{"id":"https://openalex.org/W4403791462","doi":"https://doi.org/10.1145/3664647.3680939","title":"T2I-Scorer: Quantitative Evaluation on Text-to-Image Generation via Fine-Tuned Large Multi-Modal Models","display_name":"T2I-Scorer: Quantitative Evaluation on Text-to-Image Generation via Fine-Tuned Large Multi-Modal Models","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791462","doi":"https://doi.org/10.1145/3664647.3680939"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5014879869","display_name":"Haoning Wu","orcid":"https://orcid.org/0000-0001-8642-8101"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Haoning Wu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102656080","display_name":"Xiele Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiele Wu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002451902","display_name":"Chunyi Li","orcid":"https://orcid.org/0009-0007-0634-1710"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyi Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101797192","display_name":"Zicheng Zhang","orcid":"https://orcid.org/0000-0002-7247-7938"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zicheng Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016944093","display_name":"Chaofeng Chen","orcid":"https://orcid.org/0000-0001-6137-5162"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chaofeng Chen","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087407889","display_name":"Xiaohong Liu","orcid":"https://orcid.org/0000-0001-6377-4730"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohong Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403129","display_name":"Weisi Lin","orcid":"https://orcid.org/0000-0001-9866-1947"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weisi Lin","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5014879869"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.7873,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73936111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3676","last_page":"3685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9969000220298767,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9969000220298767,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9958000183105469,"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":0.9940000176429749,"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/modal","display_name":"Modal","score":0.7634999752044678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7491492033004761},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5526663064956665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4261648654937744},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0754866898059845}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7634999752044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491492033004761},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5526663064956665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4261648654937744},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0754866898059845},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2102166818","https://openalex.org/W2897228451","https://openalex.org/W2905544033","https://openalex.org/W2981852735","https://openalex.org/W3035595647","https://openalex.org/W3103635814","https://openalex.org/W3135479537","https://openalex.org/W4214745154","https://openalex.org/W4288089799","https://openalex.org/W4312818079","https://openalex.org/W4312933868","https://openalex.org/W4386076169","https://openalex.org/W4386211581","https://openalex.org/W4387010079","https://openalex.org/W4387068132","https://openalex.org/W4388555312","https://openalex.org/W4401990587","https://openalex.org/W4402671992","https://openalex.org/W4403757510"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Text-to-image":[0],"(T2I)":[1],"generation":[2,230],"is":[3,36,134],"a":[4,37,41,102,221],"pivotal":[5],"and":[6,27,43,136,140,194,206,240],"core":[7],"interest":[8],"within":[9],"the":[10,17,58,65,73,82,100,115,131,147,175,188,195,215,226,233],"realm":[11],"of":[12,20,40,54,67,84,167,228],"AI":[13],"content":[14],"generation.":[15],"Amid":[16],"swift":[18],"advancements":[19],"both":[21,203],"open-source":[22],"(such":[23],"as":[24,129,220],"Stable":[25],"Diffusion)":[26],"proprietary":[28],"(for":[29],"example,":[30],"DALLE,":[31],"MidJourney)":[32],"T2I":[33,90,112,126,162,169,229],"models,":[34],"there":[35],"notable":[38],"absence":[39],"comprehensive":[42],"robust":[44],"quantitative":[45],"framework":[46],"for":[47,88,111,142],"evaluating":[48],"their":[49],"output":[50],"quality.":[51],"Traditional":[52],"methods":[53],"quality":[55,91,150,205],"assessment":[56,92],"overlook":[57],"textual":[59],"prompts":[60,78],"when":[61],"judging":[62],"images;":[63],"meanwhile,":[64],"advent":[66],"large":[68],"multi-modal":[69],"models":[70,87,231],"(LMMs)":[71],"introduces":[72],"capability":[74],"to":[75,125,145,185,224],"incorporate":[76],"text":[77],"in":[79,232],"evaluations,":[80],"yet":[81],"challenge":[83],"fine-tuning":[85,109],"these":[86],"precise":[89],"remains":[93],"unresolved.":[94],"In":[95],"our":[96],"study,":[97],"we":[98,118,178],"introduce":[99],"T2I-Scorer,":[101],"novel":[103],"two-stage":[104],"training":[105,183],"methodology":[106],"aimed":[107],"at":[108],"LMMs":[110],"evaluation.":[113,127],"For":[114,174],"first":[116,153],"stage,":[117,177],"collect":[119],"397K":[120],"GPT-4V-labeled":[121],"question-answer":[122],"pairs":[123],"related":[124],"Termed":[128],"T2I-ITD,":[130],"pseudo-labeled":[132],"dataset":[133],"analyzed":[135],"examined":[137],"by":[138],"human,":[139],"used":[141],"instruction":[143],"tuning":[144],"improve":[146],"LMM's":[148],"low-level":[149],"perception.":[151],"The":[152],"stage":[154],"model,":[155],"T2I-Scorer-IT,":[156],"has":[157],"reached":[158],"superior":[159],"accuracy":[160,201],"on":[161,202],"evaluation":[163],"than":[164],"all":[165],"kinds":[166],"existing":[168],"metrics":[170,217],"under":[171],"zero-shot":[172],"settings.":[173],"second":[176],"define":[179],"an":[180],"explicit":[181],"multi-task":[182],"scheme":[184],"further":[186],"align":[187],"LMM":[189],"with":[190,210],"human":[191],"opinion":[192],"scores,":[193],"fine-tuned":[196],"T2I-Scorer":[197],"can":[198,218],"reach":[199],"state-of-the-art":[200],"image":[204],"image-text":[207],"alignment":[208],"perspectives":[209],"significant":[211],"improvements.":[212],"We":[213,235],"anticipate":[214],"proposed":[216],"serve":[219],"reliable":[222],"metric":[223],"gauge":[225],"ability":[227],"future.":[234],"will":[236],"make":[237],"code,":[238],"data,":[239],"weights":[241],"publicly":[242],"available.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}