{"id":"https://openalex.org/W4408345711","doi":"https://doi.org/10.1109/icassp49660.2025.10890131","title":"Visual Entity-Centric Prompting for Knowledge Retrieval in Knowledge-based VQA","display_name":"Visual Entity-Centric Prompting for Knowledge Retrieval in Knowledge-based VQA","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345711","doi":"https://doi.org/10.1109/icassp49660.2025.10890131"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5058425766","display_name":"Jiaming Yang","orcid":"https://orcid.org/0009-0006-4035-6070"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Yang","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038772368","display_name":"Jiuxiang You","orcid":"https://orcid.org/0009-0004-0093-1128"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiuxiang You","raw_affiliation_strings":["Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055713575","display_name":"Ziyue Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyue Qiu","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602659","display_name":"Guobo Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guobo Xie","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745222","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-0294-6620"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102760381","display_name":"Zhenguo Yang","orcid":"https://orcid.org/0000-0003-3279-0732"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenguo Yang","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88932007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9175000190734863,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9175000190734863,"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":0.7365325689315796},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4952336847782135},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4847078323364258},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.47026926279067993},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.4660182297229767},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3791855275630951},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3307696580886841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3087267279624939}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365325689315796},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4952336847782135},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4847078323364258},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.47026926279067993},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.4660182297229767},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3791855275630951},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3307696580886841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3087267279624939}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2947312908","https://openalex.org/W2964303913","https://openalex.org/W3093200502","https://openalex.org/W3199693760","https://openalex.org/W4283777642","https://openalex.org/W4285294723","https://openalex.org/W4312971273","https://openalex.org/W4385245566","https://openalex.org/W4386076140","https://openalex.org/W4386159793","https://openalex.org/W4389520080","https://openalex.org/W4390873086","https://openalex.org/W4392909355","https://openalex.org/W4402917081","https://openalex.org/W6769627184","https://openalex.org/W6810334672","https://openalex.org/W6849177959","https://openalex.org/W6850204008"],"related_works":["https://openalex.org/W1520100787","https://openalex.org/W3148901273","https://openalex.org/W2357854711","https://openalex.org/W2163958188","https://openalex.org/W2508944927","https://openalex.org/W1993999021","https://openalex.org/W2888716383","https://openalex.org/W4376624582","https://openalex.org/W2793744252","https://openalex.org/W207286913"],"abstract_inverted_index":{"External":[0],"knowledge":[1,14,28,40,52,132,151],"provides":[2],"critical":[3,75],"clues":[4],"for":[5,27,39],"knowledge-based":[6],"visual":[7,36,55,64,102,147],"question":[8,66],"answering":[9,67],"(KB-VQA),":[10],"while":[11],"the":[12,45,48,74,78,119,144,168,171],"implicit":[13,49],"in":[15,21,127],"images":[16,80],"is":[17,70,111,140],"difficult":[18],"to":[19,23,43,72,83,113,129,142,156],"capture":[20],"order":[22,128],"construct":[24,114],"effective":[25],"queries":[26],"bases.":[29],"To":[30],"this":[31],"end,":[32],"we":[33],"propose":[34],"a":[35,63,88,101,106,115,135],"entity-centric":[37,85,97],"prompting":[38],"retrieval":[41,108],"(VEPR)":[42],"bridge":[44],"gap":[46],"between":[47],"and":[50,81,125,149],"explicit":[51,131],"driven":[53],"by":[54,117],"entities":[56,76],"via":[57,87,100],"large":[58,89],"language":[59,90,103],"models.":[60],"More":[61],"specifically,":[62],"entity":[65],"(EQ)":[68],"module":[69,110,139],"devised":[71,112],"localize":[73],"from":[77],"given":[79,145],"questions":[82,86],"generate":[84],"model.":[91,104],"In":[92],"particular,":[93],"EQ":[94],"obtains":[95],"several":[96],"question-answer":[98,122],"pairs":[99],"Furthermore,":[105],"question-answer-enhanced":[107],"(ER)":[109],"query":[116],"summarizing":[118],"text":[120],"including":[121],"pairs,":[123],"captions":[124],"questions,":[126,146],"require":[130],"items.":[133],"Finally,":[134],"multi-branch":[136],"reader":[137],"(MR)":[138],"designed":[141],"encode":[143],"content":[148],"retrieved":[150],"items,":[152],"which":[153],"are":[154],"decoded":[155],"make":[157],"answer":[158],"predictions.":[159],"Extensive":[160],"experiments":[161],"conducted":[162],"on":[163],"two":[164],"public":[165],"datasets":[166],"demonstrate":[167],"effectiveness":[169],"of":[170],"VEPR.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}