{"id":"https://openalex.org/W4285065310","doi":"https://doi.org/10.1109/tmm.2022.3183386","title":"Cross-Lingual Text Image Recognition via Multi-Hierarchy Cross-Modal Mimic","display_name":"Cross-Lingual Text Image Recognition via Multi-Hierarchy Cross-Modal Mimic","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W4285065310","doi":"https://doi.org/10.1109/tmm.2022.3183386"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3183386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3183386","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","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/A5106557560","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-8483-1578"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039310938","display_name":"Fei Yin","orcid":"https://orcid.org/0000-0002-6412-9140"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yin","raw_affiliation_strings":["National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101865613","display_name":"Qing Yang","orcid":"https://orcid.org/0000-0003-1947-5981"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Yang","raw_affiliation_strings":["National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100714202","display_name":"Cheng\u2010Lin Liu","orcid":"https://orcid.org/0000-0002-6743-4175"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng-Lin Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5106557560"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210100255","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.8377,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86541974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"4830","last_page":"4841"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9925000071525574,"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":0.9919000267982483,"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":0.8733258843421936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6608254909515381},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6185452938079834},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5768264532089233},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5253421664237976},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4991493225097656},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.44427019357681274},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4214697480201721},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4166065752506256},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3916354179382324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36122897267341614},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3472815752029419}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8733258843421936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6608254909515381},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6185452938079834},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5768264532089233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5253421664237976},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4991493225097656},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.44427019357681274},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4214697480201721},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4166065752506256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3916354179382324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36122897267341614},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3472815752029419},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3183386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3183386","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G2601674282","display_name":null,"funder_award_id":"2020AAA0108003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3418581704","display_name":null,"funder_award_id":"61733007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6431871145","display_name":null,"funder_award_id":"61721004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W753847829","https://openalex.org/W1491389626","https://openalex.org/W1522301498","https://openalex.org/W1569095176","https://openalex.org/W1686810756","https://openalex.org/W1753482797","https://openalex.org/W1821462560","https://openalex.org/W2101105183","https://openalex.org/W2122585011","https://openalex.org/W2125389028","https://openalex.org/W2133564696","https://openalex.org/W2134797427","https://openalex.org/W2157331557","https://openalex.org/W2194187530","https://openalex.org/W2547080737","https://openalex.org/W2565591417","https://openalex.org/W2593539516","https://openalex.org/W2613904329","https://openalex.org/W2751748110","https://openalex.org/W2785979806","https://openalex.org/W2787062907","https://openalex.org/W2790097014","https://openalex.org/W2803696107","https://openalex.org/W2810983211","https://openalex.org/W2886300652","https://openalex.org/W2895918973","https://openalex.org/W2896457183","https://openalex.org/W2924515500","https://openalex.org/W2950111065","https://openalex.org/W2962793481","https://openalex.org/W2963073217","https://openalex.org/W2963299454","https://openalex.org/W2963866045","https://openalex.org/W2966792645","https://openalex.org/W2971047694","https://openalex.org/W2981801509","https://openalex.org/W2996844526","https://openalex.org/W3002575754","https://openalex.org/W3005724337","https://openalex.org/W3034203264","https://openalex.org/W3035106683","https://openalex.org/W3044641008","https://openalex.org/W3046835050","https://openalex.org/W3082397598","https://openalex.org/W3089472875","https://openalex.org/W3090350559","https://openalex.org/W3092309237","https://openalex.org/W3106228955","https://openalex.org/W3106321930","https://openalex.org/W3125519332","https://openalex.org/W3161816735","https://openalex.org/W4288333985","https://openalex.org/W4295312788","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6629590909","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6637698695","https://openalex.org/W6678815747","https://openalex.org/W6679434410","https://openalex.org/W6679909955","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6744179516","https://openalex.org/W6755207826","https://openalex.org/W6762572962","https://openalex.org/W6766978945","https://openalex.org/W6772088657","https://openalex.org/W6774131485","https://openalex.org/W6781722990"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2292997772","https://openalex.org/W2794347674","https://openalex.org/W3152052241","https://openalex.org/W3175595715","https://openalex.org/W3108641831","https://openalex.org/W4285266806","https://openalex.org/W4297200203","https://openalex.org/W2006337894","https://openalex.org/W2150143935"],"abstract_inverted_index":{"Optical":[0],"character":[1],"recognition":[2,24,63],"and":[3,9,46,64,74,103,136,142,153],"machine":[4,117,218],"translation":[5,66,118,219],"are":[6],"usually":[7],"studied":[8],"applied":[10],"separately.":[11],"In":[12,112],"this":[13,35,113],"paper,":[14],"we":[15,82],"consider":[16],"a":[17,84,98,104,115,123,162,188,213],"new":[18],"problem":[19,36],"named":[20],"cross-lingual":[21],"text":[22,61,65,101,110,137,210,222],"image":[23,62,135],"(CLTIR)":[25],"that":[26,204],"integrates":[27],"these":[28,80],"two":[29],"tasks":[30],"together.":[31],"The":[32,198],"core":[33],"of":[34,107,169,200],"is":[37,120],"to":[38,49,71,125,192,216],"recognize":[39],"source":[40],"language":[41,52],"texts":[42],"shown":[43],"in":[44,53,156,212],"images":[45,211],"transcribe":[47],"them":[48],"the":[50,127,145,157,167,170,183,195,205,217],"target":[51],"an":[54],"end-to-end":[55,91],"manner.":[56],"Traditional":[57],"cascaded":[58],"systems":[59],"perform":[60],"sequentially.":[67],"This":[68],"can":[69,94,149,186,208],"lead":[70],"error":[72],"accumulation":[73],"parameter":[75],"redundancy":[76],"problems.":[77],"To":[78],"overcome":[79],"problems,":[81],"propose":[83],"multihierarchy":[85],"cross-modal":[86],"mimic":[87,147],"(MHCMM)":[88],"framework":[89,185],"for":[90,130],"CLTIR,":[92],"which":[93],"be":[95],"trained":[96],"with":[97,134],"massive":[99],"bilingual":[100,108,190],"corpus":[102,191],"small":[105],"number":[106],"annotated":[109],"images.":[111],"framework,":[114],"plug-in":[116],"model":[119,129,207,220],"used":[121],"as":[122],"teacher":[124],"guide":[126],"CLTIR":[128],"learning":[131,141],"representations":[132],"compatible":[133],"modes.":[138],"Via":[139],"adversarial":[140],"attention":[143,201],"mechanisms,":[144],"proposed":[146,171,206],"method":[148,174],"integrate":[150],"both":[151],"global":[152],"local":[154],"information":[155],"semantic":[158],"space.":[159],"Experiments":[160],"on":[161],"newly":[163],"collected":[164],"dataset":[165],"demonstrate":[166],"superiority":[168],"framework.":[172],"Our":[173],"outperforms":[175],"other":[176],"pipelines":[177],"while":[178],"containing":[179],"fewer":[180],"parameters.":[181],"Additionally,":[182],"MHCMM":[184],"utilize":[187],"large-scale":[189],"further":[193],"improve":[194],"performance":[196],"efficiently.":[197],"visualization":[199],"scores":[202],"indicates":[203],"read":[209],"fashion":[214],"similar":[215],"reading":[221],"tokens.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}