{"id":"https://openalex.org/W4392909355","doi":"https://doi.org/10.1109/icassp48485.2024.10448108","title":"Implicit-Knowledge-Guided Align Before Understanding for KB-VQA","display_name":"Implicit-Knowledge-Guided Align Before Understanding for KB-VQA","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909355","doi":"https://doi.org/10.1109/icassp48485.2024.10448108"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086987894","display_name":"Feng Mao","orcid":"https://orcid.org/0000-0002-7896-4809"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao Feng","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Eigineering,Guangzhou,China","School of Computer Science and Eigineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Eigineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Eigineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052227145","display_name":"Lei Liao","orcid":"https://orcid.org/0000-0002-4751-504X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liao","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Eigineering,Guangzhou,China","School of Computer Science and Eigineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Eigineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Eigineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037873810","display_name":"Meng Yang","orcid":"https://orcid.org/0000-0002-0795-3221"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yang","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Eigineering,Guangzhou,China","School of Computer Science and Eigineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Eigineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Eigineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3680","last_page":"3684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.8794999718666077,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.8794999718666077,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6433531045913696},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3267628252506256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6433531045913696},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3267628252506256}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6484137807","display_name":null,"funder_award_id":"62176271","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":27,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2947312908","https://openalex.org/W2963521239","https://openalex.org/W2963717374","https://openalex.org/W2964303913","https://openalex.org/W2966715458","https://openalex.org/W2970231061","https://openalex.org/W3035454069","https://openalex.org/W3044175177","https://openalex.org/W3093006710","https://openalex.org/W3093200502","https://openalex.org/W3101703188","https://openalex.org/W3114427170","https://openalex.org/W3118500473","https://openalex.org/W3139224848","https://openalex.org/W3172845486","https://openalex.org/W3204138855","https://openalex.org/W4283777642","https://openalex.org/W4318718936","https://openalex.org/W6752083267","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6766904570","https://openalex.org/W6789753369","https://openalex.org/W6802115918","https://openalex.org/W6849177959"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"based":[3],"on":[4,117],"external":[5],"Knowledge":[6],"Bases(KB-VQA)":[7],"have":[8],"gained":[9],"more":[10],"attention":[11],"in":[12,31,86],"recent":[13],"years.":[14],"Due":[15],"to":[16,48,57,97],"the":[17,25,32,41,49,59,73,83,87,99,102,107,123,127],"large":[18],"scale":[19],"of":[20,27,34,52,126],"knowledge":[21,36,53,74,84,104],"base":[22,75,85],"data":[23],"and":[24,90,95,106,121],"lack":[26],"manual":[28],"annotation":[29],"information":[30,81],"process":[33],"retrieving":[35],"for":[37],"image":[38],"problem":[39],"data,":[40],"current":[42,60,128],"model":[43,113],"usually":[44],"suffers":[45],"performance":[46,77,125],"due":[47],"low":[50],"accuracy":[51],"retrieval.":[54],"In":[55],"order":[56],"solve":[58],"challenges,":[61],"we":[62],"propose":[63],"an":[64],"implicit-knowledge-guided":[65],"alignment":[66],"before":[67],"understanding":[68,96],"(IK-ALBUN)":[69],"model,":[70],"which":[71],"improves":[72],"retrieval":[76],"by":[78],"aligning":[79],"multimodal":[80],"with":[82,101],"first":[88],"stage,":[89],"conduct":[91],"multi-modal":[92],"semantic":[93],"fusion":[94],"complete":[98],"KB-VQA":[100],"retrieved":[103],"bases":[105],"additionally":[108],"designed":[109],"contrastive":[110],"loss.":[111],"The":[112],"has":[114],"completed":[115],"experiments":[116],"several":[118],"public":[119],"datasets":[120],"proved":[122],"superior":[124],"method.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}