{"id":"https://openalex.org/W4392904328","doi":"https://doi.org/10.1109/icassp48485.2024.10445827","title":"Accurate and Robust Scene Text Recognition via Adversarial Training","display_name":"Accurate and Robust Scene Text Recognition via Adversarial Training","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904328","doi":"https://doi.org/10.1109/icassp48485.2024.10445827"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445827","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445827","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":"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/A5103038601","display_name":"Xiaomeng Yang","orcid":"https://orcid.org/0000-0003-4109-1562"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaomeng Yang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016775929","display_name":"Dongbao Yang","orcid":"https://orcid.org/0000-0001-8628-411X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbao Yang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000889530","display_name":"Zhi Qiao","orcid":"https://orcid.org/0000-0002-3095-3908"},"institutions":[{"id":"https://openalex.org/I4210154505","display_name":"Tomorrows Children\u2019s Fund","ror":"https://ror.org/04wgs4413","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210154505"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi Qiao","raw_affiliation_strings":["Tomorrow Advancing Life,Beijing,China","Tomorrow Advancing Life, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tomorrow Advancing Life,Beijing,China","institution_ids":["https://openalex.org/I4210154505"]},{"raw_affiliation_string":"Tomorrow Advancing Life, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016175345","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0003-4188-9953"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103038601"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.4875,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60207507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4275","last_page":"4279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9919999837875366,"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"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/adversarial-system","display_name":"Adversarial system","score":0.8673133850097656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777378559112549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6947957277297974},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6868242025375366},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5905603766441345},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49834203720092773},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45877206325531006},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4511496424674988},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3571754992008209},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32554861903190613},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3241378366947174},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07317209243774414}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8673133850097656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777378559112549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6947957277297974},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6868242025375366},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5905603766441345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49834203720092773},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45877206325531006},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4511496424674988},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3571754992008209},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32554861903190613},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3241378366947174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07317209243774414},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445827","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445827","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":[],"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/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/G349564040","display_name":null,"funder_award_id":"62376266","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","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"}],"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":39,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W2008806374","https://openalex.org/W2099247484","https://openalex.org/W2127141656","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2916286792","https://openalex.org/W2963517393","https://openalex.org/W2963823140","https://openalex.org/W3004846386","https://openalex.org/W3034447740","https://openalex.org/W3035402938","https://openalex.org/W3035449864","https://openalex.org/W3035743198","https://openalex.org/W3048753943","https://openalex.org/W3163005567","https://openalex.org/W3175958943","https://openalex.org/W3177505580","https://openalex.org/W3177684257","https://openalex.org/W3181186176","https://openalex.org/W3187071356","https://openalex.org/W3191453585","https://openalex.org/W3202415716","https://openalex.org/W3206651063","https://openalex.org/W4229030834","https://openalex.org/W4293846201","https://openalex.org/W4295246343","https://openalex.org/W4312923907","https://openalex.org/W4385767967","https://openalex.org/W4386410320","https://openalex.org/W4390871832","https://openalex.org/W6649973027","https://openalex.org/W6691603626","https://openalex.org/W6759204839","https://openalex.org/W6804570098"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W4285706568"],"abstract_inverted_index":{"Adversarial":[0],"training":[1,12,87],"(AT)":[2],"is":[3,117],"a":[4,16,68,124,139,144,152],"methodology":[5],"that":[6,99],"utilizes":[7],"adversarial":[8,20,83],"examples":[9,84],"in":[10,28,42,85,120,127],"the":[11,43,59,86,104,131,175],"process":[13],"to":[14,19,73],"enhance":[15],"model\u2019s":[17],"resistance":[18],"attacks":[21],"and":[22,37,66,77],"improve":[23],"generalization.":[24],"Despite":[25],"its":[26,40],"efficacy":[27],"several":[29],"non-sequential":[30],"computer":[31],"vision":[32],"tasks":[33],"such":[34],"as":[35,151],"classification":[36],"object":[38],"detection,":[39],"effects":[41],"realm":[44],"of":[45,61,106,134,154,177],"Scene":[46],"Text":[47],"Recognition":[48],"(STR)":[49],"remain":[50],"largely":[51],"unexplored.":[52],"This":[53,115],"paper":[54],"pioneers":[55],"an":[56,75],"investigation":[57],"into":[58,174],"implications":[60],"AT":[62,71,100,150,178],"on":[63],"STR":[64,79,107,141],"models":[65,108],"proposes":[67],"novel":[69],"regularization-based":[70],"method":[72],"develop":[74],"accurate":[76],"robust":[78,140],"model,":[80],"dynamically":[81],"generating":[82],"procedure.":[88],"Through":[89],"extensive":[90],"experiments":[91],"across":[92],"seven":[93],"public":[94],"real-world":[95,135],"datasets,":[96],"we":[97],"find":[98],"not":[101],"only":[102],"bolsters":[103],"robustness":[105],"but":[109],"also":[110],"improves":[111],"overall":[112],"recognition":[113],"accuracy.":[114],"improvement":[116],"particularly":[118],"significant":[119],"low-resolution":[121],"images":[122],"-":[123],"common":[125],"challenge":[126],"STR.":[128],"Furthermore,":[129],"given":[130],"diverse":[132],"nature":[133],"text":[136,181],"images,":[137],"developing":[138],"model":[142],"requires":[143],"large":[145],"dataset.":[146],"We":[147,166],"propose":[148],"viewing":[149],"form":[153],"model-based":[155],"data":[156],"augmentation":[157,164],"technique":[158],"for":[159,179],"STR,":[160],"compatible":[161],"with":[162],"traditional":[163],"methods.":[165],"hope":[167],"these":[168],"encouraging":[169],"findings":[170],"catalyze":[171],"further":[172],"research":[173],"application":[176],"scene":[180],"recognition.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}