{"id":"https://openalex.org/W4311681581","doi":"https://doi.org/10.1145/3551626.3564980","title":"An End-to-End Scene Text Detector with Dynamic Attention","display_name":"An End-to-End Scene Text Detector with Dynamic Attention","publication_year":2022,"publication_date":"2022-12-07","ids":{"openalex":"https://openalex.org/W4311681581","doi":"https://doi.org/10.1145/3551626.3564980"},"language":"en","primary_location":{"id":"doi:10.1145/3551626.3564980","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3551626.3564980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","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/A5048406125","display_name":"Jingyu Lin","orcid":"https://orcid.org/0009-0006-6717-5261"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyu Lin","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044594971","display_name":"Hanzi Wang","orcid":"https://orcid.org/0000-0002-6913-9786"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzi Wang","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048406125"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1175177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"1","last_page":"7"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"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":0.9955000281333923,"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":0.8213275671005249},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6106475591659546},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5704846382141113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5458987951278687},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5090005397796631},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4699440598487854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4124853312969208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213275671005249},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6106475591659546},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5704846382141113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5458987951278687},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5090005397796631},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4699440598487854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4124853312969208},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3551626.3564980","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3551626.3564980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2143830251","display_name":null,"funder_award_id":"2020J01001","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G3488832994","display_name":null,"funder_award_id":"U21A20514, 61872307, 62071404","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"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1972065312","https://openalex.org/W2065429801","https://openalex.org/W2144506857","https://openalex.org/W2144554289","https://openalex.org/W2339589954","https://openalex.org/W2343052201","https://openalex.org/W2601564443","https://openalex.org/W2605982830","https://openalex.org/W2752782242","https://openalex.org/W2784050770","https://openalex.org/W2785383245","https://openalex.org/W2902494497","https://openalex.org/W2953606406","https://openalex.org/W2953894958","https://openalex.org/W2962766617","https://openalex.org/W2963353821","https://openalex.org/W2963647456","https://openalex.org/W2964294787","https://openalex.org/W2967615747","https://openalex.org/W2991626090","https://openalex.org/W2998621280","https://openalex.org/W3012740297","https://openalex.org/W3034514377","https://openalex.org/W3035316790","https://openalex.org/W3035679705","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3181016597","https://openalex.org/W3184364189","https://openalex.org/W3184923351","https://openalex.org/W4214627427"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2366906938","https://openalex.org/W2938107654","https://openalex.org/W4390516098","https://openalex.org/W2151749779","https://openalex.org/W2349391998","https://openalex.org/W3008587939","https://openalex.org/W4205655149","https://openalex.org/W2181948922"],"abstract_inverted_index":{"Detecting":[0],"the":[1,36,109,126,170],"arbitrarily":[2],"oriented":[3],"text":[4,18,30,37,79,181],"in":[5,12,17,152],"natural":[6,25,153],"images":[7],"is":[8],"a":[9,41,54,61,72,98,103,118,123,134,138,147],"challenging":[10],"task":[11],"multimedia":[13],"due":[14],"to":[15,34,70,107,133],"variations":[16],"curvatures,":[19],"orientations,":[20],"and":[21,74,81,114,137,143,160],"aspect":[22,46],"ratios":[23],"of":[24,111,140],"scenes.":[26,154],"Most":[27],"previous":[28,86],"scene":[29,180],"detectors":[31],"often":[32],"fail":[33],"locate":[35],"instances":[38,80],"which":[39,59],"have":[40],"peculiar":[42],"shape":[43],"(an":[44],"extreme":[45],"ratio)":[47],"precisely.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"propose":[53],"dynamic":[55,63,75],"end-to-end":[56],"framework":[57],"(DEF)":[58],"includes":[60],"convolution-based":[62],"encoder":[64],"(CDE)":[65],"with":[66,102,177],"various":[67],"attention":[68,142],"types":[69],"generate":[71],"deformable":[73],"view":[76],"for":[77,150],"multi-oriented":[78],"curve":[82],"ones.":[83],"Different":[84],"from":[85],"methods":[87],"that":[88,169],"apply":[89],"time-consuming":[90],"post-processing":[91],"steps":[92],"like":[93],"NMS,":[94],"our":[95],"method":[96,172],"uses":[97],"Transformer-based":[99],"decoder":[100],"(TD)":[101],"bipartite":[104],"matching":[105],"loss":[106],"model":[108],"relationship":[110],"corresponding":[112],"queries":[113],"ground":[115],"truths.":[116],"As":[117],"result,":[119],"by":[120],"leveraging":[121],"such":[122],"well-designed":[124],"architecture,":[125],"receptive":[127],"field":[128],"will":[129],"not":[130],"be":[131],"limited":[132],"fixed":[135],"shape,":[136],"combination":[139],"global":[141],"local":[144],"features":[145],"provides":[146],"better":[148],"representation":[149],"texts":[151],"We":[155],"conduct":[156],"extensive":[157],"experiments":[158],"qualitatively":[159],"quantitatively":[161],"on":[162],"several":[163,178],"popular":[164],"datasets.":[165],"Experimental":[166],"results":[167],"show":[168],"proposed":[171],"achieves":[173],"superior":[174],"performance":[175],"compared":[176],"state-of-the-art":[179],"detectors.":[182]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}