{"id":"https://openalex.org/W2740767790","doi":"https://doi.org/10.24963/ijcai.2017/458","title":"Learning to Read Irregular Text with Attention Mechanisms","display_name":"Learning to Read Irregular Text with Attention Mechanisms","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740767790","doi":"https://doi.org/10.24963/ijcai.2017/458","mag":"2740767790"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/458","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/458","pdf_url":"https://www.ijcai.org/proceedings/2017/0458.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0458.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044694251","display_name":"Xiao Yang","orcid":"https://orcid.org/0000-0003-2136-3014"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Yang","raw_affiliation_strings":["The Pennsylvania State University","The Pennsylvania State University, University Park, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087598861","display_name":"Dafang He","orcid":"https://orcid.org/0000-0002-4049-9729"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dafang He","raw_affiliation_strings":["The Pennsylvania State University","The Pennsylvania State University, University Park, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001762730","display_name":"Zihan Zhou","orcid":"https://orcid.org/0000-0002-1697-2168"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihan Zhou","raw_affiliation_strings":["The Pennsylvania State University","The Pennsylvania State University, University Park, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005431144","display_name":"Daniel Kifer","orcid":"https://orcid.org/0000-0002-4611-7066"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Kifer","raw_affiliation_strings":["The Pennsylvania State University","The Pennsylvania State University, University Park, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University","The Pennsylvania State University, University Park, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":208,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3280","last_page":"3286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.9958999752998352,"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":0.9911999702453613,"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":0.778337836265564},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.672439455986023},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6244503259658813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6019866466522217},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5446481108665466},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5284411907196045},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5046104192733765},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.49286389350891113},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4606582820415497},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4407118558883667},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4127178490161896},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38461846113204956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34168630838394165},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.290388822555542},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09353801608085632},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08008497953414917},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07628607749938965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778337836265564},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.672439455986023},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6244503259658813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6019866466522217},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5446481108665466},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5284411907196045},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5046104192733765},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.49286389350891113},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4606582820415497},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4407118558883667},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4127178490161896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38461846113204956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34168630838394165},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.290388822555542},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09353801608085632},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08008497953414917},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07628607749938965},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/458","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/458","pdf_url":"https://www.ijcai.org/proceedings/2017/0458.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/458","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/458","pdf_url":"https://www.ijcai.org/proceedings/2017/0458.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[{"id":"https://openalex.org/G5322324752","display_name":null,"funder_award_id":"CCF 1317560","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6193076742","display_name":"Collaborative Research: Visual Cortex on Silicon","funder_award_id":"1317560","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740767790.pdf","grobid_xml":"https://content.openalex.org/works/W2740767790.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W70975097","https://openalex.org/W1491389626","https://openalex.org/W1514535095","https://openalex.org/W1607307044","https://openalex.org/W1639961155","https://openalex.org/W1686810756","https://openalex.org/W1745334888","https://openalex.org/W1903029394","https://openalex.org/W1922126009","https://openalex.org/W1924985727","https://openalex.org/W1971822075","https://openalex.org/W1978729128","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2019393228","https://openalex.org/W2061802763","https://openalex.org/W2099355420","https://openalex.org/W2108598243","https://openalex.org/W2122221966","https://openalex.org/W2127141656","https://openalex.org/W2140132917","https://openalex.org/W2146835493","https://openalex.org/W2172140247","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2294059674","https://openalex.org/W2298368322","https://openalex.org/W2322480645","https://openalex.org/W2343052201","https://openalex.org/W2407521645","https://openalex.org/W2950800384","https://openalex.org/W2952302849","https://openalex.org/W2952439627","https://openalex.org/W2962790387","https://openalex.org/W2963517393","https://openalex.org/W2964199361","https://openalex.org/W4239072543","https://openalex.org/W4308909683"],"related_works":["https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W1503216044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W2366269494","https://openalex.org/W2353650902","https://openalex.org/W2347884623","https://openalex.org/W3015404287"],"abstract_inverted_index":{"We":[0,104],"present":[1],"a":[2],"robust":[3],"end-to-end":[4],"neural-based":[5],"model":[6,127],"to":[7,54,66,84,97],"attentively":[8],"recognize":[9],"text":[10,39,48,56,86,124],"in":[11,32],"natural":[12],"images.":[13],"Particularly,":[14],"we":[15],"focus":[16],"on":[17,38,131,142],"accurately":[18],"identifying":[19],"irregular":[20,123],"(perspectively":[21],"distorted":[22],"or":[23,60],"curved)":[24],"text,":[25],"which":[26],"has":[27],"not":[28,51],"been":[29],"well":[30],"addressed":[31],"the":[33,98],"previous":[34,129],"literature.":[35],"Previous":[36],"research":[37],"reading":[40],"often":[41],"works":[42],"with":[43,57,106],"regular":[44],"(horizontal":[45],"and":[46,49,118,136,138,149],"frontal)":[47],"does":[50],"adequately":[52],"generalize":[53],"processing":[55],"perspective":[58],"distortion":[59],"curving":[61],"effects.":[62],"Our":[63,126],"work":[64,130],"proposes":[65],"overcome":[67],"this":[68],"difficulty":[69],"by":[70],"introducing":[71],"two":[72,110,132],"learning":[73],"components:":[74],"(1)":[75],"an":[76,91,101],"auxiliary":[77],"dense":[78],"character":[79],"detection":[80],"task":[81],"that":[82,94,108],"helps":[83],"learn":[85],"specific":[87],"visual":[88],"patterns,":[89],"(2)":[90],"alignment":[92],"loss":[93],"provides":[95],"guidance":[96],"training":[99],"of":[100],"attention":[102],"model.":[103],"show":[105],"experiments":[107],"these":[109],"components":[111],"are":[112],"crucial":[113],"for":[114,122],"achieving":[115],"fast":[116],"convergence":[117],"high":[119],"classification":[120],"accuracy":[121],"recognition.":[125],"outperforms":[128],"irregular-text":[133],"datasets:":[134],"SVT-Perspective":[135],"CUTE80,":[137],"is":[139],"also":[140],"highly-competitive":[141],"several":[143],"regular-text":[144],"datasets":[145],"containing":[146],"primarily":[147],"horizontal":[148],"frontal":[150],"text.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":45},{"year":2020,"cited_by_count":48},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}