{"id":"https://openalex.org/W4415350490","doi":"https://doi.org/10.1145/3746270.3760218","title":"ZeroES: Zero-Shot Ensemble for Open-Vocabulary Video Emotion Recognition with Large Multimodal Models","display_name":"ZeroES: Zero-Shot Ensemble for Open-Vocabulary Video Emotion Recognition with Large Multimodal Models","publication_year":2025,"publication_date":"2025-10-20","ids":{"openalex":"https://openalex.org/W4415350490","doi":"https://doi.org/10.1145/3746270.3760218"},"language":null,"primary_location":{"id":"doi:10.1145/3746270.3760218","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746270.3760218","pdf_url":null,"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 3rd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746270.3760218","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100337731","display_name":"Jun Xie","orcid":"https://orcid.org/0000-0002-6152-3943"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xie","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6152-3943","affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038070675","display_name":"Xiaohui Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Fan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-1498-1989","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714830","display_name":"Zhenghao Zhang","orcid":"https://orcid.org/0009-0003-1530-7486"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghao Zhang","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-1530-7486","affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656560","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0002-8278-486X"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8278-486X","affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100909481","display_name":"He Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhu Yi","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-3333-5863","affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103720145","display_name":"Yingjian Zhu","orcid":"https://orcid.org/0009-0003-5538-0645"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjian Zhu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-5538-0645","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070187615","display_name":"Xiongjun Guan","orcid":"https://orcid.org/0000-0001-8887-3735"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongjun Guan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8887-3735","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076166905","display_name":"X. Wang","orcid":"https://orcid.org/0009-0001-9111-4817"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinming Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9111-4817","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112113696","display_name":"Yue Bi","orcid":"https://orcid.org/0009-0004-6187-5641"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Bi","raw_affiliation_strings":["Shandong University, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0004-6187-5641","affiliations":[{"raw_affiliation_string":"Shandong University, Shandong, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375792","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-2980-6281"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2980-6281","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014879757","display_name":"Zhepeng Wang","orcid":"https://orcid.org/0000-0002-6088-3517"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhepeng Wang","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6088-3517","affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"23","last_page":"29"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9901999831199646,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9842000007629395,"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/robustness","display_name":"Robustness (evolution)","score":0.6236000061035156},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5587999820709229},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3995000123977661},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37369999289512634},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.3698999881744385},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.35989999771118164},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.359499990940094},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.35749998688697815},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.34880000352859497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743399977684021},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6236000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6230999827384949},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5587999820709229},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.35749998688697815},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C202889954","wikidata":"https://www.wikidata.org/wiki/Q1139554","display_name":"Subjectivity","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C15569618","wikidata":"https://www.wikidata.org/wiki/Q3561421","display_name":"Liveness","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746270.3760218","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746270.3760218","pdf_url":null,"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 3rd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746270.3760218","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746270.3760218","pdf_url":null,"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 3rd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3207246414","https://openalex.org/W4387968043","https://openalex.org/W4402368188","https://openalex.org/W4403713255","https://openalex.org/W4403713260","https://openalex.org/W4403713271","https://openalex.org/W4403713311"],"related_works":[],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,39],"has":[2],"long":[3],"grappled":[4],"with":[5,63,70,113,157],"the":[6,20,42,91,118,127],"inherent":[7],"subjectivity":[8],"and":[9,68,87,110,137,147,160],"open-ended":[10],"nature":[11],"of":[12,24,45,103,130,140],"human":[13],"affect,":[14],"where":[15],"predefined":[16],"taxonomies":[17],"falter":[18],"against":[19],"vast,":[21],"evolving":[22],"spectrum":[23],"emotional":[25],"expression.":[26],"We":[27],"present":[28],"ZeroES,":[29],"a":[30,76,82,100],"Zero-Shot":[31],"Ensemble":[32],"framework":[33,125],"that":[34,153],"redefines":[35],"open-vocabulary":[36,96,154],"video":[37],"emotion":[38,85],"by":[40,81,108],"leveraging":[41],"raw":[43],"capacity":[44],"large-scale":[46],"vision-language":[47],"models":[48],"(VLMs)":[49],"without":[50,121],"task-specific":[51,131],"optimization.":[52,165],"Departing":[53],"from":[54,117],"conventional":[55],"fine-tuning":[56,134],"paradigms,":[57],"ZeroES":[58,98,151],"synergizes":[59],"Gemini":[60],"2.5":[61],"Flash":[62],"its":[64,71],"dual-frame-rate":[65],"temporal":[66],"modeling":[67],"InternVL3-78B":[69],"depth-wise":[72],"negative-affect":[73],"priors":[74],"in":[75],"purely":[77],"zero-shot":[78],"configuration,":[79],"augmented":[80],"lightweight":[83],"six-class":[84],"anchor":[86],"commonsense-driven":[88],"calibration.":[89],"On":[90],"MER2025-FG":[92],"competition":[93],"comprising":[94],"20K":[95],"videos,":[97],"achieves":[99],"hierarchical":[101],"F1":[102],"0.6011,":[104],"outperforming":[105],"fine-tuned":[106],"baselines":[107],"0.1":[109],"ranking":[111],"2nd":[112],"only":[114],"0.0003":[115],"difference":[116],"winner,":[119],"all":[120],"training.":[122],"Crucially,":[123],"our":[124],"exposes":[126],"intrinsic":[128],"trade-off":[129],"adaptation:":[132],"closed-set":[133],"amplifies":[135],"bias":[136],"collapses":[138],"coverage":[139],"novel":[141],"affective":[142,148],"concepts.":[143],"Through":[144],"temporal-granular":[145],"decoupling":[146],"polarity":[149],"synthesis,":[150],"demonstrates":[152],"robustness":[155],"scales":[156],"model":[158],"breadth":[159],"compositional":[161],"flexibility,":[162],"not":[163],"specialized":[164]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-21T00:00:00"}