{"id":"https://openalex.org/W4406596050","doi":"https://doi.org/10.1145/3703619.3706033","title":"FP-KDNet: Facial Perception and Knowledge Distillation Network for Emotion Recogniton in Coversation","display_name":"FP-KDNet: Facial Perception and Knowledge Distillation Network for Emotion Recogniton in Coversation","publication_year":2024,"publication_date":"2024-12-01","ids":{"openalex":"https://openalex.org/W4406596050","doi":"https://doi.org/10.1145/3703619.3706033"},"language":"en","primary_location":{"id":"doi:10.1145/3703619.3706033","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3703619.3706033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","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/A5048624375","display_name":"Chuangxin Cai","orcid":"https://orcid.org/0000-0001-6414-0182"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuangxin Cai","raw_affiliation_strings":["Education International Cooperation Group Shanghai Office, Shanghai, China","School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6414-0182","affiliations":[{"raw_affiliation_string":"Education International Cooperation Group Shanghai Office, Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005555264","display_name":"Xianxuan Lin","orcid":"https://orcid.org/0000-0002-3417-6915"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianxuan Lin","raw_affiliation_strings":["Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3417-6915","affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Zhang","orcid":"https://orcid.org/0009-0005-4343-5949"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-4343-5949","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020742464","display_name":"Anoj Bhattarai","orcid":"https://orcid.org/0009-0003-0900-1763"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aditi Bhattarai","raw_affiliation_strings":["Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-0900-1763","affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chunting Cai","orcid":"https://orcid.org/0009-0006-9340-7759"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunting Cai","raw_affiliation_strings":["Education International Cooperation Group Shanghai Office, Shanghai, China","School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-9340-7759","affiliations":[{"raw_affiliation_string":"Education International Cooperation Group Shanghai Office, Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115941721","display_name":"Xianliang Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianliang Xia","raw_affiliation_strings":["AI, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-0634-276X","affiliations":[{"raw_affiliation_string":"AI, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108725893","display_name":"Zhigeng Pan","orcid":"https://orcid.org/0009-0005-6264-7146"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigeng Pan","raw_affiliation_strings":["Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-6264-7146","affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5048624375"],"corresponding_institution_ids":["https://openalex.org/I200845125"],"apc_list":null,"apc_paid":null,"fwci":0.4802,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72835107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T11448","display_name":"Face recognition and analysis","score":0.9983000159263611,"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/T11094","display_name":"Face Recognition and Perception","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7160353660583496},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6336507201194763},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5562178492546082},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4113163948059082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39734429121017456},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3666309714317322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3658619523048401},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3456355035305023},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3292383849620819},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.14073413610458374},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.10764479637145996},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.09078627824783325}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7160353660583496},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6336507201194763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5562178492546082},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4113163948059082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39734429121017456},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3666309714317322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3658619523048401},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3456355035305023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3292383849620819},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.14073413610458374},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.10764479637145996},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.09078627824783325}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3703619.3706033","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3703619.3706033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2077947937","https://openalex.org/W2146334809","https://openalex.org/W2294370754","https://openalex.org/W2963686995","https://openalex.org/W2964300796","https://openalex.org/W2965453734","https://openalex.org/W3034368386","https://openalex.org/W3138154797","https://openalex.org/W3155551469","https://openalex.org/W3156576211","https://openalex.org/W3174407341","https://openalex.org/W3185542152","https://openalex.org/W3202700139","https://openalex.org/W4221147459","https://openalex.org/W4280492827","https://openalex.org/W4281701185","https://openalex.org/W4286817192","https://openalex.org/W4309568943","https://openalex.org/W4313639160","https://openalex.org/W4321507406","https://openalex.org/W4324291273","https://openalex.org/W4360930863","https://openalex.org/W4377234444","https://openalex.org/W4383873625","https://openalex.org/W4385194642","https://openalex.org/W4386800155","https://openalex.org/W4386826611","https://openalex.org/W4387969127","https://openalex.org/W4389733467","https://openalex.org/W4389752793","https://openalex.org/W4390414889","https://openalex.org/W4391019654","https://openalex.org/W4392356983","https://openalex.org/W4392967536","https://openalex.org/W4393397422","https://openalex.org/W4394595603","https://openalex.org/W4395025868","https://openalex.org/W4400276083","https://openalex.org/W4400350678","https://openalex.org/W4400527853"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2628861693","https://openalex.org/W2344382886","https://openalex.org/W19111321","https://openalex.org/W2412887479","https://openalex.org/W3203087560","https://openalex.org/W32245304","https://openalex.org/W2953684491","https://openalex.org/W4285338581","https://openalex.org/W2768175398"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,70],"in":[2,7,28,49,134],"conversation":[3],"(ERC)":[4],"is":[5],"anchored":[6],"the":[8,19,42,85,115,135,142,156,181,190,193],"burgeoning":[9],"field":[10],"of":[11,45,158,192],"artificial":[12],"intelligence,":[13],"aiming":[14],"to":[15,21,25,76,93,107,118,130,166],"equip":[16],"machines":[17],"with":[18],"ability":[20,117],"discern":[22],"and":[23,51,88,183,186],"respond":[24],"human":[26],"emotions":[27],"nuanced":[29],"ways.":[30],"However,":[31],"recent":[32],"studies":[33,188],"have":[34],"primarily":[35],"focused":[36],"on":[37,180],"textual":[38],"modalities,":[39,161],"often":[40],"neglecting":[41],"significant":[43],"potential":[44],"non-verbal":[46,65,109,136],"cues":[47,66,110],"found":[48],"audio":[50],"video,":[52],"which":[53],"are":[54],"critical":[55],"for":[56],"accurately":[57],"capturing":[58],"emotions.":[59],"Furthermore,":[60],"when":[61],"researchers":[62],"integrate":[63],"these":[64,95],"into":[67],"multimodal":[68,194],"emotion":[69,132,169],"systems,":[71],"they":[72],"encounter":[73],"challenges":[74],"related":[75],"data":[77,140],"heterogeneity":[78],"across":[79,160],"different":[80],"modalities.":[81],"This":[82],"paper":[83],"introduces":[84],"Facial":[86,100],"Perception":[87],"Knowledge":[89],"Distillation":[90],"Network":[91],"(FP-KDNet)":[92],"address":[94],"challenges.":[96],"Specifically,":[97],"a":[98,123],"novel":[99],"Perceptual":[101],"Attention":[102],"(FPA)":[103],"module":[104],"was":[105,128],"designed":[106],"capture":[108],"from":[111,141],"videos,":[112],"significantly":[113],"enhancing":[114],"model\u2019s":[116],"process":[119],"visual":[120],"information.":[121],"Additionally,":[122],"knowledge":[124],"distillation":[125],"(KD)":[126],"strategy":[127],"proposed":[129],"improve":[131],"representation":[133],"modality":[137],"by":[138],"leveraging":[139],"text":[143],"modality,":[144],"facilitating":[145],"effective":[146],"cross-modal":[147],"information":[148],"exchange.":[149],"A":[150],"multi-head":[151],"attention":[152,164],"mechanism":[153],"further":[154],"optimizes":[155],"integration":[157],"features":[159],"dynamically":[162],"adjusting":[163],"allocation":[165],"enhance":[167],"conversational":[168],"recognition.":[170],"The":[171],"experimental":[172],"results":[173],"demonstrated":[174],"that":[175],"FP-KDNet":[176],"achieves":[177],"excellent":[178],"performance":[179],"MELD":[182],"IEMOCAP":[184],"datasets,":[185],"ablation":[187],"confirm":[189],"effectiveness":[191],"fusion":[195],"approach.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}