{"id":"https://openalex.org/W4400489591","doi":"https://doi.org/10.1109/cscwd61410.2024.10580527","title":"VIG: Visual Information-Guided Knowledge-Based Visual Question Answering","display_name":"VIG: Visual Information-Guided Knowledge-Based Visual Question Answering","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4400489591","doi":"https://doi.org/10.1109/cscwd61410.2024.10580527"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd61410.2024.10580527","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cscwd61410.2024.10580527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-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/A5100392547","display_name":"Heng Liu","orcid":"https://orcid.org/0009-0006-4959-6062"},"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 University of Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"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 University of Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"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 University of Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"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 University of Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"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 University of Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020527092","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0003-3121-1823"},"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 University of Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"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/A5100392547"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09678062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1086","last_page":"1091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9972000122070312,"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":0.9904999732971191,"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":0.837592601776123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7370468974113464},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.4814162254333496},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3893306851387024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35637208819389343},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3267403542995453}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.837592601776123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7370468974113464},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.4814162254333496},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3893306851387024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35637208819389343},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3267403542995453}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd61410.2024.10580527","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cscwd61410.2024.10580527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W2362367986","https://openalex.org/W348707231","https://openalex.org/W2064719069","https://openalex.org/W3041760129"],"abstract_inverted_index":{"A":[0],"better":[1],"knowledge-based":[2,31,114],"visual":[3,12,24,32,53,102,115,126,134,140,161,168],"question":[4,14,25,33,116],"answering":[5,26,34,117],"(KBVQA)":[6],"model":[7],"needs":[8],"to":[9,20,73,179],"rely":[10],"on":[11,65,187],"features,":[13,15],"and":[16,91,170,191],"related":[17],"external":[18,84],"knowledge":[19,85,98,149,157,174],"solve":[21,106],"an":[22,176,181],"open":[23],"task.":[27],"Although":[28],"the":[29,43,66,75,80,123,148,156,167,188],"existing":[30],"works":[35],"have":[36],"achieved":[37],"some":[38],"accomplishments,":[39],"there":[40,92],"are":[41],"still":[42],"following":[44],"challenges:":[45],"1)":[46,130],"There":[47],"is":[48,58,71,87,93],"a":[49,60,94,111],"serious":[50],"lack":[51,95],"of":[52,79,96,125,195],"feature":[54,103,141,162],"information.":[55,104,128,142,163],"Image":[56],"information":[57,70,78,135,153],"worth":[59],"thousand":[61],"words.":[62],"Only":[63],"relying":[64],"converted":[67],"salient":[68],"text":[69,152,173],"difficult":[72],"express":[74],"original":[76],"rich":[77],"image.":[81],"2)":[82,143],"The":[83],"acquired":[86],"not":[88,146],"comprehensive":[89],"enough,":[90],"relevant":[97],"directly":[99,158],"retrieved":[100,150,159,171],"by":[101],"To":[105],"these":[107],"challenges,":[108],"we":[109,165],"propose":[110],"Visual":[112],"Information-Guided":[113],"(VIG)":[118],"model.":[119],"It":[120],"fully":[121],"considers":[122],"utilization":[124],"features":[127,169],"Specifically:":[129],"We":[131,144,183],"introduce":[132],"multi-granularity":[133],"that":[136],"can":[137],"comprehensively":[138],"characterize":[139],"consider":[145],"only":[147],"through":[151],"but":[154],"also":[155],"from":[160],"Finally,":[164],"feed":[166],"multiple":[172],"into":[175],"encoder-decoder":[177],"module":[178],"generate":[180],"answer.":[182],"perform":[184],"extensive":[185],"experiments":[186],"OKVQA":[189],"dataset":[190],"achieve":[192],"state-of-the-art":[193],"performance":[194],"60.27%":[196],"accuracy.":[197]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
