{"id":"https://openalex.org/W4415535538","doi":"https://doi.org/10.1145/3746027.3762246","title":"Multiple Appropriate Facial Reaction Generation Based on Multi-View Transformation of Speaker Video","display_name":"Multiple Appropriate Facial Reaction Generation Based on Multi-View Transformation of Speaker Video","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415535538","doi":"https://doi.org/10.1145/3746027.3762246"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762246","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Jiajian Huang","orcid":"https://orcid.org/0009-0005-9298-7950"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajian Huang","raw_affiliation_strings":["Department of Information Science and Technology, Great Bay University, Dongguan, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0005-9298-7950","affiliations":[{"raw_affiliation_string":"Department of Information Science and Technology, Great Bay University, Dongguan, Guangdong, China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062522283","display_name":"Zitong Yu","orcid":"https://orcid.org/0000-0001-6505-3304"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitong Yu","raw_affiliation_strings":["Department of Information Science and Technology, Great Bay University, Dongguan, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-6505-3304","affiliations":[{"raw_affiliation_string":"Department of Information Science and Technology, Great Bay University, Dongguan, Guangdong, China","institution_ids":["https://openalex.org/I2799850029"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2799850029"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13992","last_page":"13996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9968000054359436,"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/T11448","display_name":"Face recognition and analysis","score":0.9968000054359436,"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/T10860","display_name":"Speech and Audio Processing","score":0.97079998254776,"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/T10057","display_name":"Face and Expression Recognition","score":0.9660999774932861,"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/motion","display_name":"Motion (physics)","score":0.534600019454956},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5184000134468079},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4722999930381775},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46799999475479126},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4498000144958496},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4480000138282776},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.4399999976158142},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.40619999170303345},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3882000148296356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843999862670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5960999727249146},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5184000134468079},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46799999475479126},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4480000138282776},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4433000087738037},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.40619999170303345},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.32199999690055847},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C54654163","wikidata":"https://www.wikidata.org/wiki/Q5428359","display_name":"Face hallucination","level":5,"score":0.31209999322891235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2776289891","wikidata":"https://www.wikidata.org/wiki/Q1931511","display_name":"Neglect","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.26589998602867126},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.2651999890804291},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2605000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762246","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":18,"referenced_works":["https://openalex.org/W2045528981","https://openalex.org/W2755291975","https://openalex.org/W3149845000","https://openalex.org/W4220938208","https://openalex.org/W4312358294","https://openalex.org/W4320913003","https://openalex.org/W4387968034","https://openalex.org/W4387968147","https://openalex.org/W4387969719","https://openalex.org/W4388188050","https://openalex.org/W4394625843","https://openalex.org/W4400527555","https://openalex.org/W4400527597","https://openalex.org/W4400527625","https://openalex.org/W4400527782","https://openalex.org/W4403792418","https://openalex.org/W4408351985","https://openalex.org/W4409346650"],"related_works":[],"abstract_inverted_index":{"Generating":[0],"multiple":[1],"appropriate":[2],"facial":[3,32,72],"reactions":[4],"(MAFR)":[5],"is":[6],"essential":[7],"for":[8],"effective":[9],"human-agent":[10],"interaction.":[11],"However,":[12],"existing":[13,106],"methods":[14],"typically":[15],"do":[16],"not":[17],"jointly":[18],"model":[19],"both":[20,79,109],"local":[21,47],"and":[22,26,38,48,81,94,112],"global":[23,49],"emotional":[24,50,57],"cues,":[25],"neglect":[27],"the":[28,68,118],"temporal":[29],"dynamics":[30],"of":[31,71],"expressions,":[33],"leading":[34],"to":[35,52],"emotionally":[36],"inconsistent":[37],"less":[39],"natural":[40,96],"reactions.":[41,98],"In":[42],"this":[43],"work,":[44],"we":[45],"combine":[46],"features":[51,65],"form":[53],"a":[54,85],"more":[55,92],"comprehensive":[56],"representation.":[58],"Our":[59],"method":[60,104],"further":[61],"introduces":[62],"motion-aware":[63],"visual":[64],"that":[66,102],"capture":[67],"dynamic":[69],"evolution":[70],"expressions":[73],"beyond":[74],"static":[75],"frames.":[76],"By":[77],"integrating":[78],"appearance":[80],"motion":[82],"information":[83],"within":[84],"structured":[86],"generative":[87],"framework,":[88],"our":[89,103],"approach":[90],"enables":[91],"context-aware":[93],"temporally":[95],"listener":[97],"Experimental":[99],"results":[100],"demonstrate":[101],"outperforms":[105],"approaches":[107],"in":[108,117],"reaction":[110],"diversity":[111],"appropriateness,":[113],"which":[114],"ranked":[115],"first":[116],"React":[119],"2025":[120],"challenge":[121],"offline":[122],"track.The":[123],"implementation":[124],"code":[125],"can":[126],"be":[127],"accessed":[128],"at:https://github.com/mtv-2025-react/mtv-2025-2025.git.":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}