{"id":"https://openalex.org/W7133352978","doi":"https://doi.org/10.1109/ijcb65343.2025.11410713","title":"MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition","display_name":"MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7133352978","doi":"https://doi.org/10.1109/ijcb65343.2025.11410713"},"language":null,"primary_location":{"id":"doi:10.1109/ijcb65343.2025.11410713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11410713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","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/A5111337210","display_name":"Peihao Xiang","orcid":"https://orcid.org/0009-0007-4306-111X"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peihao Xiang","raw_affiliation_strings":["Florida International University,Miami,Florida,USA"],"affiliations":[{"raw_affiliation_string":"Florida International University,Miami,Florida,USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123169341","display_name":"Kaida Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaida Wu","raw_affiliation_strings":["Florida International University,Miami,Florida,USA"],"affiliations":[{"raw_affiliation_string":"Florida International University,Miami,Florida,USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123247094","display_name":"Ou Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ou Bai","raw_affiliation_strings":["Florida International University,Miami,Florida,USA"],"affiliations":[{"raw_affiliation_string":"Florida International University,Miami,Florida,USA","institution_ids":["https://openalex.org/I19700959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111337210"],"corresponding_institution_ids":["https://openalex.org/I19700959"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83396977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.953000009059906,"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":0.953000009059906,"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/T10057","display_name":"Face and Expression Recognition","score":0.016599999740719795,"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/T11448","display_name":"Face recognition and analysis","score":0.007600000128149986,"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/autoencoder","display_name":"Autoencoder","score":0.7652999758720398},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5903000235557556},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5482000112533569},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5217000246047974},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.47699999809265137},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47589999437332153},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42260000109672546},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.40619999170303345},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.39820000529289246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890999913215637},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7652999758720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6410999894142151},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5903000235557556},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5482000112533569},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.47699999809265137},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47589999437332153},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42260000109672546},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39489999413490295},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.26980000734329224},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcb65343.2025.11410713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11410713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","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":26,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2030931454","https://openalex.org/W2064675550","https://openalex.org/W2110485445","https://openalex.org/W2157331557","https://openalex.org/W2216125271","https://openalex.org/W2341528187","https://openalex.org/W2803193013","https://openalex.org/W2926527602","https://openalex.org/W2963524571","https://openalex.org/W2977259558","https://openalex.org/W2990503944","https://openalex.org/W3099284785","https://openalex.org/W3126721948","https://openalex.org/W3157999215","https://openalex.org/W3194949249","https://openalex.org/W3206349670","https://openalex.org/W4281738330","https://openalex.org/W4313156423","https://openalex.org/W4313166855","https://openalex.org/W4321353501","https://openalex.org/W4372341111","https://openalex.org/W4388189896","https://openalex.org/W4399168297","https://openalex.org/W4401328604","https://openalex.org/W7133239857"],"related_works":[],"abstract_inverted_index":{"This":[0,96],"paper":[1],"expands":[2],"the":[3,8,40,47,54,62,67,75,86,99,130,147,172,175,179],"cascaded":[4,33,125],"network":[5],"branch":[6],"of":[7,50,117,132,174,181],"autoencoder-based":[9,123],"multi-task":[10,124],"learning":[11,126],"(MTL)":[12],"framework":[13],"for":[14,23,167],"dynamic":[15,72,94,105,133,137,141,168,183],"facial":[16,142,169],"expression":[17,143,170],"recognition,":[18,144,171],"namely":[19],"Multi-Task":[20],"Cascaded":[21],"Autoencoder":[22,78],"Dynamic":[24],"Facial":[25],"Expression":[26],"Recognition":[27],"(MTCAE-DFER).":[28],"MTCAE-DFER":[29,176],"builds":[30],"a":[31],"plug-and-play":[32],"decoder":[34,48,59],"module,":[35],"which":[36,145],"is":[37],"based":[38],"on":[39,140,163],"Vision":[41],"Transformer":[42,51],"(ViT)":[43],"architecture":[44],"and":[45,89,103,136,157,178],"employs":[46],"concept":[49],"to":[52,114,128],"reconstruct":[53],"multihead":[55],"attention":[56],"module.":[57],"The":[58],"output":[60,82],"from":[61],"previous":[63],"task":[64],"serves":[65],"as":[66,84],"query":[68],"(Q),":[69],"representing":[70,92],"local":[71,104],"features,":[73],"while":[74],"Video":[76],"Masked":[77],"(VideoMAE)":[79],"shared":[80],"encoder":[81],"acts":[83],"both":[85],"key":[87],"(K)":[88],"value":[90],"(V),":[91],"global":[93,102],"features.":[95],"setup":[97],"facilitates":[98],"interaction":[100,185],"between":[101],"features":[106],"across":[107],"related":[108,187],"tasks.":[109],"Additionally,":[110],"this":[111],"proposal":[112],"aims":[113],"alleviate":[115],"overfitting":[116],"complex":[118],"large":[119],"model.":[120],"We":[121],"utilize":[122],"approach":[127],"explore":[129],"impact":[131],"face":[134,138],"detection":[135],"landmark":[139],"enhances":[146],"model\u2019s":[148],"generalization":[149],"ability.":[150],"After":[151],"we":[152],"conduct":[153],"extensive":[154],"ablation":[155],"experiments":[156],"comparison":[158],"with":[159],"state-of-the-art":[160],"(SOTA)":[161],"methods":[162],"various":[164],"public":[165],"datasets":[166],"robustness":[173],"model":[177],"effectiveness":[180],"global-local":[182],"feature":[184],"among":[186],"tasks":[188],"have":[189],"been":[190],"proven.":[191]},"counts_by_year":[],"updated_date":"2026-03-05T07:30:30.508283","created_date":"2026-03-04T00:00:00"}