{"id":"https://openalex.org/W4415538093","doi":"https://doi.org/10.1145/3746027.3755340","title":"Grounding Emotion Recognition with Visual Prototypes: VEGA - Revisiting CLIP in MERC","display_name":"Grounding Emotion Recognition with Visual Prototypes: VEGA - Revisiting CLIP in MERC","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538093","doi":"https://doi.org/10.1145/3746027.3755340"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755340","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":"https://openalex.org/A5050711976","display_name":"Guanyu Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Guanyu Hu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, United Kingdom and Queen Mary, University of London, London, China"],"raw_orcid":"https://orcid.org/0009-0006-1911-6283","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, United Kingdom and Queen Mary, University of London, London, China","institution_ids":["https://openalex.org/I166337079","https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029879679","display_name":"Dimitrios Kollias","orcid":"https://orcid.org/0000-0002-8188-3751"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitrios Kollias","raw_affiliation_strings":["Center for Multimodal AI, Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8188-3751","affiliations":[{"raw_affiliation_string":"Center for Multimodal AI, Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056067943","display_name":"Xinyu Yang","orcid":"https://orcid.org/0000-0001-5117-4914"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Yang","raw_affiliation_strings":["Xi'an Jiaotong University, xian, China"],"raw_orcid":"https://orcid.org/0000-0001-5117-4914","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, xian, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.6582,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.98441971,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5667","last_page":"5676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9993000030517578,"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":0.9993000030517578,"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/T11431","display_name":"Action Observation and Synchronization","score":0.9861000180244446,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.980400025844574,"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/robustness","display_name":"Robustness (evolution)","score":0.5019999742507935},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3946000039577484},{"id":"https://openalex.org/keywords/cognitive-architecture","display_name":"Cognitive architecture","score":0.38119998574256897},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.3610999882221222},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.3598000109195709},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.35179999470710754},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.350600004196167},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3393000066280365},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3352000117301941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6482999920845032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5065000057220459},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5019999742507935},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.38119998574256897},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C96199812","wikidata":"https://www.wikidata.org/wiki/Q2145290","display_name":"Mental representation","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C2778949103","wikidata":"https://www.wikidata.org/wiki/Q600717","display_name":"Staring","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C2778538500","wikidata":"https://www.wikidata.org/wiki/Q3427","display_name":"Vega","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755340","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":22,"referenced_works":["https://openalex.org/W1966797434","https://openalex.org/W2046999604","https://openalex.org/W2075274068","https://openalex.org/W2787581402","https://openalex.org/W2891359673","https://openalex.org/W2964300796","https://openalex.org/W3207773797","https://openalex.org/W4212844288","https://openalex.org/W4256441345","https://openalex.org/W4303649263","https://openalex.org/W4360595168","https://openalex.org/W4379356527","https://openalex.org/W4385570630","https://openalex.org/W4386572391","https://openalex.org/W4391407004","https://openalex.org/W4392883891","https://openalex.org/W4398616892","https://openalex.org/W4399039312","https://openalex.org/W4400849567","https://openalex.org/W4401016710","https://openalex.org/W4401933151","https://openalex.org/W4403713281"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Emotion":[1,54],"Recognition":[2],"in":[3],"Conversations":[4],"remains":[5],"a":[6,51,103,139],"challenging":[7],"task":[8],"due":[9],"to":[10,36,86],"the":[11,45,65],"complex":[12],"interplay":[13],"of":[14,47],"textual,":[15],"acoustic":[16],"and":[17,49,67,99,106,119,134,152],"visual":[18,62,89],"signals.":[19],"While":[20],"recent":[21],"models":[22],"have":[23],"improved":[24],"performance":[25,149],"via":[26],"advanced":[27],"fusion":[28,66],"strategies,":[29],"they":[30],"often":[31],"lack":[32],"psychologically":[33,107],"meaningful":[34],"priors":[35],"guide":[37,97],"multimodal":[38,100],"alignment.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"revisit":[44],"use":[46],"CLIP":[48],"propose":[50],"novel":[52],"Visual":[53],"Guided":[55],"Anchoring":[56],"(VEGA)":[57],"mechanism":[58],"that":[59,74],"introduces":[60],"class-level":[61],"semantics":[63],"into":[64,138],"classification":[68],"process.":[69],"Distinct":[70],"from":[71,113],"prior":[72],"work":[73],"primarily":[75],"utilizes":[76],"CLIP's":[77],"textual":[78],"encoder,":[79],"our":[80,144],"approach":[81],"leverages":[82],"its":[83],"image":[84],"encoder":[85],"construct":[87],"emotion-specific":[88],"anchors":[90,96],"based":[91],"on":[92,150],"facial":[93],"exemplars.":[94],"These":[95],"unimodal":[98],"features":[101],"toward":[102],"perceptually":[104],"grounded":[105],"aligned":[108],"representation":[109],"space,":[110],"drawing":[111],"inspiration":[112],"cognitive":[114],"theories":[115],"(prototypical":[116],"emotion":[117],"categories":[118],"multisensory":[120],"integration).":[121],"A":[122],"stochastic":[123],"anchor":[124],"sampling":[125],"strategy":[126],"further":[127],"enhances":[128],"robustness":[129],"by":[130],"balancing":[131],"semantic":[132],"stability":[133],"intra-class":[135],"diversity.":[136],"Integrated":[137],"dual-branch":[140],"architecture":[141],"with":[142],"self-distillation,":[143],"VEGA-augmented":[145],"model":[146],"achieves":[147],"sota":[148],"IEMOCAP":[151],"MELD.":[153],"Code":[154],"is":[155],"available":[156],"at:":[157],"https://github.com/dkollias/VEGA":[158]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}