{"id":"https://openalex.org/W7125898275","doi":"https://doi.org/10.1109/smc58881.2025.11343305","title":"ViT-DGA: ViT-Driven Dual-Granularity Architecture for Image Manipulation Localization","display_name":"ViT-DGA: ViT-Driven Dual-Granularity Architecture for Image Manipulation Localization","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125898275","doi":"https://doi.org/10.1109/smc58881.2025.11343305"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124105584","display_name":"Qiang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiang Wu","raw_affiliation_strings":["Shanghai University of Electric Power,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121518745","display_name":"Weimin Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Wei","raw_affiliation_strings":["Shanghai University of Electric Power,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052420658","display_name":"Xueyang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyang Sun","raw_affiliation_strings":["Shanghai University of Electric Power,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121749554","display_name":"Wuyao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wuyao Shi","raw_affiliation_strings":["Shanghai University of Electric Power,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I23632641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5124105584"],"corresponding_institution_ids":["https://openalex.org/I23632641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71537908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1761","last_page":"1767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.5246999859809875,"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":0.5246999859809875,"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":0.1039000004529953,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.04560000076889992,"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/image-manipulation","display_name":"Image manipulation","score":0.7006999850273132},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6693000197410583},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4828999936580658},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4528999924659729},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.40220001339912415},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.37560001015663147},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3741999864578247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494999766349792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7196999788284302},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.7006999850273132},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6693000197410583},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6640999913215637},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4828999936580658},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.37560001015663147},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.28459998965263367},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6204609274864197}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2104116677","https://openalex.org/W2169439181","https://openalex.org/W2518397542","https://openalex.org/W2619748849","https://openalex.org/W2912648825","https://openalex.org/W2948407537","https://openalex.org/W2964146055","https://openalex.org/W3014641072","https://openalex.org/W3027377338","https://openalex.org/W3082623289","https://openalex.org/W3118971208","https://openalex.org/W3136675246","https://openalex.org/W3154575015","https://openalex.org/W3189718486","https://openalex.org/W3191117306","https://openalex.org/W3208354318","https://openalex.org/W4312443924","https://openalex.org/W4312948884","https://openalex.org/W4312981036","https://openalex.org/W4313121508","https://openalex.org/W4385801432","https://openalex.org/W4386075803","https://openalex.org/W4386075856","https://openalex.org/W4391274965","https://openalex.org/W4409365647"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,63,76,85,156,164,170],"development":[2],"of":[3,66,78,87,155],"deep":[4,36],"learning,":[5],"image":[6,38,99,109,136,166,198],"manipulation":[7,39,60,110,137,199],"techniques":[8],"have":[9,42,105],"become":[10],"increasingly":[11],"advanced":[12,124],"and":[13,30,70,112,129],"difficult":[14],"to":[15,18,108,132,148,172,196],"detect,":[16],"leading":[17],"serious":[19],"trust":[20],"crises":[21],"in":[22,97,207],"fields":[23],"such":[24],"as":[25],"news":[26],"reporting,":[27],"judicial":[28],"forensics,":[29],"social":[31],"media.":[32],"In":[33],"recent":[34],"years,":[35],"learning-based":[37],"localization":[40,138,193,200],"methods":[41,48,104,201],"achieved":[43],"significant":[44],"progress.":[45],"Most":[46],"current":[47],"focus":[49],"on":[50,181],"extracting":[51,98],"non-semantic":[52,71,130],"information,":[53],"which":[54],"is":[55,146],"reasonable,":[56],"but":[57,202],"since":[58],"most":[59],"operations":[61],"modify":[62],"semantic":[64,69,128],"content":[65],"images,":[67],"both":[68,127],"information":[72,131],"are":[73],"indispensable.":[74],"Since":[75],"introduction":[77],"Vision":[79],"Transformer":[80,92],"(ViT),":[81],"it":[82],"has":[83],"dominated":[84],"field":[86],"computer":[88],"vision,":[89],"with":[90,123],"its":[91],"architecture":[93],"demonstrating":[94],"powerful":[95],"capabilities":[96],"features.":[100,175],"However,":[101],"few":[102],"ViT-based":[103,160],"been":[106],"applied":[107],"localization,":[111],"their":[113],"performance":[114],"remains":[115],"unsatisfactory.":[116],"Therefore,":[117],"we":[118,177],"combine":[119],"traditional":[120,143],"vision":[121,144],"models":[122],"ViT,":[125],"integrating":[126],"construct":[133],"a":[134,159],"new":[135],"framework":[139],"called":[140],"ViT-DGA.":[141],"The":[142,184],"model":[145,171],"used":[147],"extract":[149],"features":[150],"from":[151],"different":[152],"frequency":[153],"domains":[154],"image,":[157],"while":[158],"intermediate":[161],"layer":[162],"supplements":[163],"original":[165],"features,":[167],"effectively":[168],"guiding":[169],"learn":[173],"multi-perspective":[174],"Additionally,":[176],"conducted":[178],"extensive":[179],"experiments":[180],"various":[182],"datasets.":[183],"results":[185],"demonstrate":[186],"that":[187],"ViT-DGA":[188],"not":[189],"only":[190],"achieves":[191],"superior":[192],"accuracy":[194],"compared":[195],"state-of-the-art":[197],"also":[203],"exhibits":[204],"strong":[205],"robustness":[206],"common":[208],"post-processing":[209],"scenarios.":[210]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}