{"id":"https://openalex.org/W7137988534","doi":"https://doi.org/10.1609/aaai.v40i2.37068","title":"Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework","display_name":"Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137988534","doi":"https://doi.org/10.1609/aaai.v40i2.37068"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i2.37068","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37068","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37068/41030","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37068/41030","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071191307","display_name":"Ziqi Sheng","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Ziqi Sheng","raw_affiliation_strings":["MoE Key Laboratory of Information Technology, School of Computer Science and Engineering, Sun Yat-sen University\nDepartment of Computer and Information Science, University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Information Technology, School of Computer Science and Engineering, Sun Yat-sen University\nDepartment of Computer and Information Science, University of Macau","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129738840","display_name":"Junyan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyan Wu","raw_affiliation_strings":["MoE Key Laboratory of Information Technology, School of Computer Science and Engineering, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Information Technology, School of Computer Science and Engineering, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746745","display_name":"Wei Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lu","raw_affiliation_strings":["MoE Key Laboratory of Information Technology, School of Computer Science and Engineering, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Information Technology, School of Computer Science and Engineering, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129719257","display_name":"Jiantao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jiantao Zhou","raw_affiliation_strings":["Department of Computer and Information Science, University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Macau","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.8899,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97792023,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"40","issue":"2","first_page":"988","last_page":"996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9199000000953674,"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":0.9199000000953674,"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":0.041200000792741776,"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":0.005799999926239252,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.7423999905586243},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6485999822616577},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6485999822616577},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5817000269889832},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5432999730110168},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47699999809265137},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.42879998683929443},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4083000123500824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220999836921692},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7423999905586243},{"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/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6485999822616577},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6485999822616577},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5817000269889832},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3822999894618988},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3352999985218048},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3276999890804291},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2524000108242035},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i2.37068","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37068","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37068/41030","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i2.37068","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37068","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37068/41030","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.48769208788871765,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"},{"score":0.454840749502182,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137988534.pdf","grobid_xml":"https://content.openalex.org/works/W7137988534.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"forgery":[1,27,179],"localization":[2,28,38,83,147,202],"aims":[3],"to":[4,52,97,153,168],"precisely":[5],"identify":[6],"tampered":[7,170],"regions":[8],"within":[9],"images,":[10],"but":[11],"it":[12],"commonly":[13],"depends":[14],"on":[15,183],"costly":[16],"pixel-level":[17,82,146],"annotations.":[18],"To":[19],"alleviate":[20],"this":[21,59],"annotation":[22],"burden,":[23],"weakly":[24],"supervised":[25],"image":[26],"(WSIFL)":[29],"has":[30],"emerged,":[31],"yet":[32],"existing":[33,192],"methods":[34],"still":[35],"achieve":[36],"limited":[37],"performance":[39,197],"as":[40],"they":[41],"mainly":[42],"exploit":[43],"intra-image":[44],"consistency":[45,164],"clues":[46],"and":[47,102,141,201],"lack":[48],"external":[49],"semantic":[50,72],"guidance":[51,155],"compensate":[53],"for":[54,156],"insufficient":[55],"supervision":[56,73],"information.":[57],"In":[58],"paper,":[60],"we":[61,89],"propose":[62],"ViLaCo,":[63],"a":[64,92,161],"vision-language":[65,77,93,112],"collaborative":[66],"reasoning":[67,113],"framework":[68],"that":[69,188],"introduces":[70],"auxiliary":[71],"derived":[74],"from":[75],"pre-trained":[76,107],"models":[78],"(VLMs),":[79],"enabling":[80],"accurate":[81],"using":[84],"only":[85],"image-level":[86,139],"labels.":[87],"Specifically,":[88],"first":[90],"employ":[91],"feature":[94],"modeling":[95],"network":[96,114],"jointly":[98],"extract":[99],"textual":[100],"semantics":[101],"visual":[103],"features":[104,117,171],"by":[105],"leveraging":[106],"VLMs.":[108],"Next,":[109],"an":[110],"adaptive":[111],"aligns":[115],"these":[116,126],"through":[118],"mutual":[119],"interactions,":[120],"producing":[121],"semantically":[122],"aligned":[123],"representations.":[124],"Subsequently,":[125],"representations":[127],"are":[128],"passed":[129],"into":[130],"dual":[131],"prediction":[132],"heads,":[133],"where":[134],"the":[135,142,150,157],"coarse":[136],"head":[137,144],"performs":[138],"classification":[140],"fine":[143],"generates":[145],"masks,":[148],"allowing":[149],"coarse-grained":[151],"task":[152],"provide":[154],"fine-grained":[158],"localization.":[159],"Moreover,":[160],"contrastive":[162],"patch":[163],"module":[165],"is":[166],"introduced":[167],"cluster":[169],"while":[172],"separating":[173],"authentic":[174],"ones,":[175],"facilitating":[176],"more":[177],"reliable":[178],"discrimination.":[180],"Extensive":[181],"experiments":[182],"multiple":[184],"public":[185],"datasets":[186],"demonstrate":[187],"ViLaCo":[189],"substantially":[190],"outperforms":[191],"WSIFL":[193],"methods,":[194],"achieving":[195],"state-of-the-art":[196],"in":[198],"both":[199],"detection":[200],"accuracy.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2026-03-18T00:00:00"}