{"id":"https://openalex.org/W4415708717","doi":"https://doi.org/10.1109/icme59968.2025.11209904","title":"Global-Local Aware Scene Text Editing","display_name":"Global-Local Aware Scene Text Editing","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708717","doi":"https://doi.org/10.1109/icme59968.2025.11209904"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209904","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035004815","display_name":"Fuxiang Yang","orcid":"https://orcid.org/0000-0001-7252-4207"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuxiang Yang","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033324841","display_name":"Tonghua Su","orcid":"https://orcid.org/0000-0002-8869-1664"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tonghua Su","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031208819","display_name":"Donglin Di","orcid":"https://orcid.org/0000-0002-2270-3378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donglin Di","raw_affiliation_strings":["Li Auto,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Li Auto,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430560","display_name":"Yin Chen","orcid":"https://orcid.org/0000-0002-3351-5065"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Chen","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030966569","display_name":"Xiangqian Wu","orcid":"https://orcid.org/0000-0002-0956-8757"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangqian Wu","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738314","display_name":"Zhongjie Wang","orcid":"https://orcid.org/0000-0002-4925-2941"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjie Wang","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059040724","display_name":"Lei Fan","orcid":"https://orcid.org/0000-0001-9472-7152"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lei Fan","raw_affiliation_strings":["University of New South Wales,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,Sydney,Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6992999911308289,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6992999911308289,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08410000056028366,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.03550000116229057,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/affine-transformation","display_name":"Affine transformation","score":0.5766000151634216},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.534500002861023},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.508899986743927},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4903999865055084},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44209998846054077},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.4092999994754791},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3127000033855438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097000122070312},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.534500002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5338000059127808},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.4092999994754791},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35120001435279846},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2939000129699707},{"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/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2703000009059906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209904","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2603777577","https://openalex.org/W2950689937","https://openalex.org/W2962785568","https://openalex.org/W2963073614","https://openalex.org/W2982148195","https://openalex.org/W3167911358","https://openalex.org/W3199003182","https://openalex.org/W4295935120","https://openalex.org/W4312933868","https://openalex.org/W4382463826","https://openalex.org/W4387185314","https://openalex.org/W4387968659","https://openalex.org/W4402754267","https://openalex.org/W4403791271","https://openalex.org/W4404959550","https://openalex.org/W4406970700"],"related_works":[],"abstract_inverted_index":{"Scene":[0,76],"Text":[1,77],"Editing":[2,78],"(STE)":[3],"involves":[4],"replacing":[5],"text":[6,14,20,58,106,113,130,146,159],"in":[7,57,112,184],"a":[8,95,133],"scene":[9],"image":[10,107,138],"with":[11,88],"new":[12],"target":[13,145,158],"while":[15,118,165],"preserving":[16],"both":[17,185],"the":[18,42,47,129,137,162,194],"original":[19],"style":[21,114,131],"and":[22,33,46,50,61,101,104,123,188,191],"background":[23],"texture.":[24],"Existing":[25],"methods":[26,183],"suffer":[27],"from":[28],"two":[29,195],"major":[30],"challenges:":[31],"inconsistency":[32],"length-insensitivity.":[34],"They":[35],"often":[36],"fail":[37],"to":[38,53,109,144,156],"maintain":[39],"coherence":[40],"between":[41,121],"edited":[43],"local":[44,90,102,116,122],"patch":[45,164],"surrounding":[48],"area,":[49],"they":[51],"struggle":[52],"handle":[54],"significant":[55],"differences":[56],"length":[59],"before":[60],"after":[62],"editing.":[63],"To":[64],"tackle":[65],"these":[66],"challenges,":[67],"we":[68,93,127],"propose":[69],"an":[70,153],"end-to-end":[71],"framework":[72],"called":[73],"Global-Local":[74],"Aware":[75],"(GLASTE),":[79],"which":[80,140],"simultaneously":[81],"incorporates":[82],"high-level":[83],"global":[84,100,124],"contextual":[85],"information":[86],"along":[87],"delicate":[89],"features.":[91],"Specifically,":[92],"design":[94],"global-local":[96],"combination":[97],"structure,":[98],"joint":[99],"losses,":[103],"enhance":[105],"features":[108],"ensure":[110],"consistency":[111],"within":[115],"patches":[117],"maintaining":[119,166],"harmony":[120],"areas.":[125],"Additionally,":[126],"express":[128],"as":[132],"vector":[134],"independent":[135],"of":[136,148],"size,":[139],"can":[141],"be":[142],"transferred":[143],"images":[147,160],"various":[149],"sizes.":[150],"We":[151],"use":[152],"affine":[154],"fusion":[155],"fill":[157],"into":[161],"editing":[163],"their":[167],"aspect":[168],"ratio":[169],"unchanged.":[170],"Extensive":[171],"experiments":[172],"on":[173],"real-world":[174],"datasets":[175],"validate":[176],"that":[177],"our":[178],"GLASTE":[179],"model":[180],"outperforms":[181],"previous":[182],"quantitative":[186],"metrics":[187],"qualitative":[189],"results":[190],"effectively":[192],"mitigates":[193],"challenges.":[196]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}