503323554993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5125484466552734},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4710676074028015},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43042975664138794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37037572264671326}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3575553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3575553","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W639708223","https://openalex.org/W1832693441","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2521367263","https://openalex.org/W2561529111","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2760103357","https://openalex.org/W2909384861","https://openalex.org/W2947312908","https://openalex.org/W2963717374","https://openalex.org/W2963954913","https://openalex.org/W2964061310","https://openalex.org/W2966683369","https://openalex.org/W2970231061","https://openalex.org/W2980401255","https://openalex.org/W2987671777","https://openalex.org/W3033514332","https://openalex.org/W3034987253","https://openalex.org/W3035454069","https://openalex.org/W3044175177","https://openalex.org/W3093200502","https://openalex.org/W3101703188","https://openalex.org/W3110575265","https://openalex.org/W3115476810","https://openalex.org/W3118741274","https://openalex.org/W3132185473","https://openalex.org/W3172845486","https://openalex.org/W3173038784","https://openalex.org/W3176821361","https://openalex.org/W3185066916","https://openalex.org/W3199693760","https://openalex.org/W3201302554","https://openalex.org/W4206430846","https://openalex.org/W4221155360","https://openalex.org/W4226321975","https://openalex.org/W4285280022","https://openalex.org/W4287855132","https://openalex.org/W4293261733","https://openalex.org/W4312044727","https://openalex.org/W4319301039","https://openalex.org/W4379382581","https://openalex.org/W4382998936","https://openalex.org/W4385574156","https://openalex.org/W4386065596","https://openalex.org/W4386076140","https://openalex.org/W4394744251"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"In":[0],"knowledge-based":[1],"visual":[2,14,74,112,143,169,179,188,215],"question":[3,20,31,62,78,132,192,216],"answering":[4,217],"(KB-VQA),":[5],"the":[6,19,23,30,33,36,58,61,69,77,84,89,94,104,108,119,126,134,138,142,146,168,182,185,191,205],"answer":[7],"can":[8,155],"be":[9,156,223],"naturally":[10],"represented":[11],"by":[12,18],"translating":[13],"object":[15,170],"embedding":[16,26],"referred":[17],"according":[21],"to":[22,28,66,131,190,210],"cross-modality":[24,40,70,105,116,153],"relation":[25,106,117,165],"related":[27],"both":[29,103],"and":[32,44,60,107,145,200],"image.":[34,86],"Though":[35],"triplet":[37],"representation":[38],"of":[39,111,173,178,207],"knowledge":[41],"is":[42],"plausible":[43],"proven":[45],"effective,":[46],"these":[47],"methods":[48,213],"often":[49,79],"encounter":[50],"two":[51],"challenges:":[52],"1)":[53],"The":[54,73],"semantic":[55],"gap":[56],"between":[57],"image":[59,130],"makes":[63],"it":[64],"difficult":[65],"accurately":[67],"embed":[68],"relation;":[71],"2)":[72],"objects":[75],"in":[76,83,161],"have":[80],"ambiguous":[81],"references":[82],"input":[85],"To":[87],"solve":[88],"above":[90],"challenges,":[91],"we":[92],"propose":[93],"Image-Caption-Question":[95],"Translating":[96],"Embeddings":[97],"(ICQ-TransE),":[98],"which":[99],"more":[100,157,162],"effectively":[101,158],"models":[102],"head":[109],"entity":[110],"objects.":[113],"Specifically,":[114],"for":[115,214],"embedding,":[118,171],"designed":[120],"image-caption-question":[121],"information":[122,127,154],"transmission":[123],"mechanism":[124],"transmits":[125],"flow":[128],"from":[129],"through":[133],"caption":[135,139],"bridge,":[136,152],"where":[137],"simultaneously":[140],"has":[141],"content":[144],"textual":[147],"form.":[148],"With":[149],"this":[150],"powerful":[151],"fused,":[159],"resulting":[160],"precisely":[163],"encoded":[164],"embeddings.":[166],"For":[167],"instead":[172],"using":[174],"a":[175],"fixed":[176],"number":[177],"regions":[180,189],"as":[181],"previous":[183],"methods,":[184],"most":[186],"relevant":[187],"are":[193],"dynamically":[194],"selected.":[195],"Experimental":[196],"results":[197],"on":[198],"OK-VQA":[199],"KRVQA":[201],"challenging":[202],"datasets":[203],"verify":[204],"effectiveness":[206],"ICQ-TransE":[208],"compared":[209],"multiple":[211],"state-of-the-art":[212],"with":[218],"knowledge.":[219],"Our":[220],"code":[221],"will":[222],"available":[224],"at":[225],"https://github.com/cmcv2022/ICQ-TransE.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}