{"id":"https://openalex.org/W4413278381","doi":"https://doi.org/10.1109/icip55913.2025.11084644","title":"CHTMAE: Cross-Modal Hierarchical Temporal-Spatial Masked Autoencoder Model for Micro-Expression Recognition","display_name":"CHTMAE: Cross-Modal Hierarchical Temporal-Spatial Masked Autoencoder Model for Micro-Expression Recognition","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413278381","doi":"https://doi.org/10.1109/icip55913.2025.11084644"},"language":"en","primary_location":{"id":"doi:10.1109/icip55913.2025.11084644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5060014765","display_name":"Zhihua Xie","orcid":"https://orcid.org/0000-0002-4226-7497"},"institutions":[{"id":"https://openalex.org/I41317344","display_name":"Jiangxi Science and Technology Normal University","ror":"https://ror.org/04r1zkp10","country_code":"CN","type":"education","lineage":["https://openalex.org/I41317344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Xie","raw_affiliation_strings":["Jiangxi Science and Technology Normal University,Jiangxi Province Key Lab of Advanced Electronic Materials,Nanchang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Science and Technology Normal University,Jiangxi Province Key Lab of Advanced Electronic Materials,Nanchang,China","institution_ids":["https://openalex.org/I41317344"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haolin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I41317344","display_name":"Jiangxi Science and Technology Normal University","ror":"https://ror.org/04r1zkp10","country_code":"CN","type":"education","lineage":["https://openalex.org/I41317344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolin Chang","raw_affiliation_strings":["Jiangxi Science and Technology Normal University,Jiangxi Province Key Lab of Advanced Electronic Materials,Nanchang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Science and Technology Normal University,Jiangxi Province Key Lab of Advanced Electronic Materials,Nanchang,China","institution_ids":["https://openalex.org/I41317344"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guohua Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I41317344","display_name":"Jiangxi Science and Technology Normal University","ror":"https://ror.org/04r1zkp10","country_code":"CN","type":"education","lineage":["https://openalex.org/I41317344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohua Miao","raw_affiliation_strings":["Jiangxi Science and Technology Normal University,Jiangxi Province Key Lab of Advanced Electronic Materials,Nanchang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Science and Technology Normal University,Jiangxi Province Key Lab of Advanced Electronic Materials,Nanchang,China","institution_ids":["https://openalex.org/I41317344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100388707","display_name":"Zuhong Lu","orcid":"https://orcid.org/0000-0003-3332-2615"},"institutions":[{"id":"https://openalex.org/I26653445","display_name":"Tellabs (Canada)","ror":"https://ror.org/051gaae98","country_code":"CA","type":"company","lineage":["https://openalex.org/I26653445","https://openalex.org/I4210142238"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhaojin Lu","raw_affiliation_strings":["Tellhow Group Co,Jiangxi Tellhow Animation College,Nanchang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tellhow Group Co,Jiangxi Tellhow Animation College,Nanchang,China","institution_ids":["https://openalex.org/I26653445"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21062416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"552","last_page":"557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.7903000116348267,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.7903000116348267,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.770799994468689,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.758899986743927,"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":0.8387010097503662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6737270951271057},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6653332710266113},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5786255598068237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5357031226158142},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4674927294254303},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16948038339614868},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0474487841129303}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8387010097503662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6737270951271057},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6653332710266113},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5786255598068237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5357031226158142},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4674927294254303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16948038339614868},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0474487841129303},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip55913.2025.11084644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322665","display_name":"Natural