{"id":"https://openalex.org/W4392903189","doi":"https://doi.org/10.1109/icassp48485.2024.10446874","title":"Maskstr: Guide Scene Text Recognition Models with Masking","display_name":"Maskstr: Guide Scene Text Recognition Models with Masking","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903189","doi":"https://doi.org/10.1109/icassp48485.2024.10446874"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5072974615","display_name":"Baole Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baole Wei","raw_affiliation_strings":["Peking University,Wangxuan Institute of Computer Technology,Beijing,China","Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025388895","display_name":"Minghang He","orcid":null},"institutions":[{"id":"https://openalex.org/I2801787653","display_name":"Beijing Dance Academy","ror":"https://ror.org/02g3wgj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I2801787653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghang He","raw_affiliation_strings":["ByteDance Inc,Beijing,China","ByteDance Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc,Beijing,China","institution_ids":["https://openalex.org/I2801787653"]},{"raw_affiliation_string":"ByteDance Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004474713","display_name":"Liangcai Gao","orcid":"https://orcid.org/0000-0001-9444-1568"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangcai Gao","raw_affiliation_strings":["Peking University,Wangxuan Institute of Computer Technology,Beijing,China","Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017529866","display_name":"Duoyou Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I2801787653","display_name":"Beijing Dance Academy","ror":"https://ror.org/02g3wgj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I2801787653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duoyou Zhou","raw_affiliation_strings":["ByteDance Inc,Beijing,China","ByteDance Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc,Beijing,China","institution_ids":["https://openalex.org/I2801787653"]},{"raw_affiliation_string":"ByteDance Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"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":"Xiang Bai","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China","Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103175239","display_name":"Zhi Tang","orcid":"https://orcid.org/0000-0002-6021-8357"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Tang","raw_affiliation_strings":["Peking University,Wangxuan Institute of Computer Technology,Beijing,China","Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4245","last_page":"4249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9596999883651733,"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":0.9560999870300293,"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":0.8172832727432251},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7471975088119507},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6185475587844849},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5491509437561035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5245780348777771},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5130082964897156},{"id":"https://openalex.org/keywords/information-loss","display_name":"Information loss","score":0.4638163447380066},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4450944662094116},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3969801068305969},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39645102620124817},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3509034514427185},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12374979257583618}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172832727432251},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7471975088119507},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6185475587844849},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5491509437561035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5245780348777771},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5130082964897156},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.4638163447380066},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4450944662094116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3969801068305969},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39645102620124817},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3509034514427185},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12374979257583618},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2127141656","https://openalex.org/W2194187530","https://openalex.org/W3003921261","https://openalex.org/W3094502228","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W4283821822","https://openalex.org/W4312879041","https://openalex.org/W4313156423","https://openalex.org/W4320855770","https://openalex.org/W4385245566","https://openalex.org/W4386221015","https://openalex.org/W6784333009","https://openalex.org/W6850778630"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W3081694532","https://openalex.org/W2161474341","https://openalex.org/W4302615923","https://openalex.org/W2181948922","https://openalex.org/W3203142394","https://openalex.org/W2351061015","https://openalex.org/W2384362569","https://openalex.org/W3194982682","https://openalex.org/W4401517511"],"abstract_inverted_index":{"Text":[0],"recognition":[1],"in":[2,14],"information":[3,70,80],"loss":[4,81],"scenarios":[5],"like":[6],"blurriness,":[7],"occlusion,":[8],"and":[9,43,96,112,120],"perspective":[10],"distortion":[11],"is":[12],"challenging":[13],"real-world":[15],"applications.":[16],"To":[17],"enhance":[18],"robustness,":[19],"some":[20],"studies":[21],"use":[22],"extra":[23,84],"unlabeled":[24,41],"data":[25,42,85],"for":[26,62,101],"encoder":[27],"pretraining.":[28],"Others":[29],"focus":[30],"on":[31],"improving":[32,77],"decoder":[33],"context":[34],"reasoning.":[35],"However,":[36],"pretraining":[37],"methods":[38],"require":[39],"abundant":[40],"high":[44],"computing":[45],"resources,":[46],"while":[47],"decoder-based":[48],"approaches":[49],"risk":[50],"over-correction.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,90],"propose":[56],"MaskSTR,":[57],"a":[58,94],"dual-branch":[59],"training":[60,87],"framework":[61],"STR":[63],"models,":[64],"using":[65],"patch":[66],"masking":[67],"to":[68,79],"simulate":[69],"loss.":[71],"MaskSTR":[72],"guides":[73],"visual":[74],"representation":[75],"learning,":[76],"robustness":[78],"conditions":[82],"without":[83],"or":[86],"stages.":[88],"Furthermore,":[89],"introduce":[91],"Block":[92],"Masking,":[93],"novel":[95],"straightforward":[97],"mask":[98],"generation":[99],"method,":[100],"further":[102],"performance":[103,118],"enhancement.":[104],"Experiments":[105],"demonstrate":[106],"MaskSTR\u2019s":[107],"effectiveness":[108],"across":[109],"CTC,":[110],"attention,":[111],"Transformer":[113],"decoding":[114],"methods,":[115],"achieving":[116],"significant":[117],"gains":[119],"setting":[121],"new":[122],"state-of-the-art":[123],"results.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}