{"id":"https://openalex.org/W3046116040","doi":"https://doi.org/10.1145/3406971.3406981","title":"Enhancement Spatial Transformer Networks for Text Classification","display_name":"Enhancement Spatial Transformer Networks for Text Classification","publication_year":2020,"publication_date":"2020-06-26","ids":{"openalex":"https://openalex.org/W3046116040","doi":"https://doi.org/10.1145/3406971.3406981","mag":"3046116040"},"language":"en","primary_location":{"id":"doi:10.1145/3406971.3406981","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3406971.3406981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 The 4th International Conference on Graphics and Signal Processing","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/A5061396090","display_name":"Ka\u2010Hou Chan","orcid":"https://orcid.org/0000-0002-0183-0685"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Ka-Hou Chan","raw_affiliation_strings":["School of Applied Sciences, Macao Polytechnic Institute, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Applied Sciences, Macao Polytechnic Institute, Macau, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022394682","display_name":"Sio\u2010Kei Im","orcid":"https://orcid.org/0000-0002-5599-4300"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Sio-Kei Im","raw_affiliation_strings":["Macao Polytechnic Institute, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic Institute, Macau, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028723085","display_name":"Vai-Kei Ian","orcid":"https://orcid.org/0000-0003-2505-1173"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Vai-Kei Ian","raw_affiliation_strings":["School of Applied Sciences, Macao Polytechnic Institute, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Applied Sciences, Macao Polytechnic Institute, Macau, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113912447","display_name":"Ka-Man Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Ka-Man Chan","raw_affiliation_strings":["School of Applied Sciences, Macao Polytechnic Institute, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Applied Sciences, Macao Polytechnic Institute, Macau, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019419036","display_name":"Wei Ke","orcid":"https://orcid.org/0000-0003-0952-0961"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Wei Ke","raw_affiliation_strings":["School of Applied Sciences, Macao Polytechnic Institute, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Applied Sciences, Macao Polytechnic Institute, Macau, China","institution_ids":["https://openalex.org/I49835588"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I49835588"],"apc_list":null,"apc_paid":null,"fwci":0.1709,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.45842831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.77616286277771},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.7332218885421753},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6212079524993896},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5898661017417908},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5762825608253479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5458134412765503},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4866641163825989},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.48587411642074585},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.48207002878189087},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43300533294677734},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4113117754459381},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3824986517429352},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14649537205696106},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10121628642082214},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09467333555221558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77616286277771},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.7332218885421753},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6212079524993896},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5898661017417908},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5762825608253479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5458134412765503},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4866641163825989},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.48587411642074585},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.48207002878189087},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43300533294677734},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4113117754459381},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3824986517429352},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14649537205696106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10121628642082214},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09467333555221558},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3406971.3406981","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3406971.3406981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 The 4th International Conference on Graphics and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1665214252","https://openalex.org/W2053268667","https://openalex.org/W2102605133","https://openalex.org/W2112796928","https://openalex.org/W2163605009","https://openalex.org/W2279221249","https://openalex.org/W2562066862","https://openalex.org/W2576915720","https://openalex.org/W2593539516","https://openalex.org/W2601564443","https://openalex.org/W2613718673","https://openalex.org/W2734358244","https://openalex.org/W2797174799","https://openalex.org/W2899771611","https://openalex.org/W2910816794","https://openalex.org/W2959792658","https://openalex.org/W2963066927","https://openalex.org/W2963624663","https://openalex.org/W3010045995","https://openalex.org/W3106228955","https://openalex.org/W4289864664","https://openalex.org/W4293362962","https://openalex.org/W6692647644","https://openalex.org/W6743757654"],"related_works":["https://openalex.org/W2038416447","https://openalex.org/W2364151838","https://openalex.org/W2066926363","https://openalex.org/W1623358412","https://openalex.org/W2354159744","https://openalex.org/W2351539857","https://openalex.org/W2381972071","https://openalex.org/W4301382669","https://openalex.org/W2030549801","https://openalex.org/W3011293149"],"abstract_inverted_index":{"This":[0,42],"paper":[1],"introduces":[2],"a":[3,79,83,107,113],"2D":[4],"transformation":[5],"based":[6],"framework":[7],"for":[8,82,110],"arbitrary-oriented":[9,76],"text":[10,33,60,84,91],"detection":[11,92],"in":[12,63,132],"natural":[13],"scene":[14],"images.":[15],"We":[16],"present":[17],"the":[18,53,59,66,97,100,120,124,133,138],"localization":[19],"networks":[20],"within":[21],"Spatial":[22],"Transformer":[23],"Networks":[24],"(STN),":[25],"which":[26,103],"are":[27],"designed":[28],"to":[29,51,55,74,78,106],"generate":[30],"proposals":[31,54,77],"with":[32,88],"orientation":[34,67],"affine":[35],"information":[36,43],"including":[37],"translation,":[38],"scaling":[39],"and":[40,126],"rotation.":[41],"will":[44],"then":[45],"be":[46,56,129],"adapted":[47],"as":[48],"learning":[49,101],"parameters":[50],"make":[52],"fitted":[57],"into":[58],"regular":[61],"form":[62],"terms":[64],"of":[65],"more":[68],"accurately.":[69],"Localization":[70],"network":[71],"is":[72],"proposed":[73],"project":[75],"feature":[80],"map":[81],"region":[85],"classifier.":[86],"Compared":[87],"any":[89],"previous":[90],"systems,":[93],"this":[94,115],"work":[95],"ensures":[96],"relationship":[98],"between":[99],"parameters,":[102],"can":[104,128],"lead":[105],"better":[108],"approximation":[109],"orientation.":[111],"As":[112],"result,":[114],"new":[116],"layer":[117],"greatly":[118],"enhances":[119],"training":[121],"accuracy.":[122],"Moreover,":[123],"design":[125],"implementation":[127],"easily":[130],"deployed":[131],"current":[134],"systems":[135],"built":[136],"upon":[137],"standard":[139],"CNNs":[140],"architecture.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
