{"id":"https://openalex.org/W4387609332","doi":"https://doi.org/10.1109/taslp.2023.3324540","title":"Modal Contrastive Learning Based End-to-End Text Image Machine Translation","display_name":"Modal Contrastive Learning Based End-to-End Text Image Machine Translation","publication_year":2023,"publication_date":"2023-10-13","ids":{"openalex":"https://openalex.org/W4387609332","doi":"https://doi.org/10.1109/taslp.2023.3324540"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3324540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3324540","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language 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/A5101810188","display_name":"Cong Ma","orcid":"https://orcid.org/0000-0002-9787-6273"},"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":"Cong Ma","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"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"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. 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, P.R. China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101714742","display_name":"Xu Han","orcid":"https://orcid.org/0009-0004-2070-1741"},"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":"Xu Han","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China","National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"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"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108067274","display_name":"L. J. Wu","orcid":"https://orcid.org/0009-0000-1053-5496"},"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":"Linghui Wu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China","National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"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"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090919681","display_name":"Yaping Zhang","orcid":"https://orcid.org/0000-0001-6892-905X"},"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":"Yaping Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China","National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"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"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992618","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0003-1028-3406"},"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":"Yang Zhao","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China","National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"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"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101763829","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0002-4911-4717"},"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":"Yu Zhou","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"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"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. 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, P.R. China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"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":"Chengqing Zong","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"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"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, P.R. 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, P.R. China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101810188"],"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":1.9136,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88837629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"2153","last_page":"2165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9993000030517578,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9977999925613403,"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":0.760707437992096},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7161821722984314},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.691469669342041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6503078937530518},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6088613867759705},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5577674508094788},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5384078025817871},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5099719762802124},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49148857593536377},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4800775647163391},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42008236050605774},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3423428237438202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760707437992096},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7161821722984314},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.691469669342041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6503078937530518},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6088613867759705},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5577674508094788},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5384078025817871},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5099719762802124},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49148857593536377},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4800775647163391},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42008236050605774},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3423428237438202},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3324540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3324540","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4930465771","display_name":null,"funder_award_id":"62106265","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W770111601","https://openalex.org/W2101105183","https://openalex.org/W2103642579","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2581101319","https://openalex.org/W2593572697","https://openalex.org/W2750938222","https://openalex.org/W2790097014","https://openalex.org/W2798991696","https://openalex.org/W2889326796","https://openalex.org/W2917551568","https://openalex.org/W2945136398","https://openalex.org/W2959965583","https://openalex.org/W2962784628","https://openalex.org/W2963517393","https://openalex.org/W2967615747","https://openalex.org/W2989322838","https://openalex.org/W3004846386","https://openalex.org/W3026732421","https://openalex.org/W3035027743","https://openalex.org/W3035169087","https://openalex.org/W3103062353","https://openalex.org/W3106271744","https://openalex.org/W3114894085","https://openalex.org/W3136420864","https://openalex.org/W3156394741","https://openalex.org/W3161816735","https://openalex.org/W3171975879","https://openalex.org/W3173783447","https://openalex.org/W3174554374","https://openalex.org/W3176463841","https://openalex.org/W3177224328","https://openalex.org/W3178360617","https://openalex.org/W3198612422","https://openalex.org/W4294170691","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6618372016","https://openalex.org/W6631190155","https://openalex.org/W6748139205","https://openalex.org/W6755559483","https://openalex.org/W6766904570","https://openalex.org/W6777837344","https://openalex.org/W6801311332","https://openalex.org/W6803187660","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2151749779","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2084768720","https://openalex.org/W2043010663"],"abstract_inverted_index":{"Text":[0,92],"image":[1,104,114,148],"machine":[2,105,149],"translation":[3,61,106],"(TIMT)":[4],"aims":[5],"at":[6],"directly":[7],"translating":[8],"text":[9,74,103,128,147],"in":[10,15],"the":[11,18,25,36,50,58,64,67,122,131,144,194],"source":[12],"language":[13],"embedded":[14],"images":[16,120],"into":[17,121],"target":[19],"language.":[20],"Most":[21],"existing":[22,171],"systems":[23],"follow":[24],"cascaded":[26],"pipeline":[27,172],"diagram":[28],"from":[29,35],"recognition":[30,59],"to":[31,52,118,193],"translation,":[32,150],"which":[33,97],"suffers":[34],"problem":[37],"of":[38,126,133,146],"error":[39],"propagation,":[40],"parameter":[41],"redundancy,":[42],"and":[43,60,70,75,108,136,156,182,188],"information":[44],"reduction.":[45],"The":[46],"end-to-end":[47,84,102,177],"model":[48,167],"has":[49],"potential":[51],"alleviate":[53],"these":[54,99],"issues":[55,100],"via":[56],"bridging":[57],"models.":[62],"However,":[63],"challenge":[65],"is":[66,116],"data":[68],"limitation":[69],"modality":[71],"gap":[72],"between":[73],"image.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80,151],"propose":[81],"a":[82],"novel":[83],"model,":[85],"namely":[86],"Modal":[87],"contrastive":[88,110,138],"learning":[89,139],"based":[90],"End-to-end":[91],"Image":[93],"Machine":[94],"Translation":[95],"(METIMT),":[96],"alleviates":[98],"through":[101],"architecture":[107],"modal":[109],"learning.":[111],"Specifically,":[112],"an":[113,134],"encoder":[115],"designed":[117],"encode":[119],"same":[123],"feature":[124],"space":[125],"corresponding":[127],"sentences,":[129],"with":[130],"guidance":[132],"intramodal":[135],"inter-modal":[137],"module.":[140],"To":[141],"further":[142],"promote":[143],"research":[145],"have":[152],"constructed":[153],"one":[154],"synthetic":[155,181],"two":[157],"real-world":[158,183],"datasets.":[159],"Extensive":[160],"experiments":[161],"show":[162],"that":[163],"our":[164],"lighter,":[165],"faster":[166],"outperforms":[168],"not":[169],"only":[170],"methods":[173],"but":[174],"also":[175],"state-of-the-art":[176],"models":[178],"on":[179],"both":[180],"evaluation":[184],"sets.":[185],"Our":[186],"code":[187],"dataset":[189],"will":[190],"be":[191],"released":[192],"public.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}