{"id":"https://openalex.org/W3033615934","doi":"https://doi.org/10.1145/3372278.3390717","title":"A Coordinated Representation Learning Enhanced Multimodal Machine Translation Approach with Multi-Attention","display_name":"A Coordinated Representation Learning Enhanced Multimodal Machine Translation Approach with Multi-Attention","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3033615934","doi":"https://doi.org/10.1145/3372278.3390717","mag":"3033615934"},"language":"en","primary_location":{"id":"doi:10.1145/3372278.3390717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390717","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 International Conference on Multimedia Retrieval","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/A5103182094","display_name":"Yifeng Han","orcid":"https://orcid.org/0000-0001-5519-1770"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifeng Han","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412815","display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-7553-6916"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100326967","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-5491-1745"},"institutions":[{"id":"https://openalex.org/I173009982","display_name":"Iwate University","ror":"https://ror.org/04cd75h10","country_code":"JP","type":"education","lineage":["https://openalex.org/I173009982"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["Iwate University, Morioka, Japan"],"affiliations":[{"raw_affiliation_string":"Iwate University, Morioka, Japan","institution_ids":["https://openalex.org/I173009982"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103182094"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.9279,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80121567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"571","last_page":"577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9972000122070312,"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/T10028","display_name":"Topic Modeling","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7999234199523926},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7235838174819946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6524131298065186},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5902086496353149},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5433192849159241},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5023598670959473},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.47739094495773315},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47075942158699036},{"id":"https://openalex.org/keywords/semantic-space","display_name":"Semantic space","score":0.45770737528800964},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.44559386372566223},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4215448498725891},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.41600847244262695},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3778989017009735},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3492740988731384},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.317454993724823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7999234199523926},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7235838174819946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6524131298065186},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5902086496353149},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5433192849159241},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5023598670959473},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.47739094495773315},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47075942158699036},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.45770737528800964},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.44559386372566223},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4215448498725891},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.41600847244262695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3778989017009735},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3492740988731384},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.317454993724823},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3372278.3390717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390717","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 International Conference on Multimedia Retrieval","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":22,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1773149199","https://openalex.org/W2007510844","https://openalex.org/W2062364080","https://openalex.org/W2417549359","https://openalex.org/W2599674900","https://openalex.org/W2607662938","https://openalex.org/W2626778328","https://openalex.org/W2792876194","https://openalex.org/W2798761464","https://openalex.org/W2914695977","https://openalex.org/W2918008835","https://openalex.org/W2924210975","https://openalex.org/W2963435138","https://openalex.org/W2963633722","https://openalex.org/W2964192290","https://openalex.org/W2987281104","https://openalex.org/W2989755682","https://openalex.org/W4241499611","https://openalex.org/W4254367177","https://openalex.org/W4301409532","https://openalex.org/W6602452458"],"related_works":["https://openalex.org/W2773120646","https://openalex.org/W3197060662","https://openalex.org/W4221136938","https://openalex.org/W4213225422","https://openalex.org/W2908875379","https://openalex.org/W4206762304","https://openalex.org/W2947175736","https://openalex.org/W2503569529","https://openalex.org/W564581980","https://openalex.org/W3033615934"],"abstract_inverted_index":{"In":[0,77],"recent":[1],"years,":[2],"the":[3,15,56,65,97,106,114,118,123,131,154,157,189,193],"application":[4],"of":[5,117,156],"machine":[6,88],"translation":[7,18,40,57,89,180],"has":[8],"become":[9],"more":[10,12],"and":[11,34,67,100,134,159],"widely.":[13],"Currently,":[14],"neural":[16],"multimodal":[17,87,92],"models":[19],"have":[20],"made":[21],"attractive":[22],"progress,":[23],"which":[24],"combines":[25],"images":[26,38],"into":[27,113,138],"deep":[28],"learning":[29,85],"networks,":[30],"such":[31],"as":[32,105],"Transformer":[33,120,178],"RNN.":[35],"When":[36],"considering":[37],"in":[39,73,148,176],"models,":[41],"they":[42,71],"directly":[43],"apply":[44],"gate":[45],"structure":[46],"or":[47],"image":[48,52,68,103,109,135,158],"attention":[49],"to":[50,54,129,170],"introduce":[51],"feature":[53],"enhance":[55],"effect.":[58],"We":[59],"argue":[60],"that":[61,185],"it":[62],"may":[63],"mismatch":[64],"text":[66,98,133,160],"features":[69,110,137],"since":[70],"are":[72,111,145],"different":[74,132],"semantic":[75,140,151],"space.":[76,152],"this":[78],"paper,":[79],"we":[80],"propose":[81],"a":[82,149,171],"coordinated":[83],"representation":[84],"enhanced":[86],"approach":[90,95,187],"with":[91],"attention.":[93],"Our":[94],"accepts":[96],"data":[99,104],"its":[101],"relevant":[102],"input.":[107],"The":[108,142],"fed":[112],"decoder":[115],"side":[116],"basic":[119],"model.":[121],"Moreover,":[122],"Coordinated":[124,163],"Representation":[125,165],"Learning":[126],"is":[127],"utilized":[128],"map":[130],"modal":[136],"their":[139],"representations.":[141],"mapped":[143],"representations":[144],"linearly":[146],"related":[147],"shared":[150],"Finally,":[153],"sum":[155],"representations,":[161],"called":[162],"Visual-Semantic":[164],"(CVSR),":[166],"will":[167],"be":[168],"sent":[169],"Multimodal":[172],"Attention":[173],"Layer":[174],"(MAL)":[175],"our":[177,186],"based":[179],"approach.":[181],"Experimental":[182],"results":[183],"show":[184],"achieves":[188],"state-of-art":[190],"performance":[191],"on":[192],"public":[194],"Multi30k":[195],"dataset.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}