{"id":"https://openalex.org/W4387968220","doi":"https://doi.org/10.1145/3581783.3611791","title":"Fine-grained Pseudo Labels for Scene Text Recognition","display_name":"Fine-grained Pseudo Labels for Scene Text Recognition","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968220","doi":"https://doi.org/10.1145/3581783.3611791"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611791","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5065310372","display_name":"X. Li","orcid":"https://orcid.org/0009-0009-8827-0040"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaoyu Li","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034682874","display_name":"Xiaoxue Chen","orcid":"https://orcid.org/0009-0000-1725-3184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxue Chen","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090282814","display_name":"Zuming Huang","orcid":"https://orcid.org/0009-0003-4348-229X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuming Huang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072757173","display_name":"Lele Xie","orcid":"https://orcid.org/0000-0001-7731-9341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lele Xie","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014922345","display_name":"Jingdong Chen","orcid":"https://orcid.org/0000-0002-1872-2592"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingdong Chen","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019934281","display_name":"Ming Yang","orcid":"https://orcid.org/0000-0003-1691-6817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5065310372"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2407,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53626164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5786","last_page":"5795"},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9835000038146973,"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":0.7995245456695557},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.6552252769470215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6497009992599487},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5566344857215881},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5029203295707703},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4805365204811096},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.47044697403907776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46555736660957336},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4314541220664978},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4216432273387909},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3776933252811432},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3585144877433777},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32983025908470154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.09510418772697449},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0775880515575409}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995245456695557},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.6552252769470215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6497009992599487},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5566344857215881},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5029203295707703},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4805365204811096},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.47044697403907776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46555736660957336},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4314541220664978},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4216432273387909},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3776933252811432},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3585144877433777},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32983025908470154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.09510418772697449},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0775880515575409},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611791","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2127141656","https://openalex.org/W2144554289","https://openalex.org/W2152928267","https://openalex.org/W2194187530","https://openalex.org/W2296073425","https://openalex.org/W2343052201","https://openalex.org/W2345837149","https://openalex.org/W2750938222","https://openalex.org/W2810983211","https://openalex.org/W2959965583","https://openalex.org/W2998382406","https://openalex.org/W3025872686","https://openalex.org/W3091002423","https://openalex.org/W3102178856","https://openalex.org/W3106271744","https://openalex.org/W3122930709","https://openalex.org/W3163170479","https://openalex.org/W3169879351","https://openalex.org/W3175855397","https://openalex.org/W3177684257","https://openalex.org/W3202415716","https://openalex.org/W4221161877","https://openalex.org/W4226329156","https://openalex.org/W4312965673","https://openalex.org/W4312993742","https://openalex.org/W4319300269","https://openalex.org/W4386065575","https://openalex.org/W6600339963"],"related_works":["https://openalex.org/W4251972423","https://openalex.org/W1503216044","https://openalex.org/W1554561885","https://openalex.org/W3035097673","https://openalex.org/W4287800519","https://openalex.org/W2530675634","https://openalex.org/W3022333975","https://openalex.org/W2250623963","https://openalex.org/W4392918422","https://openalex.org/W4384786634"],"abstract_inverted_index":{"Pseudo-Labeling":[0,36,77,125],"based":[1],"semi-supervised":[2,69],"learning":[3,166],"has":[4,54],"shown":[5],"promising":[6],"advantages":[7],"in":[8,37,60,68,108],"Scene":[9],"Text":[10],"Recognition":[11],"(STR).":[12],"Most":[13],"of":[14,94,111,136,184],"them":[15],"usually":[16],"use":[17],"a":[18,38,51,122],"pre-trained":[19],"model":[20,43],"to":[21,76,91,163,175,197,212],"generate":[22],"sequence-level":[23,89],"pseudo":[24,48,84,113,146,185],"labels":[25,49,85],"for":[26,128,158],"text":[27,130],"images":[28],"and":[29,64,104,142,180],"then":[30],"re-train":[31],"the":[32,47,87,98,117,140,156,164,177,182],"model.":[33],"Recently,":[34],"conducting":[35],"teacher-student":[39],"framework":[40,74],"(a":[41],"student":[42],"is":[44,173],"supervised":[45],"by":[46],"from":[50],"teacher":[52],"model)":[53],"become":[55],"increasingly":[56],"popular,":[57],"which":[58,132],"trains":[59],"an":[61,169],"end-to-end":[62],"manner":[63],"yields":[65],"outstanding":[66],"performance":[67],"learning.":[70],"However,":[71],"applying":[72],"this":[73],"directly":[75],"STR":[78,195,204],"exhibits":[79],"unstable":[80],"convergence,":[81],"as":[82],"generating":[83],"at":[86,139],"coarse-grained":[88],"leads":[90],"inefficient":[92],"utilization":[93,135],"unlabelled":[95],"data.":[96],"Furthermore,":[97],"inherent":[99],"domain":[100,178],"shift":[101],"between":[102],"labeled":[103],"unlabeled":[105,137],"data":[106,138],"results":[107,200],"low":[109],"quality":[110,183],"derived":[112],"labels.":[114,147,186],"To":[115],"mitigate":[116],"above":[118],"issues,":[119],"we":[120],"propose":[121],"novel":[123],"Cross-domain":[124],"(CPL)":[126],"approach":[127],"scene":[129],"recognition,":[131],"makes":[133],"better":[134],"character-level":[141],"provides":[143],"more":[144],"accurate":[145],"Specifically,":[148],"our":[149],"proposed":[150],"Pseudo-Labeled":[151],"Curriculum":[152],"Learning":[153],"dynamically":[154],"adjusts":[155],"thresholds":[157],"different":[159],"character":[160],"classes":[161],"according":[162],"model's":[165],"status.":[167],"Moreover,":[168],"Adaptive":[170],"Distribution":[171],"Regularizer":[172],"employed":[174],"bridge":[176],"gap":[179],"improve":[181],"Extensive":[187],"experiments":[188],"show":[189],"that":[190],"CPL":[191],"boosts":[192],"those":[193],"representative":[194],"models":[196],"achieve":[198],"state-of-the-art":[199],"on":[201],"six":[202],"challenging":[203],"benchmarks.":[205],"Besides,":[206],"it":[207],"can":[208],"be":[209],"effectively":[210],"generalized":[211],"handwritten":[213],"text.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}