{"id":"https://openalex.org/W4393148548","doi":"https://doi.org/10.1609/aaai.v38i5.28245","title":"ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining","display_name":"ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393148548","doi":"https://doi.org/10.1609/aaai.v38i5.28245"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i5.28245","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28245","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28245/28485","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/28245/28485","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012042767","display_name":"Dezhi Peng","orcid":"https://orcid.org/0000-0002-3263-3449"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhi Peng","raw_affiliation_strings":["South China University of Technology\nINTSIG-SCUT Joint Lab of Document Image Analysis and Recognition"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology\nINTSIG-SCUT Joint Lab of Document Image Analysis and Recognition","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037101589","display_name":"Chongyu Liu","orcid":"https://orcid.org/0000-0003-2516-926X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongyu Liu","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389396","display_name":"Yuliang Liu","orcid":"https://orcid.org/0000-0002-3037-173X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuliang Liu","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080674767","display_name":"Lianwen Jin","orcid":"https://orcid.org/0000-0002-5456-0957"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianwen Jin","raw_affiliation_strings":["South China University of Technology\nSCUT-Zhuhai Institute of Modern Industrial Innovation\nINTSIG-SCUT Joint Lab of Document Image Analysis and Recognition"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology\nSCUT-Zhuhai Institute of Modern Industrial Innovation\nINTSIG-SCUT Joint Lab of Document Image Analysis and Recognition","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2671,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.76037483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"38","issue":"5","first_page":"4468","last_page":"4477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9821000099182129,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9821000099182129,"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":0.9726999998092651,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9114000201225281,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/computer-vision","display_name":"Computer vision","score":0.5858001708984375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5091592669487},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49301621317863464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4467134475708008},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.33592116832733154},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23130038380622864},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.22482502460479736},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07875192165374756}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5858001708984375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5091592669487},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49301621317863464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4467134475708008},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33592116832733154},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23130038380622864},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.22482502460479736},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07875192165374756}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v38i5.28245","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28245","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28245/28485","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"},{"id":"pmh:oai:ojs.aaai.org:article/28245","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/28245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i5.28245","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28245","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28245/28485","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":0.6700000166893005,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G2085879599","display_name":null,"funder_award_id":"2022YFC3301703","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6852825479","display_name":null,"funder_award_id":"61936003","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"},{"id":"https://openalex.org/F4320323059","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4393148548.pdf"},"referenced_works_count":89,"referenced_works":["https://openalex.org/W2008806374","https://openalex.org/W2108598243","https://openalex.org/W2125389028","https://openalex.org/W2144554289","https://openalex.org/W2146751553","https://openalex.org/W2194775991","https://openalex.org/W2605982830","https://openalex.org/W2785383245","https://openalex.org/W2884959301","https://openalex.org/W2896457183","https://openalex.org/W2963005009","https://openalex.org/W2963647456","https://openalex.org/W2967615747","https://openalex.org/W2972866811","https://openalex.org/W2995942257","https://openalex.org/W2996685953","https