{"id":"https://openalex.org/W4320507215","doi":"https://doi.org/10.1145/3579051.3579053","title":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection","display_name":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection","publication_year":2022,"publication_date":"2022-10-27","ids":{"openalex":"https://openalex.org/W4320507215","doi":"https://doi.org/10.1145/3579051.3579053"},"language":"en","primary_location":{"id":"doi:10.1145/3579051.3579053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579051.3579053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Joint Conference on Knowledge Graphs","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/A5100345062","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0001-9991-6892"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-9991-6892","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046139808","display_name":"Yufeng Huang","orcid":"https://orcid.org/0000-0001-7110-9298"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Huang","raw_affiliation_strings":["School of Software Technology, Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-7110-9298","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085691361","display_name":"Jiaoyan Chen","orcid":"https://orcid.org/0000-0003-4643-6750"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiaoyan Chen","raw_affiliation_strings":["Department of Computer Science, University of Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-4643-6750","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042099863","display_name":"Yuxia Geng","orcid":"https://orcid.org/0000-0002-2461-2613"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxia Geng","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-2461-2613","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051839900","display_name":"Fang Yin","orcid":"https://orcid.org/0000-0001-9538-848X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Fang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-9538-848X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066422711","display_name":"Jeff Z. Pan","orcid":"https://orcid.org/0000-0002-9779-2088"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jeff Z. Pan","raw_affiliation_strings":["School of Informatics, The University of Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-9779-2088","affiliations":[{"raw_affiliation_string":"School of Informatics, The University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089259739","display_name":"Ningyu Zhang","orcid":"https://orcid.org/0000-0002-1970-0678"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningyu Zhang","raw_affiliation_strings":["School of Software Technology, Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-1970-0678","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023045386","display_name":"Wen Zhang","orcid":"https://orcid.org/0000-0001-8429-9326"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Zhang","raw_affiliation_strings":["School of Software Technology, Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-8429-9326","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20","last_page":"29"},"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":0.9943000078201294,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9929999709129333,"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":0.8456301689147949},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7321555614471436},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5679974555969238},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5503805875778198},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5245854258537292},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5237210392951965},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5187709331512451},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5179144740104675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.494337797164917},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4495221972465515},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3510577082633972},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12853378057479858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456301689147949},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7321555614471436},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5679974555969238},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5503805875778198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5245854258537292},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5237210392951965},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5187709331512451},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5179144740104675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.494337797164917},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4495221972465515},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3510577082633972},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12853378057479858},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579051.3579053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579051.3579053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Joint Conference on Knowledge Graphs","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3253514882","display_name":"ConCur: Knowledge Base Construction and Curation","funder_award_id":"EP/V050869/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5836572675","display_name":null,"funder_award_id":"U19B2027,91846204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7513764588","display_name":null,"funder_award_id":"EP/V050869/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2745461083","https://openalex.org/W2752573522","https://openalex.org/W2964303913","https://openalex.org/W2966317026","https://openalex.org/W2998702515","https://openalex.org/W3093200502","https://openalex.org/W3101703188","https://openalex.org/W3118741274","https://openalex.org/W3135279933","https://openalex.org/W3139224848","https://openalex.org/W3153385943","https://openalex.org/W3157008829","https://openalex.org/W3171007011","https://openalex.org/W3173220247","https://openalex.org/W3173909648","https://openalex.org/W3189827190","https://openalex.org/W4226321975","https://openalex.org/W4252076394","https://openalex.org/W4288088047","https://openalex.org/W4288345608","https://openalex.org/W4297802107","https://openalex.org/W4301471874","https://openalex.org/W4312971273"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W4401140950","https://openalex.org/W4400650325","https://openalex.org/W4292070284","https://openalex.org/W4319071221","https://openalex.org/W4313174091","https://openalex.org/W64303689","https://openalex.org/W4313219769"],"abstract_inverted_index":{"Visual":[0],"question":[1],"answering":[2],"(VQA)":[3],"often":[4,36,50],"requires":[5],"an":[6,79,107],"understanding":[7],"of":[8],"visual":[9],"concepts":[10],"and":[11,38,88],"language":[12,24],"semantics,":[13],"which":[14,49,111],"relies":[15],"on":[16,115],"external":[17,80],"knowledge.":[18],"Most":[19],"existing":[20],"methods":[21,42],"exploit":[22],"pre-trained":[23],"models":[25],"or/and":[26],"unstructured":[27],"text,":[28],"but":[29,55],"the":[30,56],"knowledge":[31,46,95],"in":[32],"these":[33],"resources":[34],"are":[35],"incomplete":[37],"noisy.":[39],"Some":[40],"other":[41],"prefer":[43],"to":[44],"use":[45],"graphs":[47],"(KGs)":[48],"have":[51],"intensive":[52],"structured":[53],"knowledge,":[54],"research":[57],"is":[58],"still":[59],"quite":[60],"preliminary.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,82,98],"propose":[66,89],"LaKo,":[67],"a":[68,90,102],"knowledge-driven":[69],"VQA":[70,100],"method":[71],"via":[72],"Late":[73],"Knowledge-to-text":[74],"Injection.":[75],"To":[76],"effectively":[77],"incorporate":[78],"KG,":[81],"transfer":[83],"triples":[84],"into":[85],"textual":[86],"format":[87],"late":[91],"injection":[92],"mechanism":[93],"for":[94],"fusion.":[96],"Finally":[97],"address":[99],"as":[101],"text":[103],"generation":[104],"task":[105],"with":[106],"effective":[108],"encoder-decoder":[109],"paradigm,":[110],"achieves":[112],"state-of-the-art":[113],"results":[114],"OKVQA":[116],"datasets.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
