{"id":"https://openalex.org/W4415538267","doi":"https://doi.org/10.1145/3746027.3754857","title":"DITL <sup>2</sup> : Dual-Stage Invariance Transfer Learning for Generalizable Document Image Tampering Localization","display_name":"DITL <sup>2</sup> : Dual-Stage Invariance Transfer Learning for Generalizable Document Image Tampering Localization","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538267","doi":"https://doi.org/10.1145/3746027.3754857"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754857","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"Songze Li","orcid":"https://orcid.org/0009-0006-1568-4697"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Songze Li","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, Chile"],"raw_orcid":"https://orcid.org/0009-0006-1568-4697","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, Chile","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101440212","display_name":"Yunfei Guo","orcid":"https://orcid.org/0000-0003-2422-3332"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfei Guo","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2422-3332","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073408438","display_name":"S. Chen","orcid":"https://orcid.org/0000-0001-9140-194X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen Chen","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9140-194X","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365163","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-2613-5451"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2613-5451","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042347681","display_name":"Kaiqing Lin","orcid":"https://orcid.org/0000-0002-5291-4635"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiqing Lin","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5291-4635","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751850","display_name":"Changsheng Chen","orcid":"https://orcid.org/0000-0003-4857-6810"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Chen","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4857-6810","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022939417","display_name":"Haodong Li","orcid":"https://orcid.org/0000-0003-0532-9481"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Li","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0532-9481","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033773467","display_name":"Taiping Yao","orcid":"https://orcid.org/0000-0002-2359-1523"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiping Yao","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2359-1523","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086397952","display_name":"Shouhong Ding","orcid":"https://orcid.org/0000-0002-3175-3553"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouhong Ding","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3175-3553","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28750442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"82","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9998000264167786,"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":0.9998000264167786,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9904999732971191,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.982699990272522,"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/generalization","display_name":"Generalization","score":0.5950000286102295},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5800999999046326},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5059000253677368},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.49149999022483826},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.490200012922287},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44110000133514404},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.40209999680519104},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203999757766724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6427000164985657},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5950000286102295},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5800999999046326},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44110000133514404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4235999882221222},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.36169999837875366},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.34369999170303345},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C77075516","wikidata":"https://www.wikidata.org/wiki/Q6027324","display_name":"Inductive transfer","level":5,"score":0.28850001096725464},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754857","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3520082866","display_name":null,"funder_award_id":"U23B2022, U22B2047 and 62371301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2560026874","https://openalex.org/W2963683323","https://openalex.org/W2981540341","https://openalex.org/W3140970613","https://openalex.org/W4200619815","https://openalex.org/W4312443924","https://openalex.org/W4312815172","https://openalex.org/W4386065512","https://openalex.org/W4390874575","https://openalex.org/W4401047396","https://openalex.org/W4402715936","https://openalex.org/W4402754093","https://openalex.org/W4408198448"],"related_works":[],"abstract_inverted_index":{"Document":[0,71],"Image":[1,72],"Tampering":[2,73],"Localization":[3,74],"(DITL)":[4],"advances":[5],"considerably,":[6],"yet":[7],"achieving":[8,162],"robust":[9],"cross-dataset":[10,169],"generalization":[11],"remains":[12],"a":[13,64,166],"formidable":[14],"challenge":[15],"for":[16,23,70],"practical":[17],"applications.":[18],"Expanding":[19],"existing":[20],"document":[21],"datasets":[22],"training":[24],"is":[25],"labor-intensive,":[26],"making":[27],"it":[28],"appealing":[29],"to":[30,100,114,138,158],"incorporate":[31],"data":[32,156],"from":[33,104,134],"non-document":[34],"domains":[35],"such":[36],"as":[37],"natural":[38,106],"scene":[39,107],"images.":[40],"However,":[41],"domain-specific":[42,102],"variations,":[43],"including":[44],"differences":[45],"in":[46],"color":[47],"distribution":[48],"and":[49,82,96,109],"texture,":[50],"compromise":[51],"the":[52,89,119,124,127,131,135,144],"performance":[53],"of":[54,77,126,146,168],"joint":[55],"training.":[56],"To":[57],"address":[58,139],"this":[59,151],"issue,":[60],"we":[61],"propose":[62],"DITL2,":[63],"Dual-stage":[65],"Invariance":[66,79],"Transfer":[67],"Learning":[68],"framework":[69],"that":[75,150],"consists":[76],"Cross-Domain":[78],"Pre-training":[80],"(CDIP)":[81],"Frequency":[83],"Decoupling":[84],"Parameter":[85],"Adaptation":[86],"(FDPA).":[87],"In":[88,118],"pre-training":[90],"stage,":[91,121],"CDIP":[92],"employs":[93],"style":[94],"transfer":[95],"texture":[97],"consistency":[98],"learning":[99,113],"suppress":[101],"influences":[103],"tampered":[105],"images,":[108],"tampering":[110],"trace":[111],"commonality":[112],"acquire":[115],"domain-invariant":[116],"features.":[117],"fine-tuning":[120],"FDPA":[122],"adapts":[123],"parameters":[125],"pre-trained":[128,136],"model,":[129],"leveraging":[130],"general":[132],"knowledge":[133],"model":[137,160],"DITL":[140],"tasks":[141],"while":[142],"reducing":[143],"risk":[145],"overfitting.":[147],"Experiments":[148],"show":[149],"approach":[152],"effectively":[153],"leverages":[154],"external":[155],"resources":[157],"boost":[159],"performance,":[161],"state-of-the-art":[163],"results":[164],"across":[165],"variety":[167],"settings.":[170]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}