{"id":"https://openalex.org/W4387968993","doi":"https://doi.org/10.1145/3581783.3612488","title":"STIRER: A Unified Model for Low-Resolution Scene Text Image Recovery and Recognition","display_name":"STIRER: A Unified Model for Low-Resolution Scene Text Image Recovery and Recognition","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968993","doi":"https://doi.org/10.1145/3581783.3612488"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612488","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612488","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612488","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612488","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045420812","display_name":"Minyi Zhao","orcid":"https://orcid.org/0000-0001-7720-806X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minyi Zhao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093130734","display_name":"Shijie Xuyang","orcid":"https://orcid.org/0009-0003-5381-6281"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Xuyang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086316879","display_name":"Jihong Guan","orcid":"https://orcid.org/0000-0003-2313-7635"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihong Guan","raw_affiliation_strings":["Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017862559","display_name":"Shuigeng Zhou","orcid":"https://orcid.org/0000-0002-1949-2768"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuigeng Zhou","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045420812"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.0706,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79839499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7530","last_page":"7539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9994999766349792,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9994999766349792,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9926000237464905,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8319013714790344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7325305342674255},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5628125071525574},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.5237051248550415},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5215320587158203},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.504228949546814},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5021824836730957},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.501476526260376},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48150500655174255},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.48082029819488525},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.4299096465110779},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4190804362297058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319013714790344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7325305342674255},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5628125071525574},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.5237051248550415},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5215320587158203},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.504228949546814},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5021824836730957},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.501476526260376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48150500655174255},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.48082029819488525},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.4299096465110779},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4190804362297058},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612488","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612488","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612488","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612488","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612488","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612488","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5760752404","display_name":null,"funder_award_id":"Projects","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6705365387","display_name":null,"funder_award_id":"U1936205","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968993.pdf","grobid_xml":"https://content.openalex.org/works/W4387968993.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1885185971","https://openalex.org/W1998042868","https://openalex.org/W2049951199","https://openalex.org/W2127141656","https://openalex.org/W2133665775","https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2750938222","https://openalex.org/W2780624730","https://openalex.org/W2810983211","https://openalex.org/W2866634454","https://openalex.org/W2954930822","https://openalex.org/W2963327605","https://openalex.org/W2963470893","https://openalex.org/W2963526661","https://openalex.org/W2997864923","https://openalex.org/W3003642782","https://openalex.org/W3042760913","https://openalex.org/W3103667010","https://openalex.org/W3106271744","https://openalex.org/W3107840264","https://openalex.org/W3134064484","https://openalex.org/W3164382044","https://openalex.org/W3174746398","https://openalex.org/W3177505580","https://openalex.org/W3202415716","https://openalex.org/W3204479434","https://openalex.org/W3207918547","https://openalex.org/W4226544595","https://openalex.org/W4285606401","https://openalex.org/W4312812783","https://openalex.org/W4312879041","https://openalex.org/W6601566401"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2135608140","https://openalex.org/W2347409177","https://openalex.org/W2895525995","https://openalex.org/W2319626700","https://openalex.org/W4319589573","https://openalex.org/W1997070615"],"abstract_inverted_index":{"Though":[0],"scene":[1,33,143,187],"text":[2,17,34,144,188],"recognition":[3,18,61,92,105,225],"(STR)":[4],"from":[5,19],"high-resolution":[6],"(HR)":[7],"images":[8,22,42,98,145,168],"has":[9],"achieved":[10],"significant":[11],"success":[12],"in":[13,237],"the":[14,30,45,53,60,80,85,94,104,110,175,179,193,197,200,215,221],"past":[15],"years,":[16],"low-resolution":[20],"(LR)":[21],"is":[23,50,114,133,235],"still":[24],"a":[25,119,147,154,185],"challenging":[26],"task.":[27],"This":[28],"inspires":[29],"study":[31],"on":[32,44,52,174,210,224],"image":[35],"super-resolution":[36,40,227],"(STISR)":[37],"to":[38,135,157,165,195,220],"generate":[39,74,166],"(SR)":[41],"based":[43,173],"LR":[46,142,181,212],"images,":[47,56,77],"then":[48],"STR":[49,108],"performed":[51],"generated":[54],"SR":[55,76,97,167],"which":[57,78],"eventually":[58],"boosts":[59],"performance.":[62],"However,":[63],"existing":[64,222],"methods":[65,223],"have":[66],"two":[67,162,211],"major":[68],"drawbacks:":[69],"1)":[70],"STISR":[71,86,113],"models":[72,87],"may":[73,99],"imperfect":[75],"mislead":[79],"subsequent":[81],"recognition.":[82,207],"2)":[83],"As":[84],"are":[88],"optimized":[89],"for":[90,203],"high":[91],"accuracy,":[93],"fidelity":[95,111,228],"of":[96,107,112,126,153,199,217],"be":[100],"degraded.":[101],"Consequently,":[102],"neither":[103],"performance":[106],"nor":[109],"desirable.":[115],"In":[116],"this":[117],"paper,":[118],"novel":[120],"model":[121,219],"called":[122],"STIRER":[123,151,233],"(the":[124],"abbreviation":[125],"Scene":[127],"Text":[128],"Image":[129],"REcovery":[130],"and":[131,137,140,161,169,178,206,229],"Recognition)":[132],"proposed":[134],"effectively":[136],"simultaneously":[138],"recover":[139],"recognize":[141,170],"under":[146],"unified":[148],"framework.":[149],"Concretely,":[150],"consists":[152],"feature":[155],"encoder":[156,194],"obtain":[158],"pixel":[159,201],"features":[160,177,202],"dedicated":[163],"decoders":[164],"texts":[171],"respectively":[172],"encoded":[176],"raw":[180],"images.":[182],"We":[183],"propose":[184],"progressive":[186],"swin":[189],"transformer":[190],"architecture":[191],"as":[192],"enrich":[196],"representations":[198],"better":[204],"recovery":[205],"Extensive":[208],"experiments":[209],"datasets":[213],"show":[214],"superiority":[216],"our":[218],"performance,":[226],"computational":[230],"cost.":[231],"The":[232],"Code":[234],"available":[236],"https://github.com/zhaominyiz/STIRER.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}