{"id":"https://openalex.org/W4416250129","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228586","title":"CLIP-Enhanced Linear Alignment for AI-Generated Image Detection Using Latent Cross-Attention","display_name":"CLIP-Enhanced Linear Alignment for AI-Generated Image Detection Using Latent Cross-Attention","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250129","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228586"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Yanxi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxi Wang","raw_affiliation_strings":["Dalian University of Technology,School of Computer Science and Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Computer Science and Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101735661","display_name":"Tao Sun","orcid":"https://orcid.org/0000-0002-9609-6590"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Sun","raw_affiliation_strings":["Dalian University of Technology,School of Innovation and Entrepreneurship,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Innovation and Entrepreneurship,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39131849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3808000087738037,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3808000087738037,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.21649999916553497,"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":0.0982000008225441,"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/leverage","display_name":"Leverage (statistics)","score":0.652999997138977},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6183000206947327},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.43140000104904175},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41940000653266907},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3817000091075897},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.37560001015663147},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.3686999976634979},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3601999878883362}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7466999888420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355999946594238},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.652999997138977},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6183000206947327},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43860000371932983},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.43140000104904175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":20,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2962793481","https://openalex.org/W3012472557","https://openalex.org/W3034864980","https://openalex.org/W3035574324","https://openalex.org/W3096831136","https://openalex.org/W3136675246","https://openalex.org/W3199003182","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4386071953","https://openalex.org/W4386075803","https://openalex.org/W4386075856","https://openalex.org/W4390872297","https://openalex.org/W4390873235","https://openalex.org/W4394597718","https://openalex.org/W4402716434","https://openalex.org/W4402727598"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,25,65,70,93,98,129,152,166,171,178,186,197,201,213,217],"rapid":[2],"development":[3],"of":[4,28,57,73,125,131,181,226,232],"generative":[5],"models,":[6],"it":[7],"has":[8],"become":[9],"increasingly":[10],"challenging":[11],"for":[12,51,155,190],"humans":[13],"to":[14,24,39,67,79,96,112,128,150,204],"distinguish":[15],"between":[16],"AI-generated":[17,29,33],"and":[18,54,146,228],"real":[19,142],"images,":[20,143,145],"which":[21],"may":[22],"lead":[23],"rampant":[26],"spread":[27],"misinformation.":[30],"Therefore,":[31],"detecting":[32],"images":[34],"is":[35],"a":[36,48,88,139],"critical":[37],"task":[38],"address":[40],"this":[41,44,81,84],"issue.":[42],"In":[43],"work,":[45],"we":[46,63,86,136,163],"propose":[47,68],"two-stage":[49],"method":[50,208],"Real/Fake":[52,61,119],"detection":[53,56,134,192],"local":[55,133,158,161,182,191],"manipulated":[58,144,153,214],"images.":[59],"For":[60,160],"detection,":[62,120,162],"are":[64],"first":[66,94,172],"rearranging":[69],"spatial":[71,105,168,188],"features":[72,169,189],"large-scale":[74],"pre-trained":[75,99],"multimodal":[76],"model":[77,103],"encoders":[78],"achieve":[80],"goal.":[82],"To":[83],"end,":[85],"introduce":[87,165],"linear":[89],"alignment":[90],"module":[91],"in":[92,118,196,216],"stage":[95,173,180],"fine-tune":[97],"model.":[100],"The":[101],"fine-tuned":[102],"produces":[104],"distributions":[106],"with":[107,223],"clearer":[108],"decision":[109],"boundaries":[110],"compared":[111],"other":[113,205],"methods,":[114,206],"demonstrating":[115],"state-of-the-art":[116,221],"performance":[117,222],"achieving":[121,220],"an":[122,224,229],"average":[123],"accuracy":[124],"89.8%.":[126],"Due":[127],"lack":[130],"high-quality":[132],"data,":[135],"have":[137],"created":[138],"dataset":[140],"comprising":[141],"corresponding":[147],"masks":[148],"(used":[149],"identify":[151],"regions)":[154],"research":[156],"on":[157],"detection.":[159,183],"innovatively":[164],"rearranged":[167,187],"from":[170],"as":[174,200],"auxiliary":[175],"conditions":[176],"into":[177],"second":[179],"We":[184],"leverage":[185],"by":[193],"employing":[194],"cross-attention":[195],"latent":[198],"space":[199],"backbone.":[202],"Compared":[203],"our":[207],"can":[209],"more":[210],"accurately":[211],"localize":[212],"regions":[215],"source":[218],"image,":[219],"IoU":[225],"61.5%":[227],"F1":[230],"score":[231],"71.2%.":[233]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}