{"id":"https://openalex.org/W4387580232","doi":"https://doi.org/10.1145/3625822","title":"Reading Scene Text with Aggregated Temporal Convolutional Encoder","display_name":"Reading Scene Text with Aggregated Temporal Convolutional Encoder","publication_year":2023,"publication_date":"2023-10-12","ids":{"openalex":"https://openalex.org/W4387580232","doi":"https://doi.org/10.1145/3625822"},"language":"en","primary_location":{"id":"doi:10.1145/3625822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625822","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5103028836","display_name":"Tianlong Ma","orcid":"https://orcid.org/0000-0003-4079-7897"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlong Ma","raw_affiliation_strings":["School of Computer Science, Fudan University, China"],"raw_orcid":"https://orcid.org/0000-0003-4079-7897","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047942518","display_name":"Xiangcheng Du","orcid":"https://orcid.org/0000-0002-4268-6114"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangcheng Du","raw_affiliation_strings":["School of Computer Science, Fudan University, China"],"raw_orcid":"https://orcid.org/0000-0002-4268-6114","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043728985","display_name":"Xingjiao Wu","orcid":"https://orcid.org/0000-0001-9146-051X"},"institutions":[{"id":"https://openalex.org/I2800393352","display_name":"China Tourism Academy","ror":"https://ror.org/01k4abj61","country_code":"CN","type":"government","lineage":["https://openalex.org/I2800393352"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjiao Wu","raw_affiliation_strings":["School of Computer Science, Fudan University & Technology Innovation Center of Digital Creation and Applications of Chinese Calligraphy and Painting, Ministry of Culture and Tourism, China"],"raw_orcid":"https://orcid.org/0000-0001-9146-051X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University & Technology Innovation Center of Digital Creation and Applications of Chinese Calligraphy and Painting, Ministry of Culture and Tourism, China","institution_ids":["https://openalex.org/I2800393352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665357","display_name":"Zhao Zhou","orcid":"https://orcid.org/0000-0001-7069-6275"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Zhou","raw_affiliation_strings":["School of Computer Science, Fudan University, China"],"raw_orcid":"https://orcid.org/0000-0001-7069-6275","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056833841","display_name":"Yingbin Zheng","orcid":"https://orcid.org/0000-0002-5590-9292"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingbin Zheng","raw_affiliation_strings":["Videt Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-5590-9292","affiliations":[{"raw_affiliation_string":"Videt Technology, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100625873","display_name":"Cheng Jin","orcid":"https://orcid.org/0000-0003-3063-1957"},"institutions":[{"id":"https://openalex.org/I2800393352","display_name":"China Tourism Academy","ror":"https://ror.org/01k4abj61","country_code":"CN","type":"government","lineage":["https://openalex.org/I2800393352"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Jin","raw_affiliation_strings":["School of Computer Science, Fudan University & Technology Innovation Center of Digital Creation and Applications of Chinese Calligraphy and Painting, Ministry of Culture and Tourism, China"],"raw_orcid":"https://orcid.org/0000-0003-3063-1957","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University & Technology Innovation Center of Digital Creation and Applications of Chinese Calligraphy and Painting, Ministry of Culture and Tourism, China","institution_ids":["https://openalex.org/I2800393352"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4254,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62849106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"11","first_page":"1","last_page":"16"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9952999949455261,"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":0.9922999739646912,"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":0.8252393007278442},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.8029961585998535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.599541425704956},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5510714650154114},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.545984148979187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4981222152709961},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4904741942882538},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47464829683303833},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4722321033477783},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46293893456459045},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4521191716194153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3428456783294678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3323298692703247},