{"id":"https://openalex.org/W2742097923","doi":"https://doi.org/10.18653/v1/p17-5002","title":"Multimodal Machine Learning: Integrating Language, Vision and Speech","display_name":"Multimodal Machine Learning: Integrating Language, Vision and Speech","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2742097923","doi":"https://doi.org/10.18653/v1/p17-5002","mag":"2742097923"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-5002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-5002","pdf_url":"https://www.aclweb.org/anthology/P17-5002.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ACL 2017, Tutorial Abstracts","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-5002.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Louis-Philippe Morency","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058610902","display_name":"Tadas Baltru\u0161aitis","orcid":"https://orcid.org/0000-0001-7923-8780"},"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":"Tadas Baltru\u0161aitis","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081398601"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":4.0209,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94360836,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9836999773979187,"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":0.8133152723312378},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7596296072006226},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7136536240577698},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.6799499988555908},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.5945823192596436},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5677648186683655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5401967167854309},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.47507089376449585},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4731524884700775},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43674522638320923},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41648513078689575},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4058108925819397},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32227617502212524},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14410755038261414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133152723312378},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7596296072006226},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7136536240577698},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.6799499988555908},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.5945823192596436},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5677648186683655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5401967167854309},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.47507089376449585},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4731524884700775},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43674522638320923},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41648513078689575},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4058108925819397},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32227617502212524},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14410755038261414},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p17-5002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-5002","pdf_url":"https://www.aclweb.org/anthology/P17-5002.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ACL 2017, Tutorial Abstracts","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-5002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-5002","pdf_url":"https://www.aclweb.org/anthology/P17-5002.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ACL 2017, Tutorial Abstracts","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2742097923.pdf","grobid_xml":"https://content.openalex.org/works/W2742097923.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4236665645","https://openalex.org/W3093803775","https://openalex.org/W4381827277","https://openalex.org/W3157841754","https://openalex.org/W4390136517","https://openalex.org/W2563212008","https://openalex.org/W4399869253","https://openalex.org/W2477990774","https://openalex.org/W3167558523","https://openalex.org/W3120825179"],"abstract_inverted_index":{"Multimodal":[0],"machine":[1],"learning":[2],"is":[3],"a":[4],"vibrant":[5],"multi-disciplinary":[6],"research":[7,35,59],"field":[8,60],"which":[9],"addresses":[10],"some":[11,62],"of":[12,16,71],"the":[13,33,69,72,75],"original":[14],"goals":[15],"artificial":[17],"intelligence":[18],"by":[19],"integrating":[20],"and":[21,29,40,51,54,74],"modeling":[22],"multiple":[23],"communicative":[24],"modalities,":[25],"including":[26],"linguistic,":[27],"acoustic":[28],"visual":[30,55],"messages.":[31],"With":[32],"initial":[34],"on":[36],"audio-visual":[37],"speech":[38],"recognition":[39],"more":[41],"recently":[42],"with":[43],"language":[44],"&":[45],"vision":[46],"projects":[47],"such":[48],"as":[49],"image":[50],"video":[52],"captioning":[53],"question":[56],"answering,":[57],"this":[58],"brings":[61],"unique":[63],"challenges":[64],"for":[65],"multimodal":[66],"researchers":[67],"given":[68],"heterogeneity":[70],"data":[73],"contingency":[76],"often":[77],"found":[78],"between":[79],"modalities.":[80]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
