{"id":"https://openalex.org/W7166800670","doi":"https://doi.org/10.18653/v1/2026.acl-long.1813","title":"EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding","display_name":"EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166800670","doi":"https://doi.org/10.18653/v1/2026.acl-long.1813"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1813","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1813","pdf_url":"https://aclanthology.org/2026.acl-long.1813.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1813.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135968808","display_name":"Pengze Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengze Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135969792","display_name":"Jingxi Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingxi Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705596","display_name":"Zhiwen Xie","orcid":"https://orcid.org/0000-0003-0837-3285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiwen Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101633505","display_name":"Qifeng Wang","orcid":"https://orcid.org/0000-0001-8544-9007"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qifeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120001875","display_name":"Derek F. Wong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Derek F. Wong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85550324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39074","last_page":"39089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9498999714851379,"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":0.9498999714851379,"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":0.007199999876320362,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/benchmark","display_name":"Benchmark (surveying)","score":0.517300009727478},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.26600000262260437},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2556999921798706},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.23929999768733978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6725999712944031},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5037999749183655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28130000829696655},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.23929999768733978},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22450000047683716},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.22220000624656677}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1813","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1813","pdf_url":"https://aclanthology.org/2026.acl-long.1813.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1813","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1813","pdf_url":"https://aclanthology.org/2026.acl-long.1813.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.45530763268470764}],"awards":[{"id":"https://openalex.org/G4615181649","display_name":null,"funder_award_id":"62266013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5893188460","display_name":null,"funder_award_id":"0007/2024/AKP","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320311133","display_name":"United Mitochondrial Disease Foundation","ror":"https://ror.org/0528q0t18"},{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323893","display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia","ror":"https://ror.org/05vna4324"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166800670.pdf","grobid_xml":"https://content.openalex.org/works/W7166800670.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,8,47,104,107],"context":[2],"of":[3,15,49,111],"today's":[4],"high-pressure,":[5],"aging":[6],"society,":[7],"demand":[9],"for":[10,106],"large-scale":[11],"emotional":[12,84],"models":[13,115],"capable":[14],"providing":[16],"empathetic":[17],"support":[18],"is":[19],"more":[20],"critical":[21],"than":[22],"ever.However,":[23],"existing":[24,55],"benchmarks":[25],"fail":[26],"to":[27,45],"simultaneously":[28],"achieve":[29],"ecological":[30,50],"validity,":[31],"signal":[32],"clarity,":[33],"and":[34,52,109,116,120],"reliable":[35],"fine-grained":[36],"labeling.We":[37],"introduce":[38],"EmoS,":[39],"a":[40,64,70],"high-fidelity":[41],"bilingual":[42],"benchmark":[43],"designed":[44],"resolve":[46],"limitations":[48],"validity":[51],"noise":[53],"in":[54],"datasets":[56],"by":[57,69],"combining":[58],"strictly":[59],"filtered":[60],"static":[61],"slices":[62],"with":[63],"dynamic":[65],"Streaming":[66],"Monologue":[67],"subset.Supported":[68],"rigorous":[71],"dual-layer":[72],"human":[73],"annotation":[74],"pipeline,":[75],"EmoS":[76,96],"provides":[77],"trusted":[78],"ground":[79],"truth":[80],"that":[81,88],"captures":[82],"continuous":[83],"evolution.Empirical":[85],"results":[86],"show":[87],"fine-tuning":[89],"MLLMs":[90],"(multimodal":[91],"large":[92],"language":[93],"models)":[94],"on":[95],"yields":[97],"significant":[98],"gains":[99],"over":[100],"zero-shot":[101],"baselines,":[102],"laying":[103],"foundation":[105],"training":[108],"evaluation":[110],"future":[112],"emotion":[113],"recognition":[114],"empathy":[117],"models.The":[118],"dataset":[119],"code":[121],"are":[122],"publicly":[123],"available":[124],"at":[125],"https://github.com/":[126],"NLP2CT/EmoS.":[127]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}