Science Foundation of Jiangxi Province","ror":null},{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2006426145","https://openalex.org/W2044106642","https://openalex.org/W2139916508","https://openalex.org/W2163586280","https://openalex.org/W2426188534","https://openalex.org/W2478411578","https://openalex.org/W2567602236","https://openalex.org/W2959679536","https://openalex.org/W2962858109","https://openalex.org/W4224951303","https://openalex.org/W4225934279","https://openalex.org/W4280528148","https://openalex.org/W4296204322","https://openalex.org/W4313156423","https://openalex.org/W4319073169","https://openalex.org/W4362674604","https://openalex.org/W4386047789","https://openalex.org/W4386075510","https://openalex.org/W4386076581","https://openalex.org/W4386158925","https://openalex.org/W4389611070","https://openalex.org/W4392904201","https://openalex.org/W4392910806","https://openalex.org/W4396628274","https://openalex.org/W4396712599","https://openalex.org/W4397031783","https://openalex.org/W4399284125","https://openalex.org/W4402979347","https://openalex.org/W4402980577","https://openalex.org/W4405315888","https://openalex.org/W4405868681"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W4297051394","https://openalex.org/W4220775285","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Most":[0],"Micro-expression":[1],"recognition":[2],"(MER)":[3],"methods":[4],"tend":[5],"to":[6,39,103],"explore":[7],"only":[8],"single":[9],"modality":[10],"(key":[11],"frames":[12],"or":[13],"optical":[14,78],"flow),":[15],"ignoring":[16],"intermediate":[17],"frames,":[18],"which":[19,138],"usually":[20],"results":[21,172],"in":[22,108],"the":[23,30,61,86,104,109,116,125,141,148,158,174,177],"omission":[24],"of":[25,32,111,128,131,176,184],"critical":[26],"temporal":[27],"cues.":[28],"Meanwhile,":[29],"generalization":[31],"MER":[33,55,186],"deep":[34,59],"models":[35],"remains":[36],"limited":[37],"due":[38],"insufficient":[40],"annotated":[41],"micro-expression":[42],"(ME)":[43],"samples.":[44],"To":[45,98],"address":[46],"these":[47],"challenges,":[48],"this":[49,113,192],"paper":[50],"proposes":[51],"an":[52],"efficient":[53],"self-supervised":[54],"scheme":[56],"based":[57],"on":[58,89,167],"learning,":[60],"cross-modal":[62],"hierarchical":[63],"temporal-spatial":[64],"masked":[65,82],"autoencoder":[66],"framework,":[67],"named":[68],"CHTMAE.":[69],"Specifically,":[70],"CHTMAE":[71,159],"constructs":[72],"a":[73,129],"reconstruction":[74],"task":[75],"via":[76],"both":[77],"flow-":[79],"and":[80,91,147],"image-based":[81],"autoencoders":[83],"(MAE)":[84],"for":[85,163,191],"multi-feature":[87],"representation":[88,166],"motion":[90,165],"spatial":[92],"features":[93],"from":[94],"unlabeled":[95],"ME":[96],"data.":[97],"obtain":[99],"spatiotemporal":[100],"fusion":[101,162],"related":[102],"action":[105],"unit":[106],"(AU)":[107],"priors":[110],"MEs,":[112],"work":[114],"designs":[115],"Hierarchical":[117],"Temporal-Spatial":[118,132],"Feature":[119,133],"Guided":[120,134,143],"Enhancement":[121,135],"Component":[122],"(H-TSGEC).":[123],"Generally,":[124],"H-TSGEC":[126],"consists":[127],"cascade":[130],"Units":[136],"(TSGEUs)":[137],"further":[139],"comprise":[140],"Spatiotemporal":[142],"Cross-Attention":[144],"Module":[145,152],"(SGCAM)":[146],"Frame":[149],"Token":[150],"Attention":[151],"(FTAM).":[153],"By":[154],"cascading":[155],"multiple":[156],"TSGEUs,":[157],"achieves":[160],"progressive":[161],"diverse":[164],"subtle":[168],"MEs.":[169],"Extensive":[170],"experimental":[171],"validate":[173],"effectiveness":[175],"CHEMAE":[178],"model,":[179],"whose":[180],"performance":[181],"surpasses":[182],"that":[183],"state-of-the-art":[185],"methods.":[187],"The":[188],"source":[189],"codes":[190],"model":[193],"are":[194],"available":[195],"on:":[196],"https://github.com/cc99forever/CHTMAE99/tree/master.":[197]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}