://openalex.org/W3003218881","https://openalex.org/W3003433862","https://openalex.org/W3010428518","https://openalex.org/W3016138282","https://openalex.org/W3030520226","https://openalex.org/W3035679705","https://openalex.org/W3082245115","https://openalex.org/W3094502228","https://openalex.org/W3100936573","https://openalex.org/W3104631613","https://openalex.org/W3104953317","https://openalex.org/W3116489684","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3139587317","https://openalex.org/W3160284783","https://openalex.org/W3162234211","https://openalex.org/W3170544306","https://openalex.org/W3170874841","https://openalex.org/W3175515048","https://openalex.org/W3179897446","https://openalex.org/W3192658445","https://openalex.org/W3193700193","https://openalex.org/W3194722168","https://openalex.org/W3204182250","https://openalex.org/W3211490618","https://openalex.org/W3213555225","https://openalex.org/W4213019189","https://openalex.org/W4214633470","https://openalex.org/W4214636423","https://openalex.org/W4225106329","https://openalex.org/W4283821822","https://openalex.org/W4286750974","https://openalex.org/W4287324101","https://openalex.org/W4289751996","https://openalex.org/W4293518729","https://openalex.org/W4304091583","https://openalex.org/W4306704603","https://openalex.org/W4306987814","https://openalex.org/W4312349930","https://openalex.org/W4312528217","https://openalex.org/W4312646899","https://openalex.org/W4312804044","https://openalex.org/W4313038702","https://openalex.org/W4313156423","https://openalex.org/W4319300528","https://openalex.org/W4321232185","https://openalex.org/W4322746719","https://openalex.org/W4327717010","https://openalex.org/W4367315935","https://openalex.org/W4385245566","https://openalex.org/W4385696635","https://openalex.org/W4386453743","https://openalex.org/W6604801084","https://openalex.org/W6652761251","https://openalex.org/W6676297131","https://openalex.org/W6687483927","https://openalex.org/W6736305252","https://openalex.org/W6737717365","https://openalex.org/W6756441975","https://openalex.org/W6760808182","https://openalex.org/W6766668266","https://openalex.org/W6772004348","https://openalex.org/W6773500736","https://openalex.org/W6774577581","https://openalex.org/W6778485988","https://openalex.org/W6782830577","https://openalex.org/W6803870738","https://openalex.org/W6803924480","https://openalex.org/W6841110117","https://openalex.org/W6848334058","https://openalex.org/W6849290737","https://openalex.org/W6849617936"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Scene":[0],"text":[1,7,25,37,65,126,147,185],"removal":[2],"(STR)":[3],"aims":[4],"at":[5,218],"replacing":[6],"strokes":[8],"in":[9,28],"natural":[10],"scenes":[11],"with":[12,115,161],"visually":[13],"coherent":[14],"backgrounds.":[15],"Recent":[16],"STR":[17,42,167,213],"approaches":[18],"rely":[19],"on":[20,145,166],"iterative":[21],"refinements":[22],"or":[23],"explicit":[24],"masks,":[26],"resulting":[27],"high":[29],"complexity":[30],"and":[31,99,118,128,143,150,172,194],"sensitivity":[32],"to":[33,80,111,179,211],"the":[34,48,85,89,93,104,108,112,141,146,191,197,207,212],"accuracy":[35],"of":[36,50,196,209],"localization.":[38],"Moreover,":[39],"most":[40],"existing":[41],"methods":[43],"adopt":[44],"convolutional":[45],"architectures":[46],"while":[47,103],"potential":[49],"vision":[51],"Transformers":[52],"(ViTs)":[53],"remains":[54],"largely":[55],"unexplored.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,130,188],"propose":[61,131],"a":[62,70,132,169],"simple-yet-effective":[63],"ViT-based":[64,198],"eraser,":[66],"dubbed":[67],"ViTEraser.":[68],"Following":[69],"concise":[71],"encoder-decoder":[72,199],"framework,":[73],"ViTEraser":[74,123,160],"can":[75],"easily":[76],"incorporate":[77],"various":[78],"ViTs":[79],"enhance":[81],"long-range":[82],"modeling.":[83],"Specifically,":[84],"encoder":[86,142],"hierarchically":[87],"maps":[88],"input":[90],"image":[91,114,152],"into":[92,206],"hidden":[94,109],"space":[95],"through":[96],"ViT":[97,116,210],"blocks":[98,117],"patch":[100,119],"embedding":[101],"layers,":[102],"decoder":[105,144],"gradually":[106],"upsamples":[107],"features":[110],"text-erased":[113],"splitting":[120],"layers.":[121],"As":[122],"implicitly":[124],"integrates":[125],"localization":[127],"inpainting,":[129],"novel":[133],"end-to-end":[134],"pretraining":[135],"method,":[136],"termed":[137],"SegMIM,":[138],"which":[139,202],"focuses":[140],"box":[148],"segmentation":[149],"masked":[151],"modeling":[153],"tasks,":[154,181],"respectively.":[155],"Experimental":[156],"results":[157],"demonstrate":[158],"that":[159],"SegMIM":[162],"achieves":[163],"state-of-the-art":[164],"performance":[165],"by":[168],"substantial":[170],"margin":[171],"exhibits":[173],"strong":[174],"generalization":[175],"ability":[176],"when":[177],"extended":[178],"other":[180],"e.g.,":[182],"tampered":[183],"scene":[184],"detection.":[186],"Furthermore,":[187],"comprehensively":[189],"explore":[190],"architecture,":[192],"pretraining,":[193],"scalability":[195],"for":[200],"STR,":[201],"provides":[203],"deep":[204],"insights":[205],"application":[208],"field.":[214],"Code":[215],"is":[216],"available":[217],"https://github.com/shannanyinxiang/ViTEraser.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}