{"id":"https://openalex.org/W7224869743","doi":"https://doi.org/10.1109/ubmk71847.2026.11745408","title":"ConvNeXt\u2013ViT Cross-Attention Fusion: Bridging Local Texture and Global Semantics for AI-Generated Image Detection","display_name":"ConvNeXt\u2013ViT Cross-Attention Fusion: Bridging Local Texture and Global Semantics for AI-Generated Image Detection","publication_year":2026,"publication_date":"2026-09-01","ids":{"openalex":"https://openalex.org/W7224869743","doi":"https://doi.org/10.1109/ubmk71847.2026.11745408"},"language":"en","primary_location":{"id":"doi:10.1109/ubmk71847.2026.11745408","doi":"https://doi.org/10.1109/ubmk71847.2026.11745408","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ubmk71847.2026.11745408","pdf_url":null,"source":{"id":"https://openalex.org/S4306498178","display_name":"International Conference on Computer Science and Engineering (UBMK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 11th International Conference on Computer Science and Engineering (UBMK)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/ubmk71847.2026.11745408","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048298541","display_name":"\u00d6mer Durmu\u015f","orcid":"https://orcid.org/0000-0003-1529-2758","observed_orcids":["https://orcid.org/0000-0003-1529-2758"]},"institutions":[{"id":"https://openalex.org/I4210115931","display_name":"Samsun University","ror":"https://ror.org/02brte405","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210115931"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"\u00d6mer Durmu\u015f","raw_affiliation_strings":["Samsun University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsun University","institution_ids":["https://openalex.org/I4210115931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032228389","display_name":"Kaz\u0131m K\u0131l\u0131\u00e7","orcid":"https://orcid.org/0000-0003-2168-1338","observed_orcids":["https://orcid.org/0000-0003-2168-1338"]},"institutions":[{"id":"https://openalex.org/I4210115931","display_name":"Samsun University","ror":"https://ror.org/02brte405","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210115931"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Kaz\u0131m K\u0131l\u0131\u00e7","raw_affiliation_strings":["Samsun University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsun University","institution_ids":["https://openalex.org/I4210115931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049433832","display_name":"Emel Soylu","orcid":"https://orcid.org/0000-0003-2774-9778","observed_orcids":["https://orcid.org/0000-0003-2774-9778"]},"institutions":[{"id":"https://openalex.org/I4210115931","display_name":"Samsun University","ror":"https://ror.org/02brte405","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210115931"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Emel Soylu","raw_affiliation_strings":["Samsun University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsun University","institution_ids":["https://openalex.org/I4210115931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077647596","display_name":"Muammer T\u00fcrko\u011flu","orcid":"https://orcid.org/0000-0002-2377-4979","observed_orcids":["https://orcid.org/0000-0002-2377-4979"]},"institutions":[{"id":"https://openalex.org/I4210115931","display_name":"Samsun University","ror":"https://ror.org/02brte405","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210115931"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Muammer T\u00fcrko\u011flu","raw_affiliation_strings":["Samsun University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsun University","institution_ids":["https://openalex.org/I4210115931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066969369","display_name":"Zafer C\u00f6mert","orcid":"https://orcid.org/0000-0001-5256-7648","observed_orcids":["https://orcid.org/0000-0001-5256-7648"]},"institutions":[{"id":"https://openalex.org/I4210115931","display_name":"Samsun University","ror":"https://ror.org/02brte405","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210115931"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Zafer C\u00f6mert","raw_affiliation_strings":["Samsun University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsun University","institution_ids":["https://openalex.org/I4210115931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210115931"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"414","last_page":"419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/ai-generated-image-detection","display_name":"AI-generated image detection","score":0.9819999933242798},{"id":"https://openalex.org/keywords/deepfakes","display_name":"deepfakes","score":0.6029999852180481},{"id":"https://openalex.org/keywords/cross-attention-fusion","display_name":"cross-attention fusion","score":0.7900000214576721},{"id":"https://openalex.org/keywords/convnext","display_name":"ConvNeXt","score":0.9340000152587891},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.6940000057220459},{"id":"https://openalex.org/keywords/bidirectional-cross-attention","display_name":"bidirectional cross-attention","score":0.9279999732971191},{"id":"https://openalex.org/keywords/multimedia-forensics","display_name":"multimedia forensics","score":0.7670000195503235},{"id":"https://openalex.org/keywords/model-efficiency","display_name":"model