{"id":"https://openalex.org/W4399487263","doi":"https://doi.org/10.1109/tmm.2024.3407693","title":"Label-Guided Dynamic Spatial-Temporal Fusion for Video-Based Facial Expression Recognition","display_name":"Label-Guided Dynamic Spatial-Temporal Fusion for Video-Based Facial Expression Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399487263","doi":"https://doi.org/10.1109/tmm.2024.3407693"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3407693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3407693","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5078897406","display_name":"Ziyang Zhang","orcid":"https://orcid.org/0000-0003-3266-7013"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Zhang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3266-7013","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101962577","display_name":"Xiang Tian","orcid":"https://orcid.org/0000-0002-9318-9994"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Tian","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073586303","display_name":"Yuan Zhang","orcid":"https://orcid.org/0000-0001-6720-6255"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6720-6255","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072766893","display_name":"Kailing Guo","orcid":"https://orcid.org/0000-0003-4753-9022"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kailing Guo","raw_affiliation_strings":["South China University of Technology, Guangzhou, China","Pazhou Laboratory, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4753-9022","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"Pazhou Laboratory, Guangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007354180","display_name":"Xiangmin Xu","orcid":"https://orcid.org/0000-0003-4573-5820"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangmin Xu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4573-5820","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":3.2667,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92193217,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"10503","last_page":"10513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8615999817848206,"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":0.8615999817848206,"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/computer-science","display_name":"Computer science","score":0.8261502385139465},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"Facial expression recognition","score":0.6487382650375366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5877344608306885},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5388374924659729},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5326851010322571},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4935532808303833},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4722941219806671},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.46815991401672363},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4261658191680908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261502385139465},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.6487382650375366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5877344608306885},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5388374924659729},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5326851010322571},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4935532808303833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4722941219806671},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.46815991401672363},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4261658191680908},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3407693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3407693","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8161837370","display_name":null,"funder_award_id":"61802131","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1938551397","https://openalex.org/W1981918162","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2096214539","https://openalex.org/W2134860945","https://openalex.org/W2161634108","https://openalex.org/W2194775991","https://openalex.org/W2277498883","https://openalex.org/W2345305417","https://openalex.org/W2487852963","https://openalex.org/W2795270851","https://openalex.org/W2798583514","https://openalex.org/W2805781993","https://openalex.org/W2895006884","https://openalex.org/W2896457183","https://openalex.org/W2960453713","https://openalex.org/W2962934715","https://openalex.org/W2963748103","https://openalex.org/W2963820951","https://openalex.org/W2980175391","https://openalex.org/W2981072818","https://openalex.org/W2990152177","https://openalex.org/W3032240740","https://openalex.org/W3034552680","https://openalex.org/W3034633006","https://openalex.org/W3047414713","https://openalex.org/W3093370878","https://openalex.org/W3094502228","https://openalex.org/W3121661546","https://openalex.org/W3128499902","https://openalex.org/W3130206595","https://openalex.org/W3136450870","https://openalex.org/W3138516171","https://openalex.org/W3154541964","https://openalex.org/W3173787706","https://openalex.org/W3178221902","https://openalex.org/W3179103990","https://openalex.org/W3184571633","https://openalex.org/W3195286673","https://openalex.org/W3203626638","https://openalex.org/W3205982571","https://openalex.org/W3206349670","https://openalex.org/W4206637691","https://openalex.org/W4210814853","https://openalex.org/W4225568094","https://openalex.org/W4246193833","https://openalex.org/W4304099113","https://openalex.org/W4372341111","https://openalex.org/W4385245566","https://openalex.org/W4386065595","https://openalex.org/W6628877408","https://openalex.org/W6637373629","https://openalex.org/W6640212811","https://openalex.org/W6755034786","https://openalex.org/W6779902714","https://openalex.org/W6788135285","https://openalex.org/W6795484856","https://openalex.org/W6803462455"],"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":{"Video-based":[0],"facial":[1],"expression":[2],"recognition":[3],"(FER)":[4],"in":[5,81,97],"the":[6,33,55,116,166],"wild":[7],"is":[8,20,88,95,162],"a":[9,21,130,153],"common":[10,22],"yet":[11],"challenging":[12],"task.":[13],"Extracting":[14,41],"spatial":[15,37,42,70,120,143,160,187],"and":[16,38,43,75,122,156],"temporal":[17,39,44,124,184],"features":[18,45,121,161],"simultaneously":[19],"approach":[23,53],"but":[24],"may":[25],"not":[26],"always":[27],"yield":[28],"optimal":[29],"results":[30,56,193],"due":[31],"to":[32,64,91,114,140,164,179],"distinct":[34],"nature":[35],"of":[36,57,69,72,78,119,159,169,186],"information.":[40],"cascadingly":[46],"has":[47],"been":[48],"proposed":[49],"as":[50,176],"an":[51],"alternative":[52],"However,":[54],"video-based":[58,99],"FER":[59,100,195],"sometimes":[60],"fall":[61],"short":[62],"compared":[63],"image-based":[65],"FER,":[66],"indicating":[67],"underutilization":[68],"information":[71],"each":[73,128,170],"frame":[74,79,86,112,129],"suboptimal":[76],"modeling":[77],"relations":[80],"spatial-temporal":[82,107],"fusion":[83,108,185],"strategies.":[84],"Although":[85],"label":[87,157],"highly":[89],"related":[90],"video":[92,131],"label,":[93,132],"it":[94],"overlooked":[96],"previous":[98],"methods.":[101],"This":[102],"paper":[103],"proposes":[104],"label-guided":[105],"dynamic":[106,177],"(LG-DSTF)":[109],"that":[110],"adopts":[111],"labels":[113],"enhance":[115],"discriminative":[117,142],"ability":[118],"guide":[123],"fusion.":[125],"By":[126],"assigning":[127],"two":[133],"auxiliary":[134],"classification":[135,167],"loss":[136],"functions":[137],"are":[138],"constructed":[139],"steer":[141],"feature":[144],"learning":[145],"at":[146],"different":[147],"levels.":[148],"The":[149,172],"cross":[150],"entropy":[151],"between":[152],"uniform":[154],"distribution":[155,158],"utilized":[163],"measure":[165],"confidence":[168,173],"frame.":[171],"values":[174],"serve":[175],"weights":[178],"emphasize":[180],"crucial":[181],"frames":[182],"during":[183],"features.":[188],"Our":[189],"LG-DSTF":[190],"achieves":[191],"state-of-the-art":[192],"on":[194],"benchmarks.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}