{"id":"https://openalex.org/W3160481349","doi":"https://doi.org/10.1109/icassp39728.2021.9413389","title":"Image-Assisted Transformer in Zero-Resource Multi-Modal Translation","display_name":"Image-Assisted Transformer in Zero-Resource Multi-Modal Translation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160481349","doi":"https://doi.org/10.1109/icassp39728.2021.9413389","mag":"3160481349"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101776167","display_name":"Ping Huang","orcid":"https://orcid.org/0000-0003-1076-3469"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ping Huang","raw_affiliation_strings":["East China Normal University,School of Computer Science and Technology,Shanghai,China","School of Computer Science and Technology, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047846625","display_name":"Shiliang Sun","orcid":"https://orcid.org/0000-0001-7069-3752"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Sun","raw_affiliation_strings":["East China Normal University,School of Computer Science and Technology,Shanghai,China","School of Computer Science and Technology, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038736812","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0001-8861-7010"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Huawei Technologies CO., LTD,2012 Labs,Beijing,China","2012 Labs, Huawei Technologies CO., LTD, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies CO., LTD,2012 Labs,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"2012 Labs, Huawei Technologies CO., LTD, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101776167"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77535225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7548","last_page":"7552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9987999796867371,"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/machine-translation","display_name":"Machine translation","score":0.8337812423706055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7938543558120728},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7606308460235596},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6185550093650818},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5553686022758484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5452609062194824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4829360842704773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3578931391239166},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.16735538840293884},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09659558534622192},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06694546341896057}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8337812423706055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7938543558120728},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7606308460235596},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6185550093650818},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5553686022758484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5452609062194824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4829360842704773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3578931391239166},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.16735538840293884},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09659558534622192},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06694546341896057},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W114341944","https://openalex.org/W1514535095","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2133564696","https://openalex.org/W2573834658","https://openalex.org/W2766184602","https://openalex.org/W2889545026","https://openalex.org/W2904651132","https://openalex.org/W2944815030","https://openalex.org/W2946928227","https://openalex.org/W2952468927","https://openalex.org/W2962784628","https://openalex.org/W2962830144","https://openalex.org/W2963216553","https://openalex.org/W2963360627","https://openalex.org/W2963403868","https://openalex.org/W2963909453","https://openalex.org/W2964308564","https://openalex.org/W2966618235","https://openalex.org/W2980216782","https://openalex.org/W2994772196","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6745847105","https://openalex.org/W6748375710","https://openalex.org/W6756559799","https://openalex.org/W6762521896","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2903810591","https://openalex.org/W2883671469","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2890256614","https://openalex.org/W2728761353","https://openalex.org/W3098873988","https://openalex.org/W2949454572"],"abstract_inverted_index":{"Humans":[0],"learn":[1,38],"language":[2,89],"speaking":[3],"and":[4],"translation":[5,19,27,101,126,140],"with":[6,46,59,102,141],"the":[7,13,52,72,79,97,135],"help":[8],"of":[9,12,71,99,137],"common":[10],"knowledge":[11],"external":[14,47],"world,":[15],"while":[16,91],"standard":[17],"machine":[18,76,139],"depends":[20],"only":[21],"on":[22],"parallel":[23,43],"corpora.":[24],"There-fore,":[25],"zero-resource":[26,100,125,138],"has":[28],"been":[29],"proposed":[30],"to":[31,35,39,65,68,111],"explore":[32],"a":[33,60,120,124],"way":[34],"make":[36,69],"models":[37,50],"translate":[40],"without":[41],"any":[42],"corpora":[44],"but":[45],"knowledge.":[48],"Current":[49],"in":[51,75,87,96,123,134],"field":[53,98,136],"usually":[54],"combine":[55],"an":[56,116],"image":[57,103,142],"encoder":[58],"textual":[61],"decoder,":[62],"which":[63],"leads":[64],"extra":[66],"efforts":[67],"use":[70,112],"original":[73],"model":[74,129],"translation.":[77],"On":[78],"other":[80],"hand,":[81],"Transformers":[82],"have":[83],"achieved":[84],"great":[85],"progress":[86],"neural":[88],"processing":[90],"they":[92],"are":[93],"rarely":[94],"utilized":[95],"pivot.":[104,143],"In":[105],"this":[106],"paper,":[107],"we":[108],"investigate":[109],"how":[110],"visual":[113],"information":[114],"as":[115],"auxiliary":[117],"hint":[118],"for":[119],"Transformer-based":[121],"system":[122],"scenario.":[127],"Our":[128],"achieves":[130],"state-of-the-art":[131],"BLEU":[132],"scores":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}