{"id":"https://openalex.org/W4387968327","doi":"https://doi.org/10.1145/3581783.3612370","title":"Masked Text Modeling: A Self-Supervised Pre-training Method for Scene Text Detection","display_name":"Masked Text Modeling: A Self-Supervised Pre-training Method for Scene Text Detection","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968327","doi":"https://doi.org/10.1145/3581783.3612370"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612370","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612370","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102984034","display_name":"Keran Wang","orcid":"https://orcid.org/0009-0001-6807-5207"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Keran Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427468","display_name":"Yuxin Wang","orcid":"https://orcid.org/0000-0002-0228-6220"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632765","display_name":"Dongming Zhang","orcid":"https://orcid.org/0000-0002-1237-7177"},"institutions":[{"id":"https://openalex.org/I4210121144","display_name":"China Machine Press","ror":"https://ror.org/02t1dzr71","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210121144"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongming Zhang","raw_affiliation_strings":["State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China","institution_ids":["https://openalex.org/I4210121144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071238622","display_name":"Yadong Qu","orcid":"https://orcid.org/0000-0003-0265-5011"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Qu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040035023","display_name":"Zuan Gao","orcid":"https://orcid.org/0009-0001-0587-4167"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuan Gao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102984034"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.305,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82942105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2006","last_page":"2015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9922000169754028,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9900000095367432,"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/computer-science","display_name":"Computer science","score":0.7784636616706848},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6578536033630371},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.6424664258956909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6405320167541504},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.6397053003311157},{"id":"https://openalex.org/keywords/noisy-text-analytics","display_name":"Noisy text analytics","score":0.5539405345916748},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5315943360328674},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5200805068016052},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.44674360752105713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4409255385398865},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.42202746868133545},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3548377454280853},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.3194124102592468},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25648391246795654},{"id":"https://openalex.org/keywords/text-graph","display_name":"Text graph","score":0.2260618507862091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784636616706848},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6578536033630371},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.6424664258956909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6405320167541504},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.6397053003311157},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.5539405345916748},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5315943360328674},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5200805068016052},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.44674360752105713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4409255385398865},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42202746868133545},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3548377454280853},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.3194124102592468},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25648391246795654},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.2260618507862091},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612370","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612370","pdf_url":null,"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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6899999976158142,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","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/G2182495747","display_name":null,"funder_award_id":"2121002","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/G3828173677","display_name":null,"funder_award_id":"62121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3990726848","display_name":null,"funder_award_id":"62121002, 62232006, 62102384","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4897510482","display_name":null,"funder_award_id":"62232006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6695563415","display_name":null,"funder_award_id":"2022YFB3104700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G891989852","display_name":null,"funder_award_id":"62102384","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1988461287","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2593539516","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2784050770","https://openalex.org/W2785383245","https://openalex.org/W2810028092","https://openalex.org/W2896034938","https://openalex.org/W2902494497","https://openalex.org/W2935842779","https://openalex.org/W2962858109","https://openalex.org/W2963299604","https://openalex.org/W2963353821","https://openalex.org/W2963647456","https://openalex.org/W2963840241","https://openalex.org/W2967615747","https://openalex.org/W2968226676","https://openalex.org/W2991626090","https://openalex.org/W2997351497","https://openalex.org/W2998621280","https://openalex.org/W3003921261","https://openalex.org/W3034514377","https://openalex.org/W3035679705","https://openalex.org/W3092619320","https://openalex.org/W3096739052","https://openalex.org/W3106228955","https://openalex.org/W3171030392","https://openalex.org/W3176196997","https://openalex.org/W3181186176","https://openalex.org/W3184364189","https://openalex.org/W3186906052","https://openalex.org/W4214540501","https://openalex.org/W4214922754","https://openalex.org/W4292825881","https://openalex.org/W4310335763","https://openalex.org/W4312312750","https://openalex.org/W4312804044","https://openalex.org/W4313006333","https://openalex.org/W4313156423"],"related_works":["https://openalex.org/W4312663241","https://openalex.org/W2152349655","https://openalex.org/W3180286081","https://openalex.org/W4297798696","https://openalex.org/W4387968327","https://openalex.org/W3046446809","https://openalex.org/W2987600763","https://openalex.org/W4312115774","https://openalex.org/W4386274962","https://openalex.org/W2970910956"],"abstract_inverted_index":{"Scene":[0],"text":[1,17,39,68,84,108,112,116,134,142,152,164,208,216,227,247],"detection":[2,18,230],"has":[3],"made":[4],"great":[5],"progress":[6],"recently":[7],"with":[8,74,191],"the":[9,31,49,52,79,115,121,138,141,150,163,167,176,181,185,192,207,224,243],"wide":[10],"use":[11],"of":[12,41,51,107,123,188,210,229,245],"pre-training.":[13],"Nonetheless,":[14],"existing":[15,246],"scene":[16,67],"methods":[19],"still":[20],"suffer":[21],"from":[22,87,120,146],"two":[23],"problems:":[24],"1)":[25],"Limited":[26],"annotated":[27],"real":[28],"data":[29,76],"reduces":[30],"feature":[32,196],"robustness.":[33],"2)":[34],"Detectors":[35],"perform":[36],"poorly":[37],"on":[38,234],"lacking":[40,209],"visual":[42,211],"information.":[43,212],"In":[44,114,149],"this":[45],"paper,":[46],"we":[47],"explore":[48],"potential":[50],"CLIP":[53,147],"model,":[54],"and":[55,77,110,143,166],"propose":[56],"a":[57,95,125,155,202,214],"novel":[58],"self-supervised":[59],"Masked":[60,168],"Text":[61,126,169],"Modeling":[62,170],"(MTM)":[63],"pre-training":[64],"method":[65],"for":[66,83,206,226],"detection,":[69],"which":[70],"can":[71,241],"be":[72],"trained":[73],"unlabeled":[75],"improve":[78],"linguistic":[80,186],"reasoning":[81],"ability":[82,182],"occlusion.":[85],"Different":[86],"previous":[88],"randomly":[89],"pixel-level":[90],"masking":[91,98],"methods,":[92],"MTM":[93,105,179,200,240],"performs":[94],"targeted":[96],"text-aware":[97],"process":[99],"under":[100],"an":[101],"unsupervised":[102],"manner.":[103],"Specifically,":[104],"consists":[106],"perception":[109,117],"masked":[111,151,177,189],"modeling.":[113],"step,":[118,154],"benefiting":[119],"text-friendliness":[122],"CLIP,":[124],"Perception":[127],"Module":[128,171],"is":[129,159,172,220],"proposed":[130,221],"to":[131,133,161,174,183,222],"attend":[132],"area":[135],"by":[136,199],"computing":[137],"similarity":[139],"between":[140],"image":[144],"tokens":[145],"model.":[148],"modeling":[153],"Text-aware":[156],"Masking":[157],"Strategy":[158],"designed":[160],"mask":[162],"area,":[165],"used":[173],"reconstruct":[175],"texts.":[178],"obtains":[180],"reason":[184],"information":[187],"texts":[190],"reconstruction.":[193],"This":[194],"robust":[195],"extraction":[197],"learned":[198],"ensures":[201],"more":[203],"discriminative":[204],"representation":[205],"Moreover,":[213],"new":[215],"dataset":[217],"named":[218],"OcclusionText":[219],"evaluate":[223],"robustness":[225],"occlusion":[228],"methods.":[231],"Extensive":[232],"experiments":[233],"public":[235],"benchmarks":[236],"demonstrate":[237],"that":[238],"our":[239],"boost":[242],"performance":[244],"detectors.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}