{"id":"https://openalex.org/W4377236343","doi":"https://doi.org/10.1145/3581807.3581808","title":"Multi-Scale Channel Attention for Chinese Scene Text Recognition","display_name":"Multi-Scale Channel Attention for Chinese Scene Text Recognition","publication_year":2022,"publication_date":"2022-11-17","ids":{"openalex":"https://openalex.org/W4377236343","doi":"https://doi.org/10.1145/3581807.3581808"},"language":"en","primary_location":{"id":"doi:10.1145/3581807.3581808","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581807.3581808","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102023722","display_name":"Haiqing Liao","orcid":"https://orcid.org/0000-0002-2815-8817"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiqing Liao","raw_affiliation_strings":["Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-2815-8817","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022975807","display_name":"Xia Du","orcid":"https://orcid.org/0000-0002-6298-846X"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia Du","raw_affiliation_strings":["Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-6298-846X","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004128654","display_name":"Yun Wu","orcid":"https://orcid.org/0000-0002-2476-7746"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Wu","raw_affiliation_strings":["Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-2476-7746","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032628425","display_name":"Da\u2010Han Wang","orcid":"https://orcid.org/0000-0002-5901-0778"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da-Han Wang","raw_affiliation_strings":["Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-5901-0778","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, China","institution_ids":["https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75867142"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9907000064849854,"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":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7807406783103943},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7344604134559631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.615967333316803},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.608189582824707},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5980976223945618},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5969516038894653},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5842443108558655},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.5613007545471191},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5472991466522217},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5019009113311768},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49398285150527954},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46945875883102417},{"id":"https://openalex.org/keywords/perspective-distortion","display_name":"Perspective distortion","score":0.4426576793193817},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39180654287338257},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3664062023162842},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34057021141052246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807406783103943},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7344604134559631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.615967333316803},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.608189582824707},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5980976223945618},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5969516038894653},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5842443108558655},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.5613007545471191},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5472991466522217},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5019009113311768},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49398285150527954},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46945875883102417},{"id":"https://openalex.org/C2779989122","wikidata":"https://www.wikidata.org/wiki/Q15889487","display_name":"Perspective distortion","level":3,"score":0.4426576793193817},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39180654287338257},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3664062023162842},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34057021141052246},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581807.3581808","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581807.3581808","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1607307044","https://openalex.org/W1686810756","https://openalex.org/W1895191496","https://openalex.org/W1922126009","https://openalex.org/W1978729128","https://openalex.org/W1998042868","https://openalex.org/W2122585011","https://openalex.org/W2128409098","https://openalex.org/W2133564696","https://openalex.org/W2146835493","https://openalex.org/W2157331557","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2239173263","https://openalex.org/W2294053032","https://openalex.org/W2412782625","https://openalex.org/W2493916176","https://openalex.org/W2609829154","https://openalex.org/W2630837129","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2799213142","https://openalex.org/W2810983211","https://openalex.org/W2904785373","https://openalex.org/W2945136398","https://openalex.org/W2959965583","https://openalex.org/W2963526661","https://openalex.org/W2970971581","https://openalex.org/W2972866811","https://openalex.org/W2973478679","https://openalex.org/W3003711889","https://openalex.org/W3004846386","https://openalex.org/W3005436539","https://openalex.org/W3028321000","https://openalex.org/W3103667010","https://openalex.org/W3119350346","https://openalex.org/W4226374800","https://openalex.org/W4236965008","https://openalex.org/W4241307704","https://openalex.org/W6649973027","https://openalex.org/W6743535247","https://openalex.org/W6743731764","https://openalex.org/W6777691785"],"related_works":["https://openalex.org/W2022849497","https://openalex.org/W2407190427","https://openalex.org/W3081299480","https://openalex.org/W2919210741","https://openalex.org/W2907584218","https://openalex.org/W3002446410","https://openalex.org/W4390224712","https://openalex.org/W4322096758","https://openalex.org/W2963517393","https://openalex.org/W2298368322"],"abstract_inverted_index":{"Scene":[0],"text":[1,56,86,146,167],"recognition":[2,17,57,87],"have":[3,24],"proven":[4],"to":[5,79,101,105,125,132],"be":[6],"highly":[7],"effective":[8],"in":[9],"solving":[10],"various":[11],"computer":[12],"vision":[13],"tasks.":[14],"Recently,":[15],"numerous":[16],"algorithms":[18],"based":[19],"on":[20],"the":[21,54,94,110,116,134,143,150,156,159,166,172],"encoder-decoder":[22],"framework":[23],"been":[25],"proposed":[26,75,151],"for":[27,62,83],"handling":[28],"scene":[29,85,145],"texts":[30],"with":[31,129],"perspective":[32],"distortion":[33],"and":[34,92,170],"curve":[35],"shape.":[36],"Nevertheless,":[37],"most":[38],"of":[39,109,136,142,158,161],"these":[40],"methods":[41,58],"only":[42],"consider":[43],"single-scale":[44],"features":[45,50,82,108,128],"while":[46,113],"not":[47],"taking":[48],"multi-scale":[49,81,107],"into":[51],"account.":[52],"Meanwhile,":[53],"existing":[55],"are":[59],"mainly":[60],"used":[61],"English":[63],"texts,":[64],"whereas":[65],"ignoring":[66],"Chinese":[67,84,144],"texts'":[68],"pivotal":[69],"role.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74,90,120],"an":[76],"end-to-end":[77],"method":[78,152],"integrate":[80],"(CSTR).":[88],"Specifically,":[89],"adopted":[91],"customized":[93],"Dense":[95],"Atrous":[96],"Spatial":[97],"Pyramid":[98],"Pooling":[99],"(DenseASPP)":[100],"our":[102],"backbone":[103],"network":[104],"capture":[106,126],"input":[111],"image":[112],"simultaneously":[114],"extending":[115],"receptive":[117],"fields.":[118],"Moreover,":[119],"added":[121],"Squeeze-and-Excitation":[122],"Networks":[123],"(SE)":[124],"attentional":[127],"global":[130],"information":[131,163],"improve":[133],"performance":[135],"CSTR":[137],"further.":[138],"The":[139],"experimental":[140],"results":[141],"datasets":[147],"demonstrate":[148],"that":[149],"can":[153],"efficiently":[154],"mitigate":[155],"impacts":[157],"loss":[160],"contextual":[162],"caused":[164],"by":[165],"scale":[168],"varying":[169],"outperforms":[171],"state-of-the-art":[173],"approaches.":[174]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}