{"id":"https://openalex.org/W4293261733","doi":"https://doi.org/10.1145/3487553.3524648","title":"Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection","display_name":"Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4293261733","doi":"https://doi.org/10.1145/3487553.3524648"},"language":"en","primary_location":{"id":"doi:10.1145/3487553.3524648","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3487553.3524648","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3487553.3524648","source":{"id":"https://openalex.org/S4363608846","display_name":"Companion Proceedings of the Web Conference 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Web Conference 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3487553.3524648","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061696723","display_name":"Diego Garc\u00eda-Olano","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego Garcia-Olano","raw_affiliation_strings":["University of Texas at Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001707231","display_name":"Yasumasa Onoe","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasumasa Onoe","raw_affiliation_strings":["University of Texas at Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103071668","display_name":"Joydeep Ghosh","orcid":"https://orcid.org/0000-0002-7366-3548"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joydeep Ghosh","raw_affiliation_strings":["University of Texas at Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.8849,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82349184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"705","last_page":"715"},"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":0.9937999844551086,"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/T10028","display_name":"Topic Modeling","score":0.9886999726295471,"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/computer-science","display_name":"Computer science","score":0.8493210077285767},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7682664394378662},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.72817462682724},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5972656607627869},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5938600301742554},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.55887770652771},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5373446345329285},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49448132514953613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.483817994594574},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4180780053138733},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39994552731513977},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.2877926230430603},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10216885805130005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8493210077285767},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7682664394378662},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.72817462682724},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5972656607627869},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5938600301742554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.55887770652771},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5373446345329285},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49448132514953613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.483817994594574},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4180780053138733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39994552731513977},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2877926230430603},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10216885805130005},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3487553.3524648","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3487553.3524648","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3487553.3524648","source":{"id":"https://openalex.org/S4363608846","display_name":"Companion Proceedings of the Web Conference 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Web Conference 2022","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3487553.3524648","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3487553.3524648","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3487553.3524648","source":{"id":"https://openalex.org/S4363608846","display_name":"Companion Proceedings of the Web Conference 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Web Conference 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293261733.pdf","grobid_xml":"https://content.openalex.org/works/W4293261733.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2963855739","https://openalex.org/W2964061310","https://openalex.org/W2964303913","https://openalex.org/W2970231061","https://openalex.org/W2970476646","https://openalex.org/W2987086322","https://openalex.org/W3093200502","https://openalex.org/W3099700870","https://openalex.org/W3100283070","https://openalex.org/W3101703188","https://openalex.org/W3102659883","https://openalex.org/W3104939451","https://openalex.org/W3105305165","https://openalex.org/W3114427170","https://openalex.org/W3168597991","https://openalex.org/W3176196997","https://openalex.org/W3199693760","https://openalex.org/W3199958362"],"related_works":["https://openalex.org/W2167202928","https://openalex.org/W4401140950","https://openalex.org/W173870552","https://openalex.org/W4400650325","https://openalex.org/W2913363942","https://openalex.org/W1793342810","https://openalex.org/W2396445622","https://openalex.org/W3006733099","https://openalex.org/W3006227201","https://openalex.org/W3151174281"],"abstract_inverted_index":{"Knowledge-Based":[0],"Visual":[1],"Question":[2],"Answering":[3],"(KBVQA)":[4],"is":[5,98],"a":[6,18,63,178],"bi-modal":[7,64,134],"task":[8,159],"requiring":[9],"external":[10],"world":[11],"knowledge":[12,31,40,174],"in":[13,62],"order":[14],"to":[15],"correctly":[16],"answer":[17],"text":[19,27],"question":[20],"and":[21,57,94,101,113,122,135,167,184],"associated":[22],"image.":[23],"Recent":[24],"single":[25,136],"modality":[26],"work":[28],"has":[29],"shown":[30],"injection":[32,175],"into":[33],"pre-trained":[34],"language":[35],"models,":[36],"specifically":[37],"entity":[38,111,147,173],"enhanced":[39,148,185],"graph":[41],"embeddings,":[42],"can":[43,66],"improve":[44,67,177],"performance":[45,72,155],"on":[46,73,156],"downstream":[47],"entity-centric":[48,100],"tasks.":[49],"In":[50],"this":[51],"work,":[52],"we":[53,114,129,168],"empirically":[54],"study":[55,115],"how":[56,131],"whether":[58],"such":[59,146],"methods,":[60],"applied":[61],"setting,":[65],"an":[68],"existing":[69],"VQA":[70,84],"system\u2019s":[71],"the":[74,116,143,157,161],"KBVQA":[75,158],"task.":[76],"We":[77,181],"experiment":[78],"with":[79,104],"two":[80],"large":[81],"publicly":[82],"available":[83],"datasets,":[85],"(1)":[86],"KVQA":[87],"which":[88,97],"contains":[89],"mostly":[90],"rare":[91],"Wikipedia":[92],"entities":[93],"(2)":[95],"OKVQA":[96],"less":[99],"more":[102],"aligned":[103],"common":[105],"sense":[106],"reasoning.":[107],"Both":[108],"lack":[109],"explicit":[110],"spans,":[112],"effect":[117],"of":[118,145],"different":[119],"weakly":[120],"supervised":[121],"manual":[123],"methods":[124],"for":[125,163,171,187],"obtaining":[126],"them.":[127],"Additionally,":[128],"analyze":[130],"recently":[132],"proposed":[133],"modal":[137],"attention":[138],"explanations":[139],"are":[140],"affected":[141],"by":[142],"incorporation":[144],"representations.":[149],"Our":[150],"results":[151],"show":[152],"substantially":[153],"improved":[154],"without":[160],"need":[162],"additional":[164],"costly":[165],"pre-training,":[166],"provide":[169,182],"insights":[170],"when":[172],"helps":[176],"model\u2019s":[179],"understanding.":[180],"code":[183],"datasets":[186],"reproducibility1.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}