{"id":"https://openalex.org/W4375869061","doi":"https://doi.org/10.1109/icassp49357.2023.10096434","title":"A3S: Adversarial Learning of Semantic Representations for Scene-Text Spotting","display_name":"A3S: Adversarial Learning of Semantic Representations for Scene-Text Spotting","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869061","doi":"https://doi.org/10.1109/icassp49357.2023.10096434"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5051026262","display_name":"Masato Fujitake","orcid":"https://orcid.org/0000-0001-7702-499X"},"institutions":[{"id":"https://openalex.org/I4210165760","display_name":"College of Accounting","ror":"https://ror.org/01e5pnf26","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210165760"]}],"countries":["SI"],"is_corresponding":true,"raw_author_name":"Masato Fujitake","raw_affiliation_strings":["Fast Accounting Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Fast Accounting Co., Ltd","institution_ids":["https://openalex.org/I4210165760"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051026262"],"corresponding_institution_ids":["https://openalex.org/I4210165760"],"apc_list":null,"apc_paid":null,"fwci":0.9839,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77201331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9700000286102295,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9562000036239624,"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/spotting","display_name":"Spotting","score":0.9100527763366699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8246102333068848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7089024186134338},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6033488512039185},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5866354703903198},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.5865815877914429},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5353572368621826},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.43643930554389954},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42964881658554077},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4284767508506775},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37242186069488525},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.37207064032554626},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09171879291534424}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9100527763366699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246102333068848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7089024186134338},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6033488512039185},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5866354703903198},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.5865815877914429},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5353572368621826},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.43643930554389954},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42964881658554077},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4284767508506775},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37242186069488525},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37207064032554626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09171879291534424},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"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":33,"referenced_works":["https://openalex.org/W2144554289","https://openalex.org/W2194187530","https://openalex.org/W2250539671","https://openalex.org/W2550687635","https://openalex.org/W2565639579","https://openalex.org/W2605982830","https://openalex.org/W2896457183","https://openalex.org/W2914492226","https://openalex.org/W2964018263","https://openalex.org/W2964296749","https://openalex.org/W2965463054","https://openalex.org/W2988098900","https://openalex.org/W3096831136","https://openalex.org/W3110398855","https://openalex.org/W3111172959","https://openalex.org/W3152831436","https://openalex.org/W3160791979","https://openalex.org/W3196976036","https://openalex.org/W3217601980","https://openalex.org/W4206184212","https://openalex.org/W4225683503","https://openalex.org/W4254298996","https://openalex.org/W4312230431","https://openalex.org/W4312880451","https://openalex.org/W4385245566","https://openalex.org/W6730903564","https://openalex.org/W6736305252","https://openalex.org/W6739901393","https://openalex.org/W6747319813","https://openalex.org/W6755207826","https://openalex.org/W6804526531","https://openalex.org/W6810681906","https://openalex.org/W6810854768"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638","https://openalex.org/W1989658893"],"abstract_inverted_index":{"Scene-text":[0],"spotting":[1,90],"is":[2,50,55],"a":[3,7,66,72,77],"task":[4],"that":[5,127],"predicts":[6,101],"text":[8,17,40,44,89,97,107,113],"area":[9,108],"on":[10,38,116,122],"natural":[11,59],"scene":[12,60,88],"images":[13,61],"and":[14],"recognizes":[15],"its":[16,30],"characters":[18,70],"simultaneously.":[19],"It":[20],"has":[21,35],"attracted":[22],"much":[23],"attention":[24],"in":[25,58,104],"recent":[26],"years":[27],"due":[28],"to":[29,63,92],"wide":[31],"applications.":[32],"Existing":[33],"research":[34],"mainly":[36],"focused":[37],"improving":[39],"region":[41],"detection,":[42],"not":[43,64],"recognition.":[45,98],"Thus,":[46],"while":[47],"detection":[48],"accuracy":[49,54,133],"improved,":[51],"the":[52,105,128],"end-to-end":[53,94],"insufficient.":[56],"Texts":[57],"tend":[62],"be":[65],"random":[67],"string":[68,74],"of":[69,75,84,110],"but":[71],"meaningful":[73],"characters,":[76],"word.":[78],"Therefore,":[79],"we":[80],"propose":[81],"adversarial":[82],"learning":[83],"semantic":[85,102],"representations":[86],"for":[87],"(A3S)":[91],"improve":[93],"accuracy,":[95],"including":[96],"A3S":[99],"simultaneously":[100],"features":[103],"detected":[106],"instead":[109],"only":[111],"performing":[112],"recognition":[114],"based":[115],"existing":[117],"visual":[118],"features.":[119],"Experimental":[120],"results":[121],"publicly":[123],"available":[124],"datasets":[125],"show":[126],"proposed":[129],"method":[130],"achieves":[131],"better":[132],"than":[134],"other":[135],"methods.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}