{"id":"https://openalex.org/W3014451280","doi":"https://doi.org/10.1145/3371382.3378261","title":"Attention-Based Multimodal Fusion for Estimating Human Emotion in Real-World HRI","display_name":"Attention-Based Multimodal Fusion for Estimating Human Emotion in Real-World HRI","publication_year":2020,"publication_date":"2020-03-23","ids":{"openalex":"https://openalex.org/W3014451280","doi":"https://doi.org/10.1145/3371382.3378261","mag":"3014451280"},"language":"en","primary_location":{"id":"doi:10.1145/3371382.3378261","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3371382.3378261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction","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/A5101930952","display_name":"Yuanchao Li","orcid":"https://orcid.org/0000-0002-8688-5246"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuanchao Li","raw_affiliation_strings":["Honda R&D Co., Ltd., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Honda R&D Co., Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048297544","display_name":"Tianyu Zhao","orcid":"https://orcid.org/0000-0003-2401-4098"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tianyu Zhao","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024027579","display_name":"Xun Shen","orcid":"https://orcid.org/0000-0002-8827-5791"},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xun Shen","raw_affiliation_strings":["The Graduate University for Advanced Studies, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The Graduate University for Advanced Studies, Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101930952"],"corresponding_institution_ids":["https://openalex.org/I1283473643"],"apc_list":null,"apc_paid":null,"fwci":1.5376,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82805127,"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":"340","last_page":"342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12032","display_name":"Multisensory perception and integration","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.7823903560638428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7089707255363464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5889179706573486},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5077310800552368},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4894813299179077},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.486752986907959},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.44652605056762695},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.42852601408958435},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.42353811860084534},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40861135721206665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3987937271595001}],"concepts":[{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.7823903560638428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089707255363464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5889179706573486},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5077310800552368},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4894813299179077},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.486752986907959},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.44652605056762695},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.42852601408958435},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.42353811860084534},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40861135721206665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3987937271595001},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3371382.3378261","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3371382.3378261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1999042468","https://openalex.org/W2004789217","https://openalex.org/W2032139348","https://openalex.org/W2056403322","https://openalex.org/W2085662862","https://openalex.org/W2113507809","https://openalex.org/W2135256083","https://openalex.org/W2156503193","https://openalex.org/W2584992898","https://openalex.org/W2586291442","https://openalex.org/W2786095354","https://openalex.org/W2904679689","https://openalex.org/W6679992976"],"related_works":["https://openalex.org/W2371994528","https://openalex.org/W2722112567","https://openalex.org/W2775620487","https://openalex.org/W3122170352","https://openalex.org/W4398164220","https://openalex.org/W4281567410","https://openalex.org/W2978665606","https://openalex.org/W2016565202","https://openalex.org/W2599908883","https://openalex.org/W4389266910"],"abstract_inverted_index":{"Toward":[0],"empathetic":[1],"and":[2,37,65,72,80,83],"harmonious":[3],"human-robot":[4],"interaction":[5],"(HRI),":[6],"automatic":[7],"estimation":[8,89],"of":[9,46],"human":[10],"emotion":[11],"has":[12],"attracted":[13],"increasing":[14],"attention":[15],"from":[16],"multidisciplinary":[17],"research":[18],"fields.":[19],"In":[20],"this":[21],"report,":[22],"we":[23],"propose":[24],"an":[25],"attention-based":[26],"multimodal":[27,48],"fusion":[28,39],"approach":[29,56],"that":[30],"explores":[31],"the":[32,44,58,62],"space":[33],"between":[34],"traditional":[35],"early":[36],"late":[38],"approaches,":[40],"to":[41,60,86],"deal":[42],"with":[43],"problem":[45],"asynchronous":[47],"inputs":[49],"while":[50],"considering":[51],"their":[52],"relatedness.":[53],"The":[54],"proposed":[55],"enables":[57],"robot":[59],"align":[61],"human's":[63],"visual":[64],"speech":[66],"signals":[67],"(more":[68],"specifically,":[69],"facial,":[70],"acoustic,":[71],"lexical":[73],"information)":[74],"extracted":[75],"by":[76],"its":[77],"cameras,":[78],"microphones,":[79],"processing":[81],"modules":[82],"is":[84],"expected":[85],"achieve":[87],"robust":[88],"performance":[90],"in":[91],"real-world":[92],"HRI.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}