{"id":"https://openalex.org/W2807844885","doi":"https://doi.org/10.24963/ijcai.2018/214","title":"Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances","display_name":"Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2807844885","doi":"https://doi.org/10.24963/ijcai.2018/214","mag":"2807844885"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/214","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/214","pdf_url":"https://www.ijcai.org/proceedings/2018/0214.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0214.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079045166","display_name":"Thao Minh Le","orcid":"https://orcid.org/0000-0002-8089-9962"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Thao Le Minh","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017387514","display_name":"Nobuyuki Shimizu","orcid":"https://orcid.org/0000-0001-6767-3662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuyuki Shimizu","raw_affiliation_strings":["Yahoo Japan Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078599820","display_name":"Takashi Miyazaki","orcid":"https://orcid.org/0000-0001-5993-4666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Miyazaki","raw_affiliation_strings":["Yahoo Japan Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5081629487"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.4555,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.74606692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1546","last_page":"1553"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T12031","display_name":"Speech and dialogue systems","score":0.9921000003814697,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9878000020980835,"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/utterance","display_name":"Utterance","score":0.9214153289794922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7734801173210144},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5321691632270813},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5291426777839661},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5236056447029114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5078955292701721},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.48575761914253235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4439052641391754},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4389265775680542},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4364088177680969},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3549097776412964},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.16287079453468323},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14553740620613098}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.9214153289794922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734801173210144},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5321691632270813},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5291426777839661},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5236056447029114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5078955292701721},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.48575761914253235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4439052641391754},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4389265775680542},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4364088177680969},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3549097776412964},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.16287079453468323},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14553740620613098},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.24963/ijcai.2018/214","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/214","pdf_url":"https://www.ijcai.org/proceedings/2018/0214.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.04288","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.04288","pdf_url":"https://arxiv.org/pdf/1809.04288","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30158849","is_oa":false,"landing_page_url":"http://doi.org/10.24963/ijcai.2018/214","pdf_url":null,"source":{"id":"https://openalex.org/S4306402457","display_name":"Deakin Research Online (Deakin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:figshare.com:article/20635332","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Deep_learning_based_multi-modal_addressee_recognition_in_visual_scenes_with_utterances/20635332","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50420229","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100770121","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/214","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/214","pdf_url":"https://www.ijcai.org/proceedings/2018/0214.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2807844885.pdf","grobid_xml":"https://content.openalex.org/works/W2807844885.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1545326209","https://openalex.org/W1554401341","https://openalex.org/W1570557094","https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1997045063","https://openalex.org/W2053154970","https://openalex.org/W2066792660","https://openalex.org/W2086115815","https://openalex.org/W2096598450","https://openalex.org/W2155243985","https://openalex.org/W2161381512","https://openalex.org/W2165698076","https://openalex.org/W2250539671","https://openalex.org/W2508984437","https://openalex.org/W2561158378","https://openalex.org/W2563399268","https://openalex.org/W2714726990","https://openalex.org/W2747419968","https://openalex.org/W2769024834","https://openalex.org/W4294375521"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W2529301793","https://openalex.org/W3133700904","https://openalex.org/W3191326035","https://openalex.org/W627697492"],"abstract_inverted_index":{"With":[0],"the":[1,119,133,140,171],"widespread":[2],"use":[3],"of":[4,77,111,135,154],"intelligent":[5],"systems,":[6],"such":[7,26,53],"as":[8,20,54],"smart":[9,56],"speakers,":[10],"addressee":[11,90,121,157,167],"recognition":[12,168],"has":[13],"become":[14],"a":[15,60,74,88,97,123,160,188],"concern":[16],"in":[17,36,66,80,127,177,191,194],"human-computer":[18],"interaction,":[19],"more":[21,23],"and":[22,38,87,109,152,183],"people":[24],"expect":[25],"systems":[27],"to":[28,117,142,173],"understand":[29,174],"complicated":[30],"social":[31,179],"scenes,":[32],"including":[33],"those":[34],"outdoors,":[35],"cafeterias,":[37],"hospitals.":[39],"Because":[40],"previous":[41],"studies":[42],"typically":[43],"focused":[44],"only":[45],"on":[46],"pre-specified":[47],"tasks":[48],"with":[49,69,83],"limited":[50],"conversational":[51,120,130],"situations":[52,180],"controlling":[55],"homes,":[57],"we":[58,138],"created":[59],"mock":[61],"dataset":[62,186],"called":[63],"Addressee":[64],"Recognition":[65],"Visual":[67],"Scenes":[68],"Utterances":[70],"(ARVSU)":[71],"that":[72,101,149,165],"contains":[73],"vast":[75],"body":[76],"image":[78],"variations":[79],"visual":[81],"scenes":[82],"an":[84,112,144],"annotated":[85],"utterance":[86,113,155],"corresponding":[89],"for":[91,156],"each":[92],"scenario.":[93],"We":[94],"also":[95],"propose":[96],"multi-modal":[98],"deep-learning-based":[99],"model":[100,148],"takes":[102],"different":[103],"human":[104,175],"cues,":[105],"specifically":[106],"eye":[107],"gazes":[108],"transcripts":[110,153],"corpus,":[114],"into":[115],"account":[116],"predict":[118],"from":[122],"specific":[124],"speaker's":[125],"view":[126],"various":[128],"real-life":[129],"scenarios.":[131],"To":[132],"best":[134],"our":[136,162,184],"knowledge,":[137],"are":[139],"first":[141,189],"introduce":[143],"end-to-end":[145],"deep":[146],"learning":[147],"combines":[150],"vision":[151],"recognition.":[158],"As":[159],"result,":[161],"study":[163],"suggests":[164],"future":[166],"can":[169],"reach":[170],"ability":[172],"intention":[176],"many":[178],"previously":[181],"unexplored,":[182],"modality":[185],"is":[187],"step":[190],"promoting":[192],"research":[193],"this":[195],"field.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2018-06-21T00:00:00"}