{"id":"https://openalex.org/W4415343382","doi":"https://doi.org/10.1109/iccv51701.2025.01742","title":"Aigi-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models","display_name":"Aigi-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415343382","doi":"https://doi.org/10.1109/iccv51701.2025.01742"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.02664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047699489","display_name":"Ziyin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyin Zhou","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005841637","display_name":"Yunpeng Luo","orcid":"https://orcid.org/0000-0002-7838-5241"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Luo","raw_affiliation_strings":["Tencent YouTu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084918752","display_name":"Yuanchen Wu","orcid":"https://orcid.org/0000-0003-4079-4725"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchen Wu","raw_affiliation_strings":["Tencent YouTu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103467403","display_name":"Ke Sun","orcid":"https://orcid.org/0000-0001-9759-8018"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Sun","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084510895","display_name":"Jiayi Ji","orcid":"https://orcid.org/0000-0002-9956-6308"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Ji","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074086087","display_name":"Ke Yan","orcid":"https://orcid.org/0000-0002-0766-0576"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Yan","raw_affiliation_strings":["Tencent YouTu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086397952","display_name":"Shouhong Ding","orcid":"https://orcid.org/0000-0002-3175-3553"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouhong Ding","raw_affiliation_strings":["Tencent YouTu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091425569","display_name":"Yunsheng Wu","orcid":"https://orcid.org/0000-0001-7462-1414"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsheng Wu","raw_affiliation_strings":["Tencent YouTu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18746","last_page":"18758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9847000241279602,"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":0.9847000241279602,"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/T10028","display_name":"Topic Modeling","score":0.9516000151634216,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.914900004863739,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6245999932289124},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5774000287055969},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5683000087738037},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4478999972343445},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.414900004863739},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.3889000117778778},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.33730000257492065},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.33169999718666077},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.32519999146461487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827000021934509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6488999724388123},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6245999932289124},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5644000172615051},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.33169999718666077},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.32190001010894775},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.31470000743865967},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.25429999828338623},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.02664","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.02664","pdf_url":"https://arxiv.org/pdf/2507.02664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.02664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.02664","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.02664","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.02664","pdf_url":"https://arxiv.org/pdf/2507.02664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2195152090","display_name":null,"funder_award_id":"U21B2037,U22B2051,U23A20383,U21A20472,62176222,62176223,62176226,62072386,62072387,62072389,62002305,62272401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4310180199","display_name":null,"funder_award_id":"2021J06003,2022J06001","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"development":[2],"of":[3,13,44,51,182,190,205],"AI-generated":[4,16],"content":[5],"(AIGC)":[6],"technology":[7],"has":[8],"led":[9],"to":[10,25],"the":[11,54,72,85,100,168,179,183,187,194,203],"misuse":[12],"highly":[14],"realistic":[15],"images":[17,81],"(AIGI)":[18],"in":[19,53],"spreading":[20],"misinformation,":[21],"posing":[22],"a":[23,42,49,64,87,129,173],"threat":[24],"public":[26],"information":[27],"security.":[28],"Although":[29],"existing":[30],"AIGI":[31,154],"detection":[32,155],"techniques":[33],"are":[34,82],"generally":[35],"effective,":[36],"they":[37],"face":[38],"two":[39],"issues:":[40],"1)":[41],"lack":[43,50],"human-verifiable":[45,158],"explanations,":[46,161],"and":[47,66,84,110,119,141,159],"2)":[48],"generalization":[52,195],"latest":[55],"generation":[56,105],"technology.":[57],"To":[58],"address":[59],"these":[60],"issues,":[61],"we":[62,125,171],"introduce":[63,172],"large-scale":[65],"comprehensive":[67],"dataset,":[68],"Holmes-Set,":[69],"which":[70],"includes":[71],"Holmes-SFTSet,":[73],"an":[74,94],"instruction-tuning":[75],"dataset":[76],"with":[77,186],"explanations":[78,109],"on":[79,199],"whether":[80],"AI-generated,":[83],"Holmes-DPOSet,":[86],"human-aligned":[88,160],"preference":[89,121,143],"dataset.":[90],"Our":[91],"work":[92],"introduces":[93],"efficient":[95],"data":[96,104],"annotation":[97],"method":[98],"called":[99],"Multi-Expert":[101],"Jury,":[102],"enhancing":[103,193],"through":[106],"structured":[107],"MLLM":[108],"quality":[111],"control":[112],"via":[113],"cross-model":[114],"evaluation,":[115],"expert":[116,137,185],"defect":[117],"filtering,":[118],"human":[120],"modification.":[122],"In":[123],"addition,":[124],"propose":[126],"Holmes":[127,145],"Pipeline,":[128],"meticulously":[130],"designed":[131],"three-stage":[132],"training":[133],"framework":[134],"comprising":[135],"visual":[136,184],"pre-training,":[138],"supervised":[139],"fine-tuning,":[140],"direct":[142],"optimization.":[144],"Pipeline":[146],"adapts":[147],"multimodal":[148],"large":[149],"language":[150],"models":[151],"(MLLMs)":[152],"for":[153],"while":[156],"generating":[157],"ultimately":[162],"yielding":[163],"our":[164,206],"model":[165,180],"AIGI-Holmes.":[166,207],"During":[167],"inference":[169],"stage,":[170],"collaborative":[174],"decoding":[175],"strategy":[176],"that":[177],"integrates":[178],"perception":[181],"semantic":[188],"reasoning":[189],"MLLMs,":[191],"further":[192],"capabilities.":[196],"Extensive":[197],"experiments":[198],"three":[200],"benchmarks":[201],"validate":[202],"effectiveness":[204]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-20T00:00:00"}