{"id":"https://openalex.org/W7131898118","doi":"https://doi.org/10.1109/tmm.2026.3668513","title":"Semantic Distribution and Authenticity Discrepancy Alignment for AI-Generated Image Detection","display_name":"Semantic Distribution and Authenticity Discrepancy Alignment for AI-Generated Image Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131898118","doi":"https://doi.org/10.1109/tmm.2026.3668513"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3668513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668513","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5127182050","display_name":"Jiehua Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiehua Zhang","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-0790-9279","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127205870","display_name":"Liang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8437-4824","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127007837","display_name":"Chenggang Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenggang Yan","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1204-0512","affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867597","display_name":"Wei Ke","orcid":"https://orcid.org/0000-0002-2899-0371"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Ke","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100687952","display_name":"Yihong Gong","orcid":"https://orcid.org/0000-0002-1793-5836"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihong Gong","raw_affiliation_strings":["College of Artificial Intelligence, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-1793-5836","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23303722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"5758","last_page":"5768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.21480000019073486,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.21480000019073486,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12080000340938568,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09300000220537186,"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/semantic-feature","display_name":"Semantic feature","score":0.699999988079071},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5756000280380249},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5694000124931335},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5182999968528748},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4754999876022339},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42239999771118164},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.41370001435279846},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.4101000130176544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281000256538391},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.699999988079071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6265000104904175},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4754999876022339},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.4101000130176544},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37610000371932983},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37549999356269836},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.35409998893737793},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C202708506","wikidata":"https://www.wikidata.org/wiki/Q7449050","display_name":"Semantic compression","level":5,"score":0.289000004529953},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3668513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668513","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6358968615531921,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G4536128632","display_name":null,"funder_award_id":"62322211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6408364431","display_name":null,"funder_award_id":"U21B2048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G918142972","display_name":null,"funder_award_id":"62376209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":35,"referenced_works":["https://openalex.org/W2603123944","https://openalex.org/W3012472557","https://openalex.org/W3034577585","https://openalex.org/W3133516147","https://openalex.org/W3154326567","https://openalex.org/W3166466426","https://openalex.org/W4312933868","https://openalex.org/W4313189772","https://openalex.org/W4316660967","https://openalex.org/W4319866156","https://openalex.org/W4385486377","https://openalex.org/W4386071953","https://openalex.org/W4386075954","https://openalex.org/W4386275888","https://openalex.org/W4386790226","https://openalex.org/W4390241320","https://openalex.org/W4390873235","https://openalex.org/W4393148275","https://openalex.org/W4393154086","https://openalex.org/W4394595619","https://openalex.org/W4399418483","https://openalex.org/W4400624794","https://openalex.org/W4402127110","https://openalex.org/W4402671841","https://openalex.org/W4402716164","https://openalex.org/W4402716434","https://openalex.org/W4402727598","https://openalex.org/W4402753859","https://openalex.org/W4402754294","https://openalex.org/W4404002774","https://openalex.org/W4404725432","https://openalex.org/W4406414399","https://openalex.org/W4409149749","https://openalex.org/W4409367167","https://openalex.org/W4413822025"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"models":[1,55,119],"have":[2],"achieved":[3],"remarkable":[4],"success":[5],"in":[6,40,82],"producing":[7],"vivid":[8],"images.":[9,49],"Compared":[10],"with":[11,23],"real":[12],"images,":[13],"generated":[14],"ones":[15],"still":[16],"show":[17],"different":[18,24],"semantic":[19,25,38,43,70,103,126,146,153,166,184,199],"structures":[20,104],"that":[21],"features":[22,127,138,188],"classes":[26],"collapse":[27,73],"as":[28],"a":[29,140],"single":[30],"cluster.":[31],"Pioneer":[32],"works":[33],"leverage":[34],"the":[35,68,75,131,152,165,178,192,198,213,217],"discrepancy":[36,96,173,180],"of":[37,105,128,155,201,216],"structure":[39,154,200],"fixed":[41],"high-level":[42,102],"feature":[44,161,167],"space":[45],"to":[46,58,74,150,176],"identify":[47],"forgery":[48,60,110,137,141,160,182,187],"Nevertheless,":[50],"such":[51],"frozen":[52,132],"pre-trained":[53,69],"representation":[54],"are":[56],"insensitive":[57],"subtle":[59],"traces.":[61],"Meanwhile,":[62],"vanilla":[63],"fine-tuning":[64],"methods":[65],"can":[66],"distort":[67],"knowledge":[71],"and":[72,94,108,120,134,183,196,208],"real-fake":[76],"binary":[77],"distribution,":[78],"losing":[79],"generalization":[80,214],"capability":[81,215],"newly":[83],"emerged":[84],"generative":[85,118],"models.":[86],"In":[87],"this":[88],"paper,":[89],"we":[90,123,144,170],"propose":[91,145],"thesemantic":[92],"distribution":[93,147,162,195],"authenticity":[95,172,179],"alignment":[97,148,174],"algorithm":[98],"(STERM),":[99],"which":[100],"learns":[101],"real-world":[106,156,202],"categories":[107,157],"low-level":[109],"traces":[111],"for":[112],"detecting":[113],"AI-generated":[114],"images":[115,129],"from":[116,189],"unseen":[117],"frameworks.":[121],"Specifically,":[122],"first":[124],"capture":[125],"by":[130,139,158],"CLIP":[133],"further":[135],"extract":[136],"encoder.":[142],"Then,":[143],"(SDA)":[149],"align":[151],"enforcing":[159],"shifting":[163],"towards":[164],"space.":[168],"Next,":[169],"introduce":[171],"(ADA)":[175],"minimize":[177],"between":[181],"features,":[185],"constraining":[186],"collapsing":[190],"into":[191],"source":[193,221],"domain-biased":[194],"learning":[197],"categories.":[203],"Extensive":[204],"experiments":[205],"on":[206],"GAN-based":[207],"diffusion":[209],"model-based":[210],"datasets":[211],"demonstrate":[212],"proposed":[218],"method.":[219],"The":[220],"code":[222],"is":[223],"publicly":[224],"available":[225],"athttps://github.com/freshjh/STERM.":[226]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-02-28T00:00:00"}