efficiency","score":0.48399999737739563}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6360999941825867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5849999785423279},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5727999806404114},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41839998960494995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.3662000000476837},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.36559998989105225},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.35530000925064087},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.33000001311302185},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2833000123500824},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2671999931335449}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ubmk71847.2026.11745408","doi":"https://doi.org/10.1109/ubmk71847.2026.11745408","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ubmk71847.2026.11745408","pdf_url":null,"source":{"id":"https://openalex.org/S4306498178","display_name":"International Conference on Computer Science and Engineering (UBMK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 11th International Conference on Computer Science and Engineering (UBMK)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/ubmk71847.2026.11745408","doi":"https://doi.org/10.1109/ubmk71847.2026.11745408","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ubmk71847.2026.11745408","pdf_url":null,"source":{"id":"https://openalex.org/S4306498178","display_name":"International Conference on Computer Science and Engineering (UBMK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 11th International Conference on Computer Science and Engineering (UBMK)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W4312443924","https://openalex.org/W4387140156","https://openalex.org/W4390189958","https://openalex.org/W4395661501","https://openalex.org/W4401203256","https://openalex.org/W4402915983","https://openalex.org/W4405021796","https://openalex.org/W4405736291","https://openalex.org/W4405778887","https://openalex.org/W4412810251","https://openalex.org/W4414810806","https://openalex.org/W4416381394","https://openalex.org/W7124134169","https://openalex.org/W7128592463","https://openalex.org/W7133207051"],"related_works":["https://openalex.org/W7082440400","https://openalex.org/W7204154023","https://openalex.org/W7167928831","https://openalex.org/W7211913400","https://openalex.org/W7106216082","https://openalex.org/W7224969328","https://openalex.org/W7223671243","https://openalex.org/W7202124844","https://openalex.org/W7168163527","https://openalex.org/W7169604787"],"abstract_inverted_index":{"The":[0,154],"growing":[1],"realism":[2],"of":[3,14,87,161,166,171,209,223],"GAN-":[4],"and":[5,40,55,107,119,136,146,168,182],"diffusion-based":[6],"image":[7,248],"generators":[8],"has":[9,25],"made":[10],"the":[11,82,88,102,174,183,198,214,220,224],"automatic":[12],"detection":[13],"AI-generated":[15,79,247],"images":[16,80],"a":[17,94,115,123,142,158,169,202,241],"pressing":[18],"problem":[19],"in":[20],"multimedia":[21],"forensics.":[22],"Prior":[23],"work":[24],"shown":[26],"that":[27,208,213,236],"convolutional":[28],"neural":[29],"networks":[30],"(CNNs)":[31],"are":[32,48,112],"well":[33],"suited":[34],"to":[35,77,207],"capturing":[36],"local":[37,105],"pixel-level":[38],"artifacts":[39],"high-frequency":[41],"texture":[42],"anomalies.":[43],"However,":[44],"Vision":[45],"Transformers":[46],"(ViTs)":[47],"better":[49],"at":[50],"simulating":[51],"long-range":[52],"semantic":[53],"structure":[54],"global":[56,108],"context.":[57],"Combining":[58],"these":[59],"two":[60,196],"strengths":[61],"through":[62,122],"dynamic,":[63],"bidirectional":[64,124,237],"interaction\u2014rather":[65],"than":[66,228],"static":[67],"feature":[68],"concatenation\u2014has,":[69],"however,":[70],"received":[71],"comparatively":[72],"little":[73],"attention.":[74],"In":[75,101],"order":[76],"detect":[78],"on":[81,141],"Stable":[83],"Diffusion":[84],"v1.5":[85],"subset":[86,145],"GenImage":[89],"benchmark,":[90],"this":[91],"paper":[92],"suggests":[93],"Bidirectional":[95],"Cross-Attention":[96],"CNN\u2013Transformer":[97],"Hybrid":[98],"(ConvNeXt\u2013ViT)":[99],"architecture.":[100],"proposed":[103,155,199],"model,":[104],"(ConvNeXt)":[106],"(ViT)":[109],"token":[110],"representations":[111],"projected":[113],"into":[114],"shared":[116],"embedding":[117],"space":[118],"mutually":[120],"enriched":[121],"cross-attention":[125,238],"mechanism":[126,226],"before":[127],"classification.":[128],"Five":[129],"widely":[130],"used":[131],"architectures\u2014ResNet50,":[132],"EfficientNet-B4,":[133],"ConvNeXt-Tiny,":[134],"ViT-Tiny,":[135],"MobileNetV3-Large\u2014were":[137],"trained":[138],"from":[139,219,229],"scratch":[140],"balanced":[143],"24,000-image":[144],"evaluated":[147],"as":[148],"baselines":[149,185],"under":[150],"an":[151,164],"identical":[152,206],"protocol.":[153],"model":[156,200,231],"reached":[157],"test":[159],"accuracy":[160,180],"95.85":[162],"percent,":[163],"F1-score":[165],"0.9585,":[167],"ROC-AUC":[170],"0.9914,":[172],"outperforming":[173],"strongest":[175],"baseline":[176],"(ResNet50)":[177],"by":[178,186],"3.25":[179],"points":[181],"remaining":[184],"9.0\u20139.6":[187],"points.":[188],"Efficiency":[189],"analysis":[190],"further":[191],"showed":[192],"that,":[193],"despite":[194],"carrying":[195],"backbones,":[197],"achieved":[201],"batch-processing":[203],"throughput":[204],"nearly":[205],"ConvNeXt-Tiny":[210],"alone,":[211],"indicating":[212],"observed":[215],"gains":[216],"stemmed":[217],"primarily":[218],"architectural":[221],"efficiency":[222,244],"fusion":[225,239],"rather":[227],"increased":[230],"capacity.":[232],"These":[233],"findings":[234],"suggest":[235],"offers":[240],"favorable":[242],"accuracy\u2013":[243],"trade-off":[245],"for":[246],"detection.":[249]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-31T00:00:00"}