{"id":"https://openalex.org/W4200547802","doi":"https://doi.org/10.1109/dicta52665.2021.9647413","title":"A Seq2seq-based Model with Global Semantic Context for Scene Text Recognition","display_name":"A Seq2seq-based Model with Global Semantic Context for Scene Text Recognition","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4200547802","doi":"https://doi.org/10.1109/dicta52665.2021.9647413"},"language":"en","primary_location":{"id":"doi:10.1109/dicta52665.2021.9647413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta52665.2021.9647413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Digital Image Computing: Techniques and Applications (DICTA)","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/A5108063743","display_name":"Yi\u2010Li Huang","orcid":"https://orcid.org/0000-0002-8039-9896"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-Li Huang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101717685","display_name":"Shilin Wang","orcid":"https://orcid.org/0000-0002-8214-6809"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi-Lin Wang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019447181","display_name":"Chengyu Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng-Yu Gu","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103055957","display_name":"Zheng Huang","orcid":"https://orcid.org/0009-0003-2994-8030"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Huang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101951847","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-0125-3988"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"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":"01","last_page":"06"},"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":0.9916999936103821,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9911999702453613,"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":0.7813335657119751},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6321932077407837},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6263614892959595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5698832869529724},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5529987215995789},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.525770902633667},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48224955797195435},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4689074754714966},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4390428364276886},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.42103683948516846},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.41180509328842163},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4107666611671448},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18521946668624878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813335657119751},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6321932077407837},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6263614892959595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698832869529724},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5529987215995789},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.525770902633667},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48224955797195435},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4689074754714966},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4390428364276886},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.42103683948516846},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.41180509328842163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4107666611671448},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18521946668624878},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C49204034","wikidata":"https://www.wikidata.org/wiki/Q52139","display_name":"Climatology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dicta52665.2021.9647413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta52665.2021.9647413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[{"id":"https://openalex.org/G7251324907","display_name":"\u9762\u5411\u5927\u8bcd\u6c47\u91cf\u8fde\u7eed\u8bed\u97f3\u7684\u81ea\u52a8\u5316\u5507\u8bfb\u6280\u672f\u7814\u7a76","funder_award_id":"61771310","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W648786980","https://openalex.org/W1491389626","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2016589492","https://openalex.org/W2140132917","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2343052201","https://openalex.org/W2810983211","https://openalex.org/W2964345285","https://openalex.org/W2965066169","https://openalex.org/W2998382406","https://openalex.org/W3003218881","https://openalex.org/W3004846386","https://openalex.org/W3034447740","https://openalex.org/W3035449864","https://openalex.org/W4287867419","https://openalex.org/W4385245566","https://openalex.org/W6618372016","https://openalex.org/W6621543089","https://openalex.org/W6629590909","https://openalex.org/W6649973027","https://openalex.org/W6739901393","https://openalex.org/W6773526639"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2171218219","https://openalex.org/W2971214053","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W3150905897","https://openalex.org/W2021517900","https://openalex.org/W1520183331"],"abstract_inverted_index":{"Scene":[0],"text":[1,112],"recognition":[2],"(STR),":[3],"with":[4,72],"various":[5],"applications,":[6],"has":[7],"become":[8],"a":[9,60,85],"popular":[10],"research.":[11],"With":[12],"deep":[13],"learning,":[14],"many":[15],"sequence":[16,18],"to":[17,36,77,92],"(seq2seq)":[19],"models":[20,33,49],"have":[21,102],"been":[22],"proposed.":[23],"However,":[24],"the":[25,31,37,43,79,104,107],"Teacher-Forcing":[26],"training":[27],"method":[28,109],"used":[29],"in":[30,66,110],"seq2seq":[32,48],"gave":[34],"rise":[35],"problem":[38,80],"of":[39,51,81,106],"exposure":[40,82],"bias.":[41],"Moreover,":[42],"autoregressive":[44],"decoding":[45],"manner":[46],"limits":[47],"ability":[50],"utilizing":[52],"future":[53],"semantic":[54],"information.":[55,96],"To":[56],"solve":[57],"these":[58],"problems,":[59],"new":[61],"Transformer-based":[62],"network":[63],"is":[64,75,90],"proposed":[65,108],"this":[67],"paper.":[68],"A":[69],"Re-Embedding":[70],"Layer":[71],"sampling":[73],"module":[74,88],"introduced":[76],"overcome":[78],"bias":[83],"and":[84],"context":[86,95],"fusion":[87],"(CFM)":[89],"designed":[91],"model":[93],"global":[94],"Experiment":[97],"results":[98],"on":[99],"several":[100],"benchmarks":[101],"demonstrated":[103],"effectiveness":[105],"scene":[111],"recognition.":[113]},"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"}