{"id":"https://openalex.org/W7147506984","doi":"https://doi.org/10.48550/arxiv.2603.28613","title":"TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark","display_name":"TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7147506984","doi":"https://doi.org/10.48550/arxiv.2603.28613"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.28613","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28613","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.28613","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069780111","display_name":"Hannes Mareen","orcid":"https://orcid.org/0000-0002-0660-3190"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mareen, Hannes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018338482","display_name":"Dimitrios Karageorgiou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karageorgiou, Dimitrios","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132602675","display_name":"Paschalis Giakoumoglou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giakoumoglou, Paschalis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066816962","display_name":"Peter Lambert","orcid":"https://orcid.org/0000-0001-5313-4158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lambert, Peter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132696930","display_name":"Symeon Papadopoulos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Papadopoulos, Symeon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048527990","display_name":"Glenn Van Wallendael","orcid":"https://orcid.org/0000-0001-9530-3466"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Van Wallendael, Glenn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.6538000106811523,"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":0.6538000106811523,"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":0.2971999943256378,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.007600000128149986,"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/inpainting","display_name":"Inpainting","score":0.958899974822998},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6425999999046326},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.631600022315979},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6126000285148621},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5530999898910522},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45809999108314514},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.3880000114440918}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.958899974822998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282999753952026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6888999938964844},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6425999999046326},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.631600022315979},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5530999898910522},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47360000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.3880000114440918},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.33730000257492065},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28060001134872437},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.28613","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28613","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.28613","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28613","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6165446639060974,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"AI":[1],"has":[2],"made":[3],"text-guided":[4,26,102],"inpainting":[5,27,70,103,223],"a":[6,16,106,136],"powerful":[7],"image":[8,33,54,196,226],"editing":[9],"tool,":[10],"but":[11,44,63],"at":[12,231],"the":[13,74,114,131,218],"same":[14],"time":[15],"growing":[17],"challenge":[18],"for":[19],"media":[20],"forensics.":[21],"Existing":[22],"benchmarks,":[23],"including":[24,143],"our":[25],"forgery":[28,34],"(TGIF)":[29],"dataset,":[30,133],"show":[31,156],"that":[32,97,157,194],"localization":[35,78,174],"(IFL)":[36],"methods":[37,57,146,162],"can":[38,58,199],"localize":[39],"manipulations":[40],"in":[41,47,79,101],"spliced":[42],"images":[43,62,81,149],"struggle":[45],"not":[46],"fully":[48,60],"regenerated":[49,61],"(FR)":[50],"images,":[51,177],"while":[52,171],"synthetic":[53],"detection":[55],"(SID)":[56],"detect":[59],"cannot":[64],"perform":[65],"localization.":[66],"With":[67],"new":[68,215],"generative":[69,151,187],"models":[71],"emerging":[72],"and":[73,85,104,141,150,160,211,224],"open":[75],"problem":[76],"of":[77,95,109],"FR":[80,148,176],"remaining,":[82],"updated":[83,209],"datasets":[84],"benchmarks":[86],"are":[87],"needed.":[88],"We":[89],"introduce":[90],"TGIF2,":[91],"an":[92,208],"extended":[93],"version":[94],"TGIF,":[96],"captures":[98],"recent":[99],"advances":[100],"enables":[105,214],"deeper":[107],"analysis":[108],"forensic":[110,137,191,202],"robustness.":[111],"TGIF2":[112,132,206,228],"augments":[113],"original":[115],"dataset":[116,210],"with":[117,126,179],"edits":[118],"generated":[119],"by":[120,221],"FLUX.1":[121,165],"models,":[122],"as":[123,125],"well":[124],"random":[127,180],"non-semantic":[128,181],"masks.":[129],"Using":[130],"we":[134],"conduct":[135],"evaluation":[138,178],"spanning":[139],"IFL":[140,145,159],"SID,":[142],"fine-tuning":[144,172],"on":[147,164,175],"super-resolution":[152,188],"attacks.":[153],"Our":[154],"experiments":[155],"both":[158],"SID":[161],"degrade":[163],"manipulations,":[166],"highlighting":[167],"limited":[168],"generalization.":[169],"Additionally,":[170],"improves":[173],"masks":[182],"reveals":[183],"object":[184],"bias.":[185],"Furthermore,":[186],"significantly":[189],"weakens":[190],"traces,":[192],"demonstrating":[193],"common":[195],"enhancement":[197],"operations":[198],"undermine":[200],"current":[201],"pipelines.":[203],"In":[204],"summary,":[205],"provides":[207],"benchmark,":[212],"which":[213],"insights":[216],"into":[217],"challenges":[219],"posed":[220],"modern":[222],"AI-based":[225],"enhancements.":[227],"is":[229],"available":[230],"https://github.com/IDLabMedia/tgif-dataset.":[232]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2026-04-02T00:00:00"}