{"id":"https://openalex.org/W2952728748","doi":"https://doi.org/10.18653/v1/p19-1564","title":"Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems","display_name":"Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952728748","doi":"https://doi.org/10.18653/v1/p19-1564","mag":"2952728748"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1564","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1564","pdf_url":"https://www.aclweb.org/anthology/P19-1564.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 the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1564.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hung Le","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hung Le","raw_affiliation_strings":["Institute of Inforcomm Research (I2R), Singapore","Singapore Management University"],"affiliations":[{"raw_affiliation_string":"Institute of Inforcomm Research (I2R), Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Doyen Sahoo","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Doyen Sahoo","raw_affiliation_strings":["Singapore Management University"],"affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nancy Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy Chen","raw_affiliation_strings":["Institute of Inforcomm Research (I2R), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Inforcomm Research (I2R), Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":null,"display_name":"Steven Hoi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]},{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Steven Hoi","raw_affiliation_strings":["Salesforce Research Asia","Singapore Management University"],"affiliations":[{"raw_affiliation_string":"Salesforce Research Asia","institution_ids":["https://openalex.org/I4210155268"]},{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I79891267"],"apc_list":null,"apc_paid":null,"fwci":2.4522,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.91512133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5612","last_page":"5623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9987000226974487,"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/T12031","display_name":"Speech and dialogue systems","score":0.998199999332428,"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/feature","display_name":"Feature (linguistics)","score":0.538100004196167},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48840001225471497},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3723999857902527},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.3009999990463257},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3005000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7129999995231628},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48840001225471497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4677000045776367},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36800000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3402000069618225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29159998893737793},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p19-1564","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1564","pdf_url":"https://www.aclweb.org/anthology/P19-1564.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 the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.01166","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.01166","pdf_url":"https://arxiv.org/pdf/1907.01166","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":"doi:10.18653/v1/p19-1564","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1564","pdf_url":"https://www.aclweb.org/anthology/P19-1564.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 the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3616239415","display_name":null,"funder_award_id":"A18A2b0046","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"},{"id":"https://openalex.org/G5921878779","display_name":null,"funder_award_id":"18A2b0046","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"},{"id":"https://openalex.org/G7777593022","display_name":null,"funder_award_id":"#A18A2b0046","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952728748.pdf","grobid_xml":"https://content.openalex.org/works/W2952728748.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Developing":[0],"Video-Grounded":[1],"Dialogue":[2],"Systems":[3],"(VGDS),":[4],"where":[5],"a":[6,17],"dialogue":[7,29],"is":[8,20],"conducted":[9],"based":[10],"on":[11],"visual":[12],"and":[13,49],"audio":[14],"aspects":[15],"of":[16,35],"given":[18],"video,":[19],"significantly":[21],"more":[22],"challenging":[23],"than":[24],"traditional":[25],"image":[26],"or":[27],"text-grounded":[28],"systems":[30],"because":[31],"(1)":[32],"feature":[33],"space":[34],"videos":[36],"span":[37],"across":[38],"multiple":[39],"picture":[40],"frames,":[41],"making":[42],"it":[43],"difficult":[44],"to":[45],"obtain":[46],"semantic":[47],"information;":[48]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-06-27T00:00:00"}
