{"id":"https://openalex.org/W7127911111","doi":"https://doi.org/10.1145/3779232.3779470","title":"ALTSA: Adaptive Latent-space Teacher - Student Architecture for Emotion Recognition in Conversation","display_name":"ALTSA: Adaptive Latent-space Teacher - Student Architecture for Emotion Recognition in Conversation","publication_year":2025,"publication_date":"2025-12-13","ids":{"openalex":"https://openalex.org/W7127911111","doi":"https://doi.org/10.1145/3779232.3779470"},"language":null,"primary_location":{"id":"doi:10.1145/3779232.3779470","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3779232.3779470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 20th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","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":"https://openalex.org/A5125120408","display_name":"Aditi Bhattarai","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":"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":"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"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuangxin Cai","raw_affiliation_strings":["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":"School of Artificial Intelligence, Nanjing university of information science and technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125","https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mengxia Li","orcid":"https://orcid.org/0000-0002-2889-4670"},"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"]},{"id":"https://openalex.org/I4210158664","display_name":"Dongfeng Motor (China)","ror":"https://ror.org/049j15k39","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210158664"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxia Li","raw_affiliation_strings":["Dongfeng Motor Corporation Research and Development Institute, Wuhan, China","Nanjing university of information science and technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2889-4670","affiliations":[{"raw_affiliation_string":"Dongfeng Motor Corporation Research and Development Institute, Wuhan, China","institution_ids":["https://openalex.org/I4210158664"]},{"raw_affiliation_string":"Nanjing university of information science and technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083630951","display_name":"Kao Zhang","orcid":"https://orcid.org/0000-0001-9111-0499"},"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":"Kao Zhang","raw_affiliation_strings":["Nanjing university of information science and technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9111-0499","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":"Ming Li","orcid":"https://orcid.org/0000-0002-1341-5585"},"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"]},{"id":"https://openalex.org/I4210158664","display_name":"Dongfeng Motor (China)","ror":"https://ror.org/049j15k39","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210158664"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Dongfeng Motor Corporation Research and Development Institute, Wuhan, China","Nanjing university of information science and technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1341-5585","affiliations":[{"raw_affiliation_string":"Dongfeng Motor Corporation Research and Development Institute, Wuhan, China","institution_ids":["https://openalex.org/I4210158664"]},{"raw_affiliation_string":"Nanjing university of information science and technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":null,"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":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9740999937057495,"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":0.9740999937057495,"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/T12031","display_name":"Speech and dialogue systems","score":0.006099999882280827,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0035000001080334187,"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/modalities","display_name":"Modalities","score":0.8030999898910522},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7581999897956848},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5932000279426575},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5095999836921692},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4975999891757965},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4542999863624573}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8030999898910522},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7581999897956848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6082000136375427},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5932000279426575},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952999949455261},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2533000111579895},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779232.3779470","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3779232.3779470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 20th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.845823347568512}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2963686995","https://openalex.org/W2964300796","https://openalex.org/W2965453734","https://openalex.org/W3034368386","https://openalex.org/W3156576211","https://openalex.org/W3185542152","https://openalex.org/W4296990086","https://openalex.org/W4321507406","https://openalex.org/W4324291273","https://openalex.org/W4360930863","https://openalex.org/W4385570058","https://openalex.org/W4385573172","https://openalex.org/W4389752793","https://openalex.org/W4392356983","https://openalex.org/W4394595603","https://openalex.org/W4400527853"],"related_works":[],"abstract_inverted_index":{"Emotion":[0],"Recognition":[1],"in":[2,146],"Conversation":[3],"(ERC)":[4],"is":[5],"essential":[6],"for":[7],"dialogue":[8],"systems":[9],"to":[10,16,73],"comprehend":[11],"and":[12,25,75,83,102],"provide":[13],"suitable":[14],"responses":[15],"user":[17],"emotions.":[18],"While":[19],"multimodal":[20,49,147],"ERC":[21],"leverages":[22],"text,":[23],"audio,":[24],"visual":[26,84],"signals":[27],"cues,non-verbal":[28],"modalities":[29,63,92],"often":[30],"contribute":[31],"weakly,":[32],"making":[33],"effective":[34],"fusion":[35,50,58,141],"challenging.":[36],"To":[37],"address":[38,143],"this,":[39],"we":[40],"propose":[41],"ALTSA":[42,124],"(Adaptive":[43],"Latent-space":[44],"Teacher-Student":[45],"Architecture)":[46],"that":[47,60,108,134],"enhances":[48],"through":[51,119],"hierarchical":[52],"cross-modal":[53],"knowledge":[54],"distillation.":[55],"Unlike":[56],"transformer-based":[57],"approaches":[59],"treat":[61],"all":[62,91],"equally,":[64],"our":[65],"architecture":[66],"employs":[67],"a":[68,94],"robust":[69],"text-based":[70],"teacher":[71,135],"model":[72,88],"guide":[74],"refine":[76],"the":[77,129,153],"representations":[78],"learned":[79],"by":[80],"weaker":[81],"audio":[82],"student":[85,114],"encoders.":[86],"The":[87,112],"first":[89],"projects":[90],"into":[93],"shared":[95],"latent":[96],"space,":[97],"applies":[98],"dynamic":[99],"modality":[100],"weighting,":[101],"integrates":[103],"an":[104],"emotion-aware":[105],"attention":[106],"mechanism":[107],"prioritizes":[109],"textual":[110],"cues.":[111],"distilled":[113],"features":[115],"are":[116],"further":[117],"enriched":[118],"BiLSTM":[120],"based":[121],"temporal":[122],"modeling.":[123],"achieves":[125],"state-of-the-art":[126],"performance":[127],"on":[128],"MELD":[130],"benchmark":[131],"dataset,":[132],"demonstrating":[133],"assisted":[136],"distillation":[137],"combined":[138],"with":[139],"adaptive":[140],"effectively":[142],"core":[144],"limitations":[145],"ERC.":[148],"Additional":[149],"ablation":[150],"studies":[151],"validate":[152],"contribution":[154],"of":[155],"each":[156],"component.":[157]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-07T00:00:00"}