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12988775968551636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252393007278442},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8029961585998535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.599541425704956},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5510714650154114},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.545984148979187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4981222152709961},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4904741942882538},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47464829683303833},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4722321033477783},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46293893456459045},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4521191716194153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3428456783294678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3323298692703247},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12988775968551636},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625822","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[{"id":"https://openalex.org/G6701200520","display_name":null,"funder_award_id":"12511505303","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1491389626","https://openalex.org/W1903029394","https://openalex.org/W2127141656","https://openalex.org/W2186222003","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2284481408","https://openalex.org/W2343052201","https://openalex.org/W2518164973","https://openalex.org/W2559655401","https://openalex.org/W2565639579","https://openalex.org/W2593539516","https://openalex.org/W2599337667","https://openalex.org/W2602753196","https://openalex.org/W2604292070","https://openalex.org/W2612690371","https://openalex.org/W2735457106","https://openalex.org/W2752782242","https://openalex.org/W2785631370","https://openalex.org/W2810983211","https://openalex.org/W2884585870","https://openalex.org/W2962790387","https://openalex.org/W2963526661","https://openalex.org/W2998382406","https://openalex.org/W3018001946","https://openalex.org/W3025830232","https://openalex.org/W3034447740","https://openalex.org/W3043311956","https://openalex.org/W3045717997","https://openalex.org/W3106228955","https://openalex.org/W3173107258","https://openalex.org/W3181676856","https://openalex.org/W4224305666","https://openalex.org/W4226374800","https://openalex.org/W4236965008","https://openalex.org/W4301185181","https://openalex.org/W4303185326","https://openalex.org/W4308391738","https://openalex.org/W4377021651","https://openalex.org/W6640226783"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W4243305035","https://openalex.org/W2379407973","https://openalex.org/W2964954556"],"abstract_inverted_index":{"Reading":[0],"scene":[1,31,162],"text":[2,32,155,163],"in":[3,11,106,149],"the":[4,36,41,45,50,54,76,80,96,102,107,128,143,171,174,182],"natural":[5],"image":[6],"is":[7,117],"of":[8,53,112,145,184],"fundamental":[9],"importance":[10],"many":[12],"real-world":[13],"problems.":[14],"Text":[15],"recognition":[16,33,164],"has":[17],"a":[18,62,70,84],"profound":[19],"effect":[20],"on":[21,49,160],"information":[22,137],"processing":[23],"by":[24,43,126],"enabling":[25],"automated":[26],"extraction":[27],"and":[28,57,79,169,181],"interpretation.":[29],"Recent":[30],"methods":[34],"employ":[35],"encoder-decoder":[37],"framework,":[38],"which":[39],"constructs":[40],"encoder":[42,72,108],"obtaining":[44],"visual":[46,121],"representations":[47],"based":[48],"last":[51],"layer":[52],"backbone":[55],"network":[56],"then":[58],"feeding":[59],"them":[60],"into":[61],"sequence":[63,81],"model.":[64],"In":[65],"this":[66],"article,":[67],"we":[68],"propose":[69],"novel":[71],"structure":[73],"that":[74],"performs":[75],"feature":[77],"extractor":[78],"modeling":[82],"within":[83],"unified":[85],"framework.":[86],"The":[87,110],"introduced":[88],"Aggregated":[89],"Temporal":[90],"Convolutional":[91],"Encoder":[92],"(ATCE)":[93],"first":[94],"incorporates":[95],"temporal":[97,104,114],"convolutional":[98,150],"layers":[99],"to":[100,119,134],"consider":[101],"long-term":[103],"relationship":[105],"stage.":[109],"aggregation":[111,133],"these":[113],"convolution":[115],"modules":[116,148],"designed":[118],"utilize":[120],"features":[122],"from":[123],"different":[124,146,178],"levels,":[125],"augmenting":[127],"standard":[129],"architecture":[130],"with":[131,177],"deeper":[132],"better":[135],"fuse":[136],"across":[138],"modules.":[139],"We":[140,157],"also":[141],"study":[142],"impact":[144],"attention":[147],"blocks":[151],"for":[152,166],"learning":[153],"accurate":[154],"representations.":[156],"conduct":[158],"comparisons":[159],"several":[161],"benchmarks":[165],"both":[167],"Chinese":[168],"English;":[170],"experiments":[172],"demonstrate":[173],"complementary":[175],"ability":[176],"decoder":[179],"variants":[180],"effectiveness":[183],"our":[185],"proposed":[186],"approach.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}