{"id":"https://openalex.org/W3092863018","doi":"https://doi.org/10.1145/3394171.3413913","title":"LAL: Linguistically Aware Learning for Scene Text Recognition","display_name":"LAL: Linguistically Aware Learning for Scene Text Recognition","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092863018","doi":"https://doi.org/10.1145/3394171.3413913","mag":"3092863018"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413913","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394171.3413913","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394171.3413913","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/10.1145/3394171.3413913","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101675150","display_name":"Yi Zheng","orcid":"https://orcid.org/0000-0001-5547-0956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Zheng","raw_affiliation_strings":["Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085882524","display_name":"Wenda Qin","orcid":"https://orcid.org/0000-0001-9265-6899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenda Qin","raw_affiliation_strings":["Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027174211","display_name":"Derry Wijaya","orcid":"https://orcid.org/0000-0002-0848-4703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Derry Wijaya","raw_affiliation_strings":["Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058798782","display_name":"Margrit Betke","orcid":"https://orcid.org/0000-0002-4491-6868"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Margrit Betke","raw_affiliation_strings":["Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4051","last_page":"4059"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9914000034332275,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9783999919891357,"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":0.8123890161514282},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7181396484375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6673257350921631},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5468591451644897},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5378038287162781},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.528694748878479},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.520017147064209},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.4870612919330597},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4371386766433716},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4315357506275177},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41425955295562744},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41404855251312256},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.40421780943870544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.384403795003891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123890161514282},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7181396484375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6673257350921631},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5468591451644897},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5378038287162781},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.528694748878479},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.520017147064209},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.4870612919330597},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4371386766433716},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4315357506275177},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41425955295562744},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41404855251312256},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40421780943870544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.384403795003891},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413913","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394171.3413913","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394171.3413913","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3394171.3413913","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394171.3413913","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394171.3413913","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2140357557","display_name":null,"funder_award_id":"N00014-19-1-2571","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"},{"id":"https://openalex.org/G2680810362","display_name":null,"funder_award_id":"AUSMURIB000001","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3024551116","display_name":null,"funder_award_id":"N00014-19-1-2571","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5094092752","display_name":null,"funder_award_id":"MURI N00014-19-1-2571","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6346747064","display_name":"BIGDATA: IA: Multiplatform, Multilingual, and Multimodal Tools for Analyzing Public Communication in over 100 Languages","funder_award_id":"1838193","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3092863018.pdf","grobid_xml":"https://content.openalex.org/works/W3092863018.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W179875071","https://openalex.org/W603908379","https://openalex.org/W1491389626","https://openalex.org/W1924770834","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1988461287","https://openalex.org/W1998042868","https://openalex.org/W2031648200","https://openalex.org/W2064675550","https://openalex.org/W2128409098","https://openalex.org/W2146835493","https://openalex.org/W2160927412","https://openalex.org/W2194187530","https://openalex.org/W2402268235","https://openalex.org/W2550687635","https://openalex.org/W2593572697","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2755558557","https://openalex.org/W2768779776","https://openalex.org/W2788069964","https://openalex.org/W2810983211","https://openalex.org/W2899368669","https://openalex.org/W2949650786","https://openalex.org/W2952285877","https://openalex.org/W2952302849","https://openalex.org/W2952439627","https://openalex.org/W2953022181","https://openalex.org/W2962773189","https://openalex.org/W2963403868","https://openalex.org/W2963517393","https://openalex.org/W2963712589","https://openalex.org/W2964308564","https://openalex.org/W2965097167","https://openalex.org/W2967615747","https://openalex.org/W3034230962","https://openalex.org/W4248839592","https://openalex.org/W6600529467"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"Scene":[0],"text":[1,22,33,44,164,169],"recognition":[2,34,74],"is":[3,160],"the":[4,19,49,140],"task":[5],"of":[6,12,21,108],"recognizing":[7],"character":[8,39,51],"sequences":[9,52],"in":[10,18,23,166],"images":[11],"natural":[13],"scenes.":[14],"The":[15],"considerable":[16],"diversity":[17],"appearance":[20],"a":[24,54,62,87,98,144,151,163,167],"scene":[25],"image":[26],"and":[27,69,90,94,134,154],"potentially":[28],"highly":[29],"complex":[30],"backgrounds":[31],"make":[32],"challenging.":[35],"Previous":[36],"approaches":[37],"employ":[38],"sequence":[40],"generators":[41],"to":[42,72],"analyze":[43],"regions":[45],"and,":[46],"subsequently,":[47],"compare":[48],"candidate":[50],"against":[53],"language":[55],"model.":[56,102],"In":[57],"this":[58],"work,":[59],"we":[60],"propose":[61],"bimodal":[63,141],"framework":[64],"that":[65,121,139],"simultaneously":[66],"utilizes":[67],"visual":[68,84],"linguistic":[70,95],"information":[71],"enhance":[73],"performance.":[75],"Our":[76,114],"linguistically":[77],"aware":[78],"learning":[79],"(LAL)":[80],"method":[81,123],"effectively":[82],"learns":[83],"embeddings":[85,112],"using":[86,97],"rectifier,":[88],"encoder,":[89],"attention":[91],"decoder":[92],"approach,":[93],"embeddings,":[96],"deep":[99],"next-character":[100],"prediction":[101],"We":[103,137,148],"present":[104],"an":[105],"innovative":[106],"way":[107],"combining":[109],"these":[110],"two":[111],"effectively.":[113],"experiments":[115],"on":[116,131],"eight":[117],"standard":[118],"benchmarks":[119],"show":[120,138,155],"our":[122],"outperforms":[124],"previous":[125],"methods":[126],"by":[127],"large":[128],"margins,":[129],"particularly":[130],"rotated,":[132],"foreshortened,":[133],"curved":[135],"text.":[136],"approach":[142],"has":[143],"statistically":[145],"significant":[146],"impact.":[147],"also":[149],"contribute":[150],"new":[152],"dataset,":[153],"robust":[156],"performance":[157],"when":[158],"LAL":[159],"combined":[161],"with":[162],"detector":[165],"pipelined":[168],"spotting":[170],"framework.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}