{"id":"https://openalex.org/W4400231027","doi":"https://doi.org/10.1109/iscas58744.2024.10558259","title":"Visual question answering based evaluation metrics for text-to-image generation","display_name":"Visual question answering based evaluation metrics for text-to-image generation","publication_year":2024,"publication_date":"2024-05-19","ids":{"openalex":"https://openalex.org/W4400231027","doi":"https://doi.org/10.1109/iscas58744.2024.10558259"},"language":"en","primary_location":{"id":"doi:10.1109/iscas58744.2024.10558259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas58744.2024.10558259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5099841865","display_name":"Mizuki Miyamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mizuki Miyamoto","raw_affiliation_strings":["Hosei University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Tokyo,Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008003363","display_name":"Ryugo Morita","orcid":"https://orcid.org/0009-0007-6324-9291"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryugo Morita","raw_affiliation_strings":["Hosei University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Tokyo,Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021863826","display_name":"Jinjia Zhou","orcid":"https://orcid.org/0000-0002-5078-0522"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jinjia Zhou","raw_affiliation_strings":["Hosei University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Tokyo,Japan","institution_ids":["https://openalex.org/I204291657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47382588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9945999979972839,"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/T12290","display_name":"Human Motion and Animation","score":0.949999988079071,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.7656934261322021},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7267199754714966},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6047985553741455},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48123717308044434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.420513391494751},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3931536078453064},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.329136461019516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656934261322021},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7267199754714966},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6047985553741455},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48123717308044434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.420513391494751},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3931536078453064},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.329136461019516}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas58744.2024.10558259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas58744.2024.10558259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2962793481","https://openalex.org/W3035316078","https://openalex.org/W3094502228","https://openalex.org/W3153469116","https://openalex.org/W4224267514","https://openalex.org/W4226278401","https://openalex.org/W4281485151","https://openalex.org/W4301206121","https://openalex.org/W4312933868","https://openalex.org/W4365600514","https://openalex.org/W4385245566","https://openalex.org/W4385570204","https://openalex.org/W4386071687","https://openalex.org/W6638319203","https://openalex.org/W6765779288","https://openalex.org/W6791353385","https://openalex.org/W6810738896","https://openalex.org/W6838639034"],"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/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4225922023"],"abstract_inverted_index":{"Text-to-image":[0],"generation":[1,15],"and":[2,44,57,74,172],"text-guided":[3],"image":[4,14,173],"manipulation":[5],"have":[6,25],"received":[7],"considerable":[8],"attention":[9],"in":[10,27,40],"the":[11,18,31,34,41,50,54,58,69,84,94,106,109,113,124,142,147,150,162,178],"field":[12],"of":[13,108,123,149,180],"tasks.":[16],"However,":[17],"mainstream":[19],"evaluation":[20,65,122,159],"methods":[21],"for":[22,77,93,118,177],"these":[23,181],"tasks":[24],"difficulty":[26],"evaluating":[28,49],"whether":[29],"all":[30],"information":[32],"from":[33],"input":[35,55,72,85,114],"text":[36,56,73],"is":[37,88,161],"accurately":[38],"reflected":[39],"generated":[42,59,75,95,110,151],"images,":[43],"they":[45],"mainly":[46],"focus":[47],"on":[48],"overall":[51],"alignment":[52,70,125,144,171],"between":[53,71],"images.":[60,96,152],"This":[61],"paper":[62],"proposes":[63],"new":[64],"metrics":[66],"that":[67,156,165],"assess":[68,168],"images":[76,111],"every":[78],"individual":[79],"object.":[80],"Firstly,":[81],"according":[82],"to":[83,90,104,112,127,138],"text,":[86,115],"chatGPT":[87],"utilized":[89],"produce":[91],"questions":[92],"After":[97],"that,":[98],"we":[99,132],"use":[100,133],"Visual":[101],"Question":[102],"Answering(VQA)":[103],"measure":[105],"relevance":[107],"which":[116],"allows":[117],"a":[119],"more":[120],"detailed":[121],"compared":[126],"existing":[128],"methods.":[129],"In":[130],"addition,":[131],"Non-Reference":[134],"Image":[135],"Quality":[136],"Assessment(NR-IQA)":[137],"evaluate":[139],"not":[140],"only":[141],"text-image":[143,170],"but":[145],"also":[146],"quality":[148,174],"Experimental":[153],"results":[154],"show":[155],"our":[157],"proposed":[158],"approach":[160],"superior":[163],"metric":[164],"can":[166],"simultaneously":[167],"finer":[169],"while":[175],"allowing":[176],"adjustment":[179],"ratios.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}