{"id":"https://openalex.org/W3001592365","doi":"https://doi.org/10.1109/vcip47243.2019.8965779","title":"DSAN: Double Supervised Network with Attention Mechanism for Scene Text Recognition","display_name":"DSAN: Double Supervised Network with Attention Mechanism for Scene Text Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3001592365","doi":"https://doi.org/10.1109/vcip47243.2019.8965779","mag":"3001592365"},"language":"en","primary_location":{"id":"doi:10.1109/vcip47243.2019.8965779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip47243.2019.8965779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Visual Communications and Image Processing (VCIP)","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/A5101682899","display_name":"Yuting Gao","orcid":"https://orcid.org/0000-0002-4329-4091"},"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":"Yuting Gao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","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":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067772383","display_name":"Yuchen Dai","orcid":"https://orcid.org/0000-0002-9710-9031"},"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":"Yuchen Dai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101588348","display_name":"Cheng Xu","orcid":"https://orcid.org/0000-0002-4281-6214"},"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 Xu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437924","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-6384-0355"},"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":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100709304","display_name":"Jie Guo","orcid":"https://orcid.org/0000-0002-2859-0159"},"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":"Jie Guo","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","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":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9914000034332275,"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":0.8427773714065552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6012508869171143},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6010260581970215},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5945383906364441},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5780476331710815},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5658109784126282},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5158316493034363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4689609110355377},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.46755990386009216},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4240576922893524},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.386550635099411},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.341091513633728},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2773458957672119},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09586042165756226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8427773714065552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6012508869171143},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6010260581970215},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5945383906364441},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5780476331710815},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5658109784126282},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5158316493034363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4689609110355377},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.46755990386009216},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4240576922893524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.386550635099411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.341091513633728},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2773458957672119},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09586042165756226},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip47243.2019.8965779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip47243.2019.8965779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W1491389626","https://openalex.org/W1607307044","https://openalex.org/W1922126009","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2122221966","https://openalex.org/W2127141656","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2341629100","https://openalex.org/W2343052201","https://openalex.org/W2741147179","https://openalex.org/W2750938222","https://openalex.org/W2795619303","https://openalex.org/W2963517393","https://openalex.org/W3106271744","https://openalex.org/W4294629828","https://openalex.org/W6602936574","https://openalex.org/W6629590909","https://openalex.org/W6636382570","https://openalex.org/W6741742085"],"related_works":["https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W2144059113","https://openalex.org/W3003836766","https://openalex.org/W1964120219","https://openalex.org/W2000165426","https://openalex.org/W2385132419","https://openalex.org/W2772780115","https://openalex.org/W2114557664","https://openalex.org/W2546942002"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"Double":[5],"Supervised":[6],"Network":[7],"with":[8],"Attention":[9],"Mechanism":[10],"(DSAN),":[11],"a":[12],"novel":[13],"end-to-end":[14],"trainable":[15],"framework":[16,42],"for":[17],"scene":[18],"text":[19,24,37,90,110],"recognition.":[20],"It":[21],"incorporates":[22],"one":[23,59],"attention":[25],"module":[26],"during":[27],"feature":[28],"extraction":[29],"which":[30,64,124],"enforces":[31],"the":[32,40,104,126,129],"model":[33],"to":[34],"focus":[35],"on":[36,108],"regions":[38],"and":[39,55,81,94,115,121],"whole":[41],"is":[43],"supervised":[44],"by":[45],"two":[46,75],"branches.":[47],"One":[48],"supervision":[49,61],"comes":[50,57],"from":[51,58],"context-level":[52],"modelling":[53],"branch":[54,63],"another":[56],"extra":[60],"enhancement":[62],"aims":[65],"at":[66,71],"tackling":[67],"inexplicit":[68],"semantic":[69],"information":[70],"character":[72],"level.":[73],"These":[74],"supervisions":[76],"can":[77,88],"benefit":[78],"each":[79],"other":[80],"yield":[82],"better":[83],"performance.":[84],"The":[85],"proposed":[86,130],"approach":[87],"recognize":[89],"in":[91],"arbitrary":[92],"length":[93],"does":[95],"not":[96],"need":[97],"any":[98],"predefined":[99],"lexicon.":[100],"Our":[101],"method":[102],"achieves":[103],"current":[105],"state-of-the-art":[106],"results":[107],"three":[109],"recognition":[111],"benchmarks:":[112],"IIIT5K,":[113],"ICDAR2013":[114],"SVT":[116],"reaching":[117],"accuracy":[118],"88.6%,":[119],"92.3%":[120],"84.1%":[122],"respectively":[123],"suggests":[125],"effectiveness":[127],"of":[128],"method.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}