{"id":"https://openalex.org/W4377236345","doi":"https://doi.org/10.1145/3581807.3581837","title":"Improved Fusion of Visual and Semantic Representations by Gated Co-Attention for Scene Text Recognition","display_name":"Improved Fusion of Visual and Semantic Representations by Gated Co-Attention for Scene Text Recognition","publication_year":2022,"publication_date":"2022-11-17","ids":{"openalex":"https://openalex.org/W4377236345","doi":"https://doi.org/10.1145/3581807.3581837"},"language":"en","primary_location":{"id":"doi:10.1145/3581807.3581837","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581807.3581837","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581807.3581837","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 11th International Conference on Computing and Pattern Recognition","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581807.3581837","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074727026","display_name":"Junwei Zhou","orcid":"https://orcid.org/0000-0002-2734-1310"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwei Zhou","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China and \rSchool of Cyber Security, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-2734-1310","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and \rSchool of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018114609","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0002-6642-8160"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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":"Xi Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-6642-8160","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031794241","display_name":"Jiao Dai","orcid":"https://orcid.org/0000-0003-3559-8009"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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":"Jiao Dai","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-3559-8009","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082300353","display_name":"Jizhong Han","orcid":"https://orcid.org/0000-0003-1107-3873"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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":"Jizhong Han","raw_affiliation_strings":["Institute of Information Engineering,Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-1107-3873","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0925,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45519194,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"204","last_page":"209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9929999709129333,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9896000027656555,"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":0.8504767417907715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6634066104888916},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5520411729812622},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5266242623329163},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.5158595442771912},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47810524702072144},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4301779866218567},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41631895303726196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8504767417907715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6634066104888916},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5520411729812622},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5266242623329163},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.5158595442771912},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47810524702072144},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4301779866218567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41631895303726196},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581807.3581837","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581807.3581837","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581807.3581837","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 11th International Conference on Computing and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581807.3581837","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581807.3581837","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581807.3581837","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 11th International Conference on Computing and Pattern Recognition","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4377236345.pdf","grobid_xml":"https://content.openalex.org/works/W4377236345.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W254514693","https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1981276685","https://openalex.org/W2099247484","https://openalex.org/W2194187530","https://openalex.org/W2255466643","https://openalex.org/W2595840341","https://openalex.org/W2608702473","https://openalex.org/W2810983211","https://openalex.org/W3157598734","https://openalex.org/W6600503824"],"related_works":["https://openalex.org/W2012531322","https://openalex.org/W2402761219","https://openalex.org/W4321487865","https://openalex.org/W2785900585","https://openalex.org/W4313906399","https://openalex.org/W2020521331","https://openalex.org/W101162712","https://openalex.org/W4256618828","https://openalex.org/W2786691313","https://openalex.org/W3196281958"],"abstract_inverted_index":{"Recognizing":[0],"variations":[1],"of":[2,20,100,119,129],"text":[3,21,57],"occurrences":[4],"in":[5,11],"scene":[6,56],"photos":[7],"is":[8],"still":[9],"difficult":[10],"the":[12,18,26,75,84,92,97,103,117,120,127,136,151],"present":[13,51],"day.":[14],"In":[15,47,123],"recent":[16],"years,":[17],"performance":[19,128,145],"recognition":[22,58],"models":[23,34],"based":[24],"on":[25,37,132,146,155],"attention":[27,43,69],"mechanism":[28],"has":[29,143],"vastly":[30],"increased.":[31],"However,":[32],"these":[33],"typically":[35],"focus":[36],"recognizing":[38],"image":[39],"regions":[40],"or":[41],"visual":[42,66,76,109],"that":[44,140],"are":[45],"significant.":[46],"this":[48],"paper,":[49],"we":[50,125],"a":[52,80,89],"unique":[53],"paradigm":[54],"for":[55],"named":[59],"gated":[60,104],"co-attention.":[61],"Using":[62],"our":[63,130,141],"suggested":[64],"model,":[65,91],"and":[67,83,111,135],"semantic":[68,85,113],"may":[70],"be":[71],"jointly":[72],"reasoned.":[73],"Given":[74],"features":[77,86],"extracted":[78,87],"by":[79,88],"convolutional":[81],"network":[82],"language":[90],"first":[93],"step":[94],"involves":[95],"combining":[96],"two":[98,121],"sets":[99],"features.":[101],"Second,":[102],"co-attention":[105],"stage":[106],"eliminates":[107],"irrelevant":[108],"characteristics":[110],"incorrect":[112],"data":[114],"before":[115],"fusing":[116],"knowledge":[118],"modalities.":[122],"addition,":[124],"analyze":[126],"model":[131],"several":[133],"datasets,":[134,149],"experimental":[137],"results":[138,153],"demonstrate":[139],"method":[142],"outstanding":[144],"all":[147],"seven":[148],"with":[150],"best":[152],"reached":[154],"four":[156],"datasets.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}