{"id":"https://openalex.org/W4415540608","doi":"https://doi.org/10.1145/3746027.3755637","title":"LES-CLIP: A Lightweight Emotion-Sensitive Adaptation of CLIP for Precise Similar Emotion Discrimination","display_name":"LES-CLIP: A Lightweight Emotion-Sensitive Adaptation of CLIP for Precise Similar Emotion Discrimination","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540608","doi":"https://doi.org/10.1145/3746027.3755637"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755637","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755637","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":"article","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/A5103805225","display_name":"Xiao Fu","orcid":"https://orcid.org/0009-0006-6601-5290"},"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":true,"raw_author_name":"Xiao Fu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0006-6601-5290","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pengyu Wang","orcid":"https://orcid.org/0009-0002-2485-8311"},"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":"Pengyu Wang","raw_affiliation_strings":["Xi'an Jiaotong University, xi'an, shannxi, China"],"raw_orcid":"https://orcid.org/0009-0002-2485-8311","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, xi'an, shannxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050052141","display_name":"Wei Xi","orcid":"https://orcid.org/0000-0001-9348-2982"},"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":"Wei Xi","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-9348-2982","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001944828","display_name":"Kun Zhao","orcid":"https://orcid.org/0000-0003-2326-4343"},"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":"Kun Zhao","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-2326-4343","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113690057","display_name":"Jiadong Feng","orcid":null},"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":"Jiadong Feng","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0007-6276-6182","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jizhong Zhao","orcid":"https://orcid.org/0000-0003-1037-9619"},"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":"Jizhong Zhao","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-1037-9619","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103805225"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30278869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5765","last_page":"5774"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.993399977684021,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.989799976348877,"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/facial-expression","display_name":"Facial expression","score":0.5494999885559082},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5494999885559082},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5374000072479248},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4964999854564667},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4422999918460846},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4341999888420105},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3968999981880188},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.3813999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6726999878883362},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5494999885559082},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5271000266075134},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32100000977516174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755637","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755637","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2738672149","https://openalex.org/W2745497104","https://openalex.org/W2963351448","https://openalex.org/W4283211831","https://openalex.org/W4285606530","https://openalex.org/W4294891853","https://openalex.org/W4382240798","https://openalex.org/W4382462760","https://openalex.org/W4386072096","https://openalex.org/W4386076045","https://openalex.org/W4386076638","https://openalex.org/W4390264360","https://openalex.org/W4391549765","https://openalex.org/W4393153464","https://openalex.org/W4395667994","https://openalex.org/W4396720269","https://openalex.org/W4400527853","https://openalex.org/W4402979749","https://openalex.org/W4403792374"],"related_works":[],"abstract_inverted_index":{"CLIP":[0,103],"has":[1],"been":[2],"widely":[3],"adopted":[4],"in":[5,30],"affective":[6],"computing":[7],"for":[8,104,136],"its":[9],"strong":[10],"vision-language":[11],"representation":[12],"capabilities.":[13],"However,":[14],"it":[15,185],"fails":[16],"to":[17,89,151],"accurately":[18],"distinguish":[19],"visually":[20],"similar":[21,108],"yet":[22],"label-distinct":[23],"facial":[24,61,121,153],"expressions.":[25],"This":[26,81],"limitation":[27],"is":[28],"rooted":[29],"CLIP's":[31,148],"encoding":[32],"paradigm":[33],"and":[34,50,63,98,120,155,188],"large-scale":[35],"contrastive":[36,163],"pretraining,":[37],"which":[38,133],"bias":[39],"the":[40,77,86,180],"model":[41],"toward":[42,165],"focusing":[43],"primarily":[44],"on":[45,179],"globally":[46],"salient":[47],"visual":[48,149],"features":[49],"aligning":[51],"them":[52],"with":[53],"broad":[54],"semantic":[55,79,82],"concepts.":[56],"Such":[57],"alignment":[58],"overlooks":[59],"subtle":[60,137],"variations":[62],"induces":[64],"representational":[65],"shortcuts,":[66],"where":[67],"emotionally":[68],"distinct":[69],"categories":[70],"are":[71],"projected":[72],"into":[73],"overlapping":[74],"regions":[75],"of":[76,107],"shared":[78],"space.":[80],"entanglement":[83],"severely":[84],"compromises":[85],"model's":[87],"ability":[88],"preserve":[90],"emotional":[91,113],"separability.":[92],"We":[93],"propose":[94],"LES-CLIP,":[95],"a":[96,141,157],"Lightweight":[97],"Emotion-Sensitive":[99,130],"framework":[100],"that":[101,146,161,172],"adapts":[102],"precise":[105],"discrimination":[106],"emotions.":[109],"LES-CLIP":[110,173],"achieves":[111,174],"fine-grained":[112,152],"sensitivity":[114,150],"using":[115],"only":[116],"simple":[117],"text":[118],"prompts":[119],"images.":[122],"It":[123],"introduces":[124],"three":[125],"novel":[126],"components:":[127],"1)":[128],"an":[129],"Adaptive":[131],"Mixture-of-Experts,":[132],"pre-adapts":[134],"representations":[135],"expression":[138],"discrimination;":[139],"2)":[140],"Prompt-Guided":[142],"Emotion":[143],"Discrimination":[144],"module":[145],"activates":[147],"cues;":[154],"3)":[156],"LES":[158],"hybrid":[159],"loss":[160],"guides":[162],"learning":[164],"accurate":[166],"emotion-label":[167],"alignment.":[168],"Extensive":[169],"experiments":[170],"demonstrate":[171],"state-of-the-art":[175],"performance,":[176],"reaching":[177],"70.18%":[178],"8-class":[181],"AffectNet":[182],"dataset.":[183],"Moreover,":[184],"converges":[186],"faster":[187],"requires":[189],"significantly":[190],"fewer":[191],"parameters.":[192]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}