{"id":"https://openalex.org/W4408352453","doi":"https://doi.org/10.1109/icassp49660.2025.10888501","title":"Micro-expression Spotting based on Multi-modal Hierarchical Semantic-guided Deep Fusion Model*","display_name":"Micro-expression Spotting based on Multi-modal Hierarchical Semantic-guided Deep Fusion Model*","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352453","doi":"https://doi.org/10.1109/icassp49660.2025.10888501"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41317344"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9387000203132629,"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"}},"topics":[{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9387000203132629,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.8383263349533081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6791427135467529},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5561860799789429},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5546860098838806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5255095958709717},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4471096992492676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4075028598308563},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08146423101425171},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07657834887504578}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8383263349533081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791427135467529},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5561860799789429},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5546860098838806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5255095958709717},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4471096992492676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4075028598308563},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08146423101425171},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07657834887504578},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2060174972","https://openalex.org/W2100128860","https://openalex.org/W2151564195","https://openalex.org/W2163586280","https://openalex.org/W2567602236","https://openalex.org/W2571743746","https://openalex.org/W2587585332","https://openalex.org/W2899883316","https://openalex.org/W2929689627","https://openalex.org/W2962802777","https://openalex.org/W3128621833","https://openalex.org/W3128811047","https://openalex.org/W3128946893","https://openalex.org/W3141012605","https://openalex.org/W3162395899","https://openalex.org/W3162950802","https://openalex.org/W3194570764","https://openalex.org/W3205667279","https://openalex.org/W3206355728","https://openalex.org/W3206718318","https://openalex.org/W4386159691","https://openalex.org/W4390607209","https://openalex.org/W4391102514","https://openalex.org/W4391998254","https://openalex.org/W4399251150","https://openalex.org/W4400527623"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W3184921334","https://openalex.org/W4249589822","https://openalex.org/W4386895402","https://openalex.org/W2103063669","https://openalex.org/W4380551034","https://openalex.org/W3202382261","https://openalex.org/W2139675209","https://openalex.org/W4255446307","https://openalex.org/W4362466842"],"abstract_inverted_index":{"Most":[0],"existing":[1],"micro-expression":[2],"spotting":[3],"(MES)":[4],"methods":[5],"predominantly":[6],"learn":[7],"from":[8,165],"optical":[9,33,116],"flow":[10,34,117],"features":[11,92,150,154,164],"while":[12,121],"neglecting":[13],"the":[14,27,32,89,95,97,123,130,145,156,166,186,192],"detailed":[15],"information":[16,114],"contained":[17],"in":[18,155],"RGB":[19,37,119],"images":[20],"and":[21,36,78,109,118,151,159,174,191,205],"few":[22],"MES":[23,54],"works":[24],"have":[25],"explored":[26],"optimal":[28],"interaction":[29,111],"fusion":[30,51,108,131],"of":[31,112,126,132],"modality":[35,128],"modality.":[38],"To":[39,63],"address":[40],"these":[41],"issues,":[42],"we":[43,176],"propose":[44],"a":[45,56,72,79],"multi-scale":[46,90],"layered":[47],"semantic-guided":[48],"end-to-end":[49],"cross-modal":[50,65],"framework":[52],"for":[53],"with":[55],"convolutional":[57],"neural":[58],"network":[59],"(CNN)-Transformer,":[60],"named":[61],"MESFusion.":[62],"obtain":[64],"complementary":[66,113],"information,":[67],"this":[68],"scheme":[69],"sequentially":[70],"constructs":[71],"Multi-Scale":[73],"Feature":[74],"Extraction":[75],"Module":[76,85],"(MFEM)":[77],"Hierarchical":[80],"Cross-modal":[81],"Semantic":[82],"Guidance":[83],"Fusion":[84,100,138],"(H-CSGFM).":[86],"Guided":[87],"by":[88,94,170],"fused":[91,149],"extracted":[93],"MFEM,":[96],"Spatial":[98],"Cross-Attention":[99],"Unit":[101,139],"(SCAFU)":[102],"is":[103,141],"designed":[104],"to":[105,143,160],"achieve":[106],"comprehensive":[107],"global":[110],"between":[115,147],"images,":[120],"maintaining":[122],"intrinsic":[124],"characteristics":[125],"each":[127],"during":[129],"different":[133],"modalities.":[134],"The":[135],"Channel":[136],"Self-Attention":[137],"(CSAFU)":[140],"introduced":[142],"model":[144,201],"correlation":[146],"non-scale":[148],"source":[152,167],"image":[153],"channel":[157],"dimension":[158],"filter":[161],"out":[162],"interfering":[163],"images.":[168],"Furthermore,":[169],"hierarchically":[171],"integrating":[172],"SCAFU":[173],"CSAFU,":[175],"capture":[177],"diverse":[