{"id":"https://openalex.org/W3083614545","doi":"https://doi.org/10.1145/3394171.3413715","title":"Dynamic Context-guided Capsule Network for Multimodal Machine Translation","display_name":"Dynamic Context-guided Capsule Network for Multimodal Machine Translation","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3083614545","doi":"https://doi.org/10.1145/3394171.3413715","mag":"3083614545"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.02016","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Lin","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fandong Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fandong Meng","raw_affiliation_strings":["Tencent WeChat AI, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent WeChat AI, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinsong Su","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Su","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yongjing Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjing Yin","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhengyuan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengyuan Yang","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yubin Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yubin Ge","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana-Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["Tencent WeChat AI, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent WeChat AI, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jiebo Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1320","last_page":"1329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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/T10028","display_name":"Topic Modeling","score":0.9929999709129333,"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/context","display_name":"Context (archaeology)","score":0.6189000010490417},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5630999803543091},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5601000189781189},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.486299991607666},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.38119998574256897},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3783999979496002},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3614000082015991},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6485000252723694},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6189000010490417},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5630999803543091},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.486299991607666},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.38119998574256897},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.3427000045776367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32589998841285706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31380000710487366},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394171.3413715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.02016","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02016","pdf_url":"https://arxiv.org/pdf/2009.02016","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.02016","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02016","pdf_url":"https://arxiv.org/pdf/2009.02016","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2509282593","https://openalex.org/W2513263213","https://openalex.org/W2581101319","https://openalex.org/W2593341061","https://openalex.org/W2726413184","https://openalex.org/W2766605158","https://openalex.org/W2767057417","https://openalex.org/W2781918655","https://openalex.org/W2886134486","https://openalex.org/W2888070626","https://openalex.org/W2892244498","https://openalex.org/W2895526696","https://openalex.org/W2895836448","https://openalex.org/W2902031175","https://openalex.org/W2903343986","https://openalex.org/W2949448715","https://openalex.org/W2950207430","https://openalex.org/W2950404230","https://openalex.org/W2950886580","https://openalex.org/W2962712961","https://openalex.org/W2962784628","https://openalex.org/W2962853356","https://openalex.org/W2963143796","https://openalex.org/W2963212250","https://openalex.org/W2963331233","https://openalex.org/W2963407669","https://openalex.org/W2963713328","https://openalex.org/W2963909453","https://openalex.org/W2964093087","https://openalex.org/W2964192290","https://openalex.org/W2965597639","https://openalex.org/W2971452554","https://openalex.org/W2973009097","https://openalex.org/W2981578638","https://openalex.org/W2981963155","https://openalex.org/W2981994675","https://openalex.org/W2990804422","https://openalex.org/W3034871396","https://openalex.org/W3102507836","https://openalex.org/W6600421821"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"machine":[1],"translation":[2,10,200],"(MMT),":[3],"which":[4,65,175],"mainly":[5],"focuses":[6],"on":[7,192,210],"enhancing":[8],"text-only":[9],"with":[11,146,162],"visual":[12,45,63,132,150,163],"features,":[13,151],"has":[14],"attracted":[15],"considerable":[16],"attention":[17,33,49,107],"from":[18],"both":[19],"computer":[20],"vision":[21],"and":[22,122,148,178,198],"natural":[23],"language":[24],"processing":[25],"communities.":[26],"Most":[27],"current":[28],"MMT":[29],"models":[30],"resort":[31],"to":[32,43,108,125,157],"mechanism,":[34],"global":[35,147],"context":[36,113,160,173],"modeling":[37,69],"or":[38],"multimodal":[39,159,172],"joint":[40],"representation":[41],"learning":[42],"utilize":[44],"features.":[46],"However,":[47],"the":[48,58,70,78,104,127,143,181,184,187,193,202],"mechanism":[50],"lacks":[51],"sufficient":[52],"semantic":[53],"interactions":[54],"between":[55],"modalities":[56],"while":[57],"other":[59],"two":[60,154,171],"provide":[61],"fixed":[62],"context,":[64],"is":[66,208],"unsuitable":[67],"for":[68,93,183],"observed":[71],"variability":[72],"when":[73],"generating":[74],"translation.":[75],"To":[76],"address":[77],"above":[79],"issues,":[80],"in":[81],"this":[82,118],"paper,":[83],"we":[84,101,141,152,169],"propose":[85],"a":[86,110,135],"novel":[87],"Dynamic":[88],"Context-guided":[89],"Capsule":[90],"Network":[91],"(DCCN)":[92],"MMT.":[94],"Specifically,":[95],"at":[96,165],"each":[97],"timestep":[98],"of":[99,130,186,196,204],"decoding,":[100],"first":[102],"employ":[103],"conventional":[105],"source-target":[106],"produce":[109],"timestep-specific":[111],"source-side":[112],"vector.":[114],"Next,":[115],"DCCN":[116],"takes":[117],"vector":[119],"as":[120],"input":[121,144],"uses":[123],"it":[124],"guide":[126],"iterative":[128],"extraction":[129],"related":[131],"features":[133,164],"via":[134],"context-guided":[136],"dynamic":[137],"routing":[138],"mechanism.":[139],"Particularly,":[140],"represent":[142],"image":[145],"regional":[149],"introduce":[153],"parallel":[155],"DCCNs":[156],"model":[158],"vectors":[161],"different":[166],"granularities.":[167],"Finally,":[168],"obtain":[170],"vectors,":[174],"are":[176],"fused":[177],"incorporated":[179],"into":[180],"decoder":[182],"prediction":[185],"target":[188],"word.":[189],"Experimental":[190],"results":[191],"Multi30K":[194],"dataset":[195],"English-to-German":[197],"English-to-French":[199],"demonstrate":[201],"superiority":[203],"DCCN.":[205],"Our":[206],"code":[207],"available":[209],"https://github.com/DeepLearnXMU/MM-DCCN.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2020-09-11T00:00:00"}