{"id":"https://openalex.org/W2962931510","doi":"https://doi.org/10.1609/aaai.v33i01.33016892","title":"Found in Translation: Learning Robust Joint Representations by Cyclic Translations between Modalities","display_name":"Found in Translation: Learning Robust Joint Representations by Cyclic Translations between Modalities","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2962931510","doi":"https://doi.org/10.1609/aaai.v33i01.33016892","mag":"2962931510"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33016892","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016892","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33016892","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017287333","display_name":"Hai Pham","orcid":"https://orcid.org/0000-0001-9391-5514"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hai Pham","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086233510","display_name":"Paul Pu Liang","orcid":"https://orcid.org/0000-0001-7768-3610"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Pu Liang","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020258556","display_name":"Thomas Manzini","orcid":"https://orcid.org/0009-0002-4937-1948"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Manzini","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081398601","display_name":"Louis\u2013Philippe Morency","orcid":"https://orcid.org/0000-0001-6376-7696"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis-Philippe Morency","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013695358","display_name":"Barnab\u00e1s P\u00f3czos","orcid":"https://orcid.org/0000-0002-2898-4705"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barnab\u00e1s P\u00f3czos","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017287333"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":21.3194,"has_fulltext":false,"cited_by_count":411,"citation_normalized_percentile":{"value":0.99459916,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"6892","last_page":"6899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9991999864578247,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9991999864578247,"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":0.9860000014305115,"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":0.9761999845504761,"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/modalities","display_name":"Modalities","score":0.9201967716217041},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.7798627614974976},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7654471397399902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7473167181015015},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6213282346725464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6037445068359375},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5486786961555481},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4641135334968567},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4581316113471985},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.43784159421920776},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.43656831979751587},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39424604177474976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3925173878669739}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.9201967716217041},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.7798627614974976},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7654471397399902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473167181015015},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6213282346725464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6037445068359375},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5486786961555481},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4641135334968567},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4581316113471985},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.43784159421920776},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.43656831979751587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39424604177474976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3925173878669739},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33016892","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016892","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33016892","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016892","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6700000166893005,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Multimodal":[0],"sentiment":[1,11,195,230],"analysis":[2,231],"is":[3,83,122,176],"a":[4,53,109,131,134,138,156,218],"core":[5],"research":[6],"area":[7],"that":[8,30,94,128,162,199,240],"studies":[9],"speaker":[10],"expressed":[12],"from":[13,36,130,169,186,204],"the":[14,55,70,125,146,187,210],"language,":[15],"visual,":[16],"and":[17,33,51,222,235],"acoustic":[18],"modalities.":[19,38,119,171,212,259],"The":[20],"central":[21],"challenge":[22],"in":[23,79,209],"multimodal":[24,180,229],"learning":[25,91,141],"involves":[26],"inferring":[27],"joint":[28,43,92,114,142,164,246],"representations":[29,44,57,93,115,143,165,247],"can":[31],"process":[32],"relate":[34],"information":[35,168,208],"these":[37],"However,":[39],"existing":[40],"work":[41],"learns":[42,243],"by":[45,116],"requiring":[46],"all":[47,98,170],"modalities":[48,65,100,251],"as":[49,52,149],"input":[50,99,250],"result,":[54],"learned":[56],"may":[58,95],"be":[59],"sensitive":[60],"to":[61,75,86,111,133,160,255],"noisy":[62],"or":[63,206,257],"missing":[64,207,256],"at":[66,101,190],"test":[67,102,191],"time.":[68,103],"With":[69],"recent":[71],"success":[72],"of":[73,90,140],"sequence":[74,76],"(Seq2Seq)":[77],"models":[78],"machine":[80],"translation,":[81],"there":[82],"an":[84],"opportunity":[85],"explore":[87],"new":[88,225],"ways":[89],"not":[96],"require":[97],"In":[104],"this":[105],"paper,":[106],"we":[107,182],"propose":[108],"method":[110,121,139],"learn":[112],"robust":[113,203],"translating":[117],"between":[118],"Our":[120],"based":[123],"on":[124,228],"key":[126],"insight":[127],"translation":[129,174],"source":[132,147,188],"target":[135],"modality":[136,148,153,189],"provides":[137],"using":[144],"only":[145,183],"input.":[150],"We":[151,213],"augment":[152],"translations":[154],"with":[155,178,217,248],"cycle":[157],"consistency":[158],"loss":[159],"ensure":[161],"our":[163,173,200,215,241],"retain":[166],"maximal":[167],"Once":[172],"model":[175,201,216,242],"trained":[177],"paired":[179],"data,":[181],"need":[184],"data":[185],"time":[192],"for":[193],"final":[194],"prediction.":[196],"This":[197],"ensures":[198],"remains":[202],"perturbations":[205],"other":[211],"train":[214],"coupled":[219],"translationprediction":[220],"objective":[221],"it":[223],"achieves":[224],"state-of-the-art":[226],"results":[227],"datasets:":[232],"CMU-MOSI,":[233],"ICTMMMO,":[234],"YouTube.":[236],"Additional":[237],"experiments":[238],"show":[239],"increasingly":[244],"discriminative":[245],"more":[249],"while":[252],"maintaining":[253],"robustness":[254],"perturbed":[258]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":77},{"year":2024,"cited_by_count":85},{"year":2023,"cited_by_count":83},{"year":2022,"cited_by_count":54},{"year":2021,"cited_by_count":63},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":9}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}