{"id":"https://openalex.org/W4408848262","doi":"https://doi.org/10.1145/3712676.3719267","title":"Efficient and Accurate Scene Text Recognition with Cascaded-Transformers","display_name":"Efficient and Accurate Scene Text Recognition with Cascaded-Transformers","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4408848262","doi":"https://doi.org/10.1145/3712676.3719267"},"language":"en","primary_location":{"id":"doi:10.1145/3712676.3719267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712676.3719267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Multimedia Systems Conference","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/A5103889759","display_name":"Savas Ozkan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Savas Ozkan","raw_affiliation_strings":["Samsung Research UK, Surrey, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0006-0450-0645","affiliations":[{"raw_affiliation_string":"Samsung Research UK, Surrey, United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andrea Maracani","orcid":"https://orcid.org/0000-0002-7189-7260"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrea Maracani","raw_affiliation_strings":["Samsung Research UK, Surrey, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-7189-7260","affiliations":[{"raw_affiliation_string":"Samsung Research UK, Surrey, United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116800570","display_name":"Mete Ozay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mete Ozay","raw_affiliation_strings":["Samsung Research UK, Surrey, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-6217-8731","affiliations":[{"raw_affiliation_string":"Samsung Research UK, Surrey, United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyowon Kim","orcid":"https://orcid.org/0009-0007-9599-1095"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyowon Kim","raw_affiliation_strings":["Samsung Electronics, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0007-9599-1095","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109986096","display_name":"Sijun Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sijun Cho","raw_affiliation_strings":["Samsung Electronics, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0001-4722-7419","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114847604","display_name":"Eunchung Noh","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eunchung Noh","raw_affiliation_strings":["Samsung Electronics, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-2049-4222","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026331733","display_name":"Jeongwon Min","orcid":"https://orcid.org/0000-0001-8412-5545"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongwon Min","raw_affiliation_strings":["Samsung Electronics, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-8412-5545","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022648717","display_name":"Jung\u2010Min Cho","orcid":"https://orcid.org/0000-0002-1884-6675"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung Min Cho","raw_affiliation_strings":["Samsung Electronics, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1884-6675","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5103889759"],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":1.1332,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76068774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"335","last_page":"341"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9976000189781189,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9959999918937683,"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":0.7106755971908569},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6644442081451416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5283123850822449},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44192561507225037},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4078386127948761},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3321712017059326},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14234048128128052},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13951024413108826},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13220536708831787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106755971908569},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6644442081451416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5283123850822449},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44192561507225037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4078386127948761},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3321712017059326},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14234048128128052},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13951024413108826},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13220536708831787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712676.3719267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712676.3719267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Multimedia Systems Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W2108598243","https://openalex.org/W2146835493","https://openalex.org/W2343052201","https://openalex.org/W2529099292","https://openalex.org/W2885311373","https://openalex.org/W3003711889","https://openalex.org/W3003921261","https://openalex.org/W3179897446","https://openalex.org/W3202415716","https://openalex.org/W3204479434","https://openalex.org/W4312879041","https://openalex.org/W4390871832","https://openalex.org/W6753278433"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,115],"recent":[1],"years,":[2],"vision":[3,81],"transformers":[4],"with":[5,28,132],"text":[6],"decoder":[7],"have":[8],"demonstrated":[9],"remarkable":[10],"performance":[11,106],"on":[12,64],"Scene":[13],"Text":[14],"Recognition":[15],"(STR)":[16],"due":[17],"to":[18,21,107],"their":[19,44],"ability":[20],"capture":[22],"long-range":[23],"dependencies":[24],"and":[25,35,57,92],"contextual":[26],"relationships":[27],"high":[29],"learning":[30],"capacity.":[31],"However,":[32],"the":[33,66,80,85,119],"computational":[34,94,113,127],"memory":[36],"demands":[37],"of":[38,68],"these":[39],"models":[40,70],"are":[41],"significant,":[42],"limiting":[43],"deployment":[45],"in":[46],"resource-constrained":[47],"applications.":[48],"To":[49],"address":[50],"this":[51],"challenge,":[52],"we":[53,62],"propose":[54],"an":[55],"efficient":[56],"accurate":[58],"STR":[59,102],"system.":[60],"Specifically,":[61],"focus":[63],"improving":[65],"efficiency":[67],"encoder":[69],"by":[71],"introducing":[72],"a":[73],"cascaded-transformers":[74],"structure.":[75,134],"This":[76],"structure":[77],"progressively":[78],"reduces":[79],"token":[82],"size":[83],"during":[84],"encoding":[86],"step,":[87],"effectively":[88],"eliminating":[89],"redundant":[90],"tokens":[91],"reducing":[93],"cost.":[95],"Our":[96],"experimental":[97],"results":[98],"confirm":[99],"that":[100],"our":[101,133],"system":[103],"achieves":[104],"comparable":[105],"state-of-the-art":[108],"baselines":[109],"while":[110,126],"substantially":[111],"decreasing":[112],"requirements.":[114],"particular,":[116],"for":[117],"large-models,":[118],"accuracy":[120],"remains":[121],"same,":[122],"92.77":[123],"\u2192":[124],"92.68,":[125],"complexity":[128],"is":[129],"almost":[130],"halved":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}