{"id":"https://openalex.org/W4415182217","doi":"https://doi.org/10.1109/iccv51701.2025.01169","title":"Multimodal Prompt Alignment for Facial Expression Recognition","display_name":"Multimodal Prompt Alignment for Facial Expression Recognition","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415182217","doi":"https://doi.org/10.1109/iccv51701.2025.01169"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.21017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090221825","display_name":"Fuyan Ma","orcid":"https://orcid.org/0000-0003-0483-8866"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fuyan Ma","raw_affiliation_strings":["Chinese Academy of Military Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Military Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113410708","display_name":"Yinong He","orcid":null},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiran He","raw_affiliation_strings":["Changchun University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changchun University of Science and Technology","institution_ids":["https://openalex.org/I106645853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641761","display_name":"Bin Sun","orcid":"https://orcid.org/0000-0002-7029-8784"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Sun","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067097659","display_name":"Shutao Li","orcid":"https://orcid.org/0000-0002-0585-9848"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shutao Li","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090221825"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27825704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12581","last_page":"12591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9061999917030334,"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":0.9061999917030334,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6628999710083008},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.619700014591217},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5565000176429749},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.553600013256073},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5052000284194946},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4814999997615814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41359999775886536},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.36079999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986999750137329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6879000067710876},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6628999710083008},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5565000176429749},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.553600013256073},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3384999930858612},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3059999942779541},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.21017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21017","pdf_url":"https://arxiv.org/pdf/2506.21017","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.21017","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.21017","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.21017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21017","pdf_url":"https://arxiv.org/pdf/2506.21017","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Prompt":[0],"learning":[1,66],"has":[2],"been":[3],"widely":[4],"adopted":[5],"to":[6,29,64,97],"efficiently":[7],"adapt":[8],"vision-language":[9],"models":[10],"(VLMs)":[11],"like":[12,95],"CLIP":[13,136],"for":[14,37,55,101],"various":[15],"downstream":[16],"tasks.":[17],"Despite":[18],"their":[19],"success,":[20],"current":[21],"VLM-based":[22],"facial":[23,42,103,173],"expression":[24],"recognition":[25],"(FER)":[26],"methods":[27,191],"struggle":[28],"capture":[30],"fine-grained":[31,61],"textual-visual":[32],"relationships,":[33],"which":[34],"are":[35],"essential":[36],"distinguishing":[38],"subtle":[39],"differences":[40],"between":[41,120,179],"expressions.":[43],"To":[44,128],"address":[45],"this":[46],"challenge,":[47],"we":[48,80,162],"propose":[49,163],"a":[50,82,90,164],"multimodal":[51],"prompt":[52,85],"alignment":[53,167,178],"framework":[54,188],"FER,":[56],"called":[57],"MPA-FER,":[58],"that":[59,88,146,169],"provides":[60],"semantic":[62],"guidance":[63],"the":[65,112,117,121,125,130,134,147,152,177,199,202],"process":[67],"of":[68,133,201],"prompted":[69,148],"visual":[70,142,149,182],"features,":[71,174],"resulting":[72],"in":[73],"more":[74],"precise":[75],"and":[76,124,181,205],"interpretable":[77],"representations.":[78],"Specifically,":[79],"introduce":[81],"multi-granularity":[83],"hard":[84,126],"generation":[86],"strategy":[87],"utilizes":[89],"large":[91],"language":[92],"model":[93,204],"(LLM)":[94],"ChatGPT":[96],"generate":[98],"detailed":[99],"descriptions":[100],"each":[102],"expression.":[104],"The":[105],"LLM-based":[106],"external":[107],"knowledge":[108],"is":[109],"injected":[110],"into":[111],"soft":[113,122],"prompts":[114,123],"by":[115],"minimizing":[116,206],"feature":[118,143],"discrepancy":[119],"prompts.":[127],"preserve":[129],"generalization":[131],"abilities":[132],"pretrained":[135,203],"model,":[137],"our":[138,187],"approach":[139],"incorporates":[140],"prototype-guided":[141],"alignment,":[144],"ensuring":[145],"features":[150],"from":[151],"frozen":[153],"image":[154],"encoder":[155],"align":[156],"closely":[157],"with":[158],"class-specific":[159],"prototypes.":[160],"Additionally,":[161],"cross-modal":[165],"global-local":[166],"module":[168],"focuses":[170],"on":[171,192],"expression-relevant":[172],"further":[175],"improving":[176],"textual":[180],"features.":[183],"Extensive":[184],"experiments":[185],"demonstrate":[186],"outperforms":[189],"state-of-the-art":[190],"three":[193],"FER":[194],"benchmark":[195],"datasets,":[196],"while":[197],"retaining":[198],"benefits":[200],"computational":[207],"costs.":[208]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-15T00:00:00"}