{"id":"https://openalex.org/W7131265938","doi":"https://doi.org/10.1109/tcsvt.2026.3667545","title":"MSINet: A Mask Structure Inference Network for Scene Text Image Super-Resolution","display_name":"MSINet: A Mask Structure Inference Network for Scene Text Image Super-Resolution","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131265938","doi":"https://doi.org/10.1109/tcsvt.2026.3667545"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3667545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3667545","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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":"https://openalex.org/A5049658962","display_name":"Runmin Wang","orcid":"https://orcid.org/0000-0001-9687-9918"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runmin Wang","raw_affiliation_strings":["School of Information Science and Engineering, Hunan Normal University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-9687-9918","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Hunan Normal University, Changsha, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126734098","display_name":"Shengrong Yuan","orcid":null},"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":"Shengrong Yuan","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126716656","display_name":"Shan Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Ye","raw_affiliation_strings":["School of Information Science and Engineering, Hunan Normal University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Hunan Normal University, Changsha, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126677781","display_name":"Xingdong Song","orcid":null},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingdong Song","raw_affiliation_strings":["School of Information Science and Engineering, Hunan Normal University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0009-9937-2659","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Hunan Normal University, Changsha, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126725934","display_name":"Han Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Xu","raw_affiliation_strings":["School of Information Science and Engineering, Hunan Normal University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0000-8876-2023","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Hunan Normal University, Changsha, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126727967","display_name":"Shengyou Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyou Qian","raw_affiliation_strings":["School of Physical and Electronic Sciences, Hunan Normal University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-8253-8290","affiliations":[{"raw_affiliation_string":"School of Physical and Electronic Sciences, Hunan Normal University, Changsha, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029752909","display_name":"Changxin Gao","orcid":null},"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":"Changxin Gao","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-2736-3920","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013734579","display_name":"Nong Sang","orcid":"https://orcid.org/0000-0002-9167-1496"},"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":"Nong Sang","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-9167-1496","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23083518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"7894","last_page":"7908"},"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":0.7906000018119812,"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":0.7906000018119812,"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":0.07590000331401825,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.01720000058412552,"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/prior-probability","display_name":"Prior probability","score":0.628000020980835},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6269000172615051},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5800999999046326},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5619999766349792},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5268999934196472},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.4862000048160553},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4733999967575073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46709999442100525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803999781608582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7318000197410583},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.628000020980835},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6269000172615051},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5800999999046326},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5268999934196472},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47859999537467957},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4262999892234802},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3978999853134155},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3667545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3667545","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2950222348","display_name":null,"funder_award_id":"62576137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3406572080","display_name":null,"funder_award_id":"2024JJ10034","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G7643348484","display_name":null,"funder_award_id":"2020JJ4057","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"the":[1,28,34,38,43,48,56,73,77,94,177,182,197],"structure":[2,30,138,146],"of":[3,50,130,181],"characters":[4],"is":[5,159],"crucial":[6],"for":[7,136,144],"recovering":[8],"clear":[9],"and":[10,92,140,172,179,199],"readable":[11],"high-resolution":[12],"scene":[13,103,184,206],"text":[14,53,104,185,207],"images":[15,105],"in":[16,33,210],"Scene":[17],"Text":[18,155],"Image":[19,89],"Super-Resolution":[20],"(STISR).":[21],"Recently,":[22],"many":[23],"existing":[24],"STISR":[25,117],"methods":[26,192],"inject":[27],"character":[29,108,137,145,168],"information":[31],"implicit":[32],"recognition":[35,57,113,208,211],"priors":[36,58,71],"into":[37,72],"super-resolution":[39,44,78],"network":[40,74],"to":[41,161],"guide":[42],"process,":[45],"thereby":[46],"facilitating":[47],"generation":[49],"more":[51],"legible":[52,167],"images.":[54,186],"However,":[55],"obtained":[59],"from":[60,87],"low":[61],"resolution":[62],"are":[63],"inaccurate,":[64],"which":[65,100,128],"means":[66],"that":[67],"directly":[68,111],"embedding":[69,112],"these":[70],"easily":[75],"misleads":[76],"process.":[79],"To":[80,115],"address":[81],"this":[82],"problem,":[83],"we":[84,121],"draw":[85],"inspiration":[86],"Masked":[88],"Modeling":[90],"(MIM)":[91],"propose":[93,123],"Mask":[95,157],"Structure":[96],"Inference":[97],"Network":[98],"(MSINet),":[99],"can":[101],"generate":[102],"with":[106,119],"accurate":[107],"structures":[109],"without":[110],"priors.":[114],"make":[116],"compatible":[118],"MIM,":[120],"also":[122],"a":[124,131,141,150],"Mask-and-Inference":[125],"Paradigm":[126],"(MIP),":[127],"consists":[129],"mask":[132,152],"image":[133],"pre-training":[134],"stage":[135,143],"learning":[139],"fine-tuning":[142],"inference.":[147],"In":[148],"addition,":[149],"novel":[151],"strategy":[153],"named":[154],"Confidence":[156],"(TCM)":[158],"proposed":[160],"avoid":[162],"recovery":[163],"errors":[164],"by":[165,193],"masking":[166],"regions.":[169],"With":[170],"MIP":[171],"TCM,":[173],"MSINet":[174],"impressively":[175],"improves":[176],"clarity":[178],"readability":[180],"degraded":[183,205],"Specifically,":[187],"MSINet-B":[188],"outperforms":[189],"recent":[190],"state-of-the-art":[191],"about":[194],"+3.7%":[195],"on":[196,202],"TextZoom":[198],"average":[200],"+3.6%":[201],"six":[203],"manually":[204],"datasets":[209],"accuracy.":[212],"The":[213],"code":[214],"will":[215],"be":[216],"released":[217],"at":[218],"https://github.com/Yuanssr/MSINet.":[219]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-25T00:00:00"}
