{"id":"https://openalex.org/W4402915821","doi":"https://doi.org/10.1109/icip51287.2024.10647657","title":"SLNL: Soft Label Regularization For Semi-Supervised Facial Expression Recognition With Negative Label Learning","display_name":"SLNL: Soft Label Regularization For Semi-Supervised Facial Expression Recognition With Negative Label Learning","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915821","doi":"https://doi.org/10.1109/icip51287.2024.10647657"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647657","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","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/A5000903346","display_name":"Youwei Zhang","orcid":"https://orcid.org/0000-0001-6640-9317"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youwei Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036650015","display_name":"Jing Jiang","orcid":"https://orcid.org/0000-0001-5424-6338"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Jiang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065808540","display_name":"Yuying Zhao","orcid":"https://orcid.org/0009-0001-6976-8638"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuying Zhao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077313814","display_name":"Kongming Liang","orcid":"https://orcid.org/0000-0002-4726-093X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kongming Liang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"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":"3","issue":null,"first_page":"423","last_page":"429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8863000273704529,"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":0.8863000273704529,"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.7932999730110168,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6641792058944702},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6355544924736023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.606429934501648},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5632287263870239},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"Facial expression recognition","score":0.5248054265975952},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5078478455543518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44243934750556946},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38128662109375},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.3025701642036438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6641792058944702},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6355544924736023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.606429934501648},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5632287263870239},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.5248054265975952},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5078478455543518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44243934750556946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38128662109375},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3025701642036438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647657","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","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":33,"referenced_works":["https://openalex.org/W2035372623","https://openalex.org/W2103943262","https://openalex.org/W2194775991","https://openalex.org/W2341528187","https://openalex.org/W2566079294","https://openalex.org/W2738672149","https://openalex.org/W2745497104","https://openalex.org/W2904483377","https://openalex.org/W2982153880","https://openalex.org/W3003720578","https://openalex.org/W3016125456","https://openalex.org/W3035336958","https://openalex.org/W3035682985","https://openalex.org/W3091476632","https://openalex.org/W3096651426","https://openalex.org/W3173787706","https://openalex.org/W3185372235","https://openalex.org/W4310007442","https://openalex.org/W4312108898","https://openalex.org/W4312465353","https://openalex.org/W4313128368","https://openalex.org/W4319300140","https://openalex.org/W4386076243","https://openalex.org/W4390871994","https://openalex.org/W6740005241","https://openalex.org/W6762913911","https://openalex.org/W6765939562","https://openalex.org/W6770578729","https://openalex.org/W6771630921","https://openalex.org/W6773005947","https://openalex.org/W6781063151","https://openalex.org/W6802864417","https://openalex.org/W6844056358"],"related_works":["https://openalex.org/W4205986151","https://openalex.org/W2355913164","https://openalex.org/W1153638794","https://openalex.org/W2168968280","https://openalex.org/W2116055069","https://openalex.org/W2162992774","https://openalex.org/W4323520705","https://openalex.org/W2356663679","https://openalex.org/W2169777806","https://openalex.org/W3027190010"],"abstract_inverted_index":{"Semi-supervised":[0],"learning":[1],"(SSL)":[2],"methods":[3,23],"have":[4],"been":[5],"widely":[6,137],"employed":[7],"in":[8,52],"facial":[9],"expression":[10],"recognition":[11],"(FER)":[12],"to":[13,29],"eliminate":[14],"the":[15,44,84,103,107,142],"substantial":[16],"cost":[17],"of":[18,86],"acquiring":[19],"well-labeled":[20],"samples.":[21],"These":[22],"typically":[24],"involve":[25],"assigning":[26],"pseudo":[27,48,104],"labels":[28,120],"unlabeled":[30,88,92],"samples":[31],"beyond":[32],"a":[33,65,72,98],"certain":[34],"confidence":[35,96],"threshold":[36],"for":[37,112],"calculating":[38,122],"cross-entropy":[39],"loss.":[40],"However,":[41],"they":[42],"overlook":[43],"correctness":[45],"issue":[46],"with":[47,147],"labels,":[49],"potentially":[50],"resulting":[51],"network":[53,79],"over-fitting.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"introduce":[59],"an":[60],"SLNL":[61,130],"model":[62,131],"that":[63],"incorporates":[64],"Soft":[66],"Label":[67,74],"Regularization":[68],"(SLR)":[69],"module":[70],"and":[71,106],"Negative":[73],"Learning":[75],"(NLL)":[76],"module,":[77],"preventing":[78],"from":[80],"over-fitting":[81],"while":[82],"enhancing":[83],"efficiency":[85],"utilizing":[87],"data.":[89,150],"For":[90],"each":[91],"sample":[93],"whose":[94],"pseudo-label":[95],"surpasses":[97],"threshold,":[99],"SLR":[100],"concurrently":[101],"uses":[102],"label":[105,111],"previously":[108],"recorded":[109],"soft":[110],"supervised":[113],"learning.":[114],"Additionally,":[115],"NLL":[116],"dynamically":[117],"explores":[118],"negative":[119],"by":[121],"top-k":[123],"accuracy,":[124],"further":[125],"removing":[126],"irrelevant":[127],"information.":[128],"The":[129],"achieves":[132],"state-of-the-art":[133],"performance":[134],"across":[135],"several":[136],"used":[138],"datasets,":[139],"notably":[140],"surpassing":[141],"fully-supervised":[143],"baseline":[144],"on":[145],"AffectNet":[146],"fewer":[148],"labeled":[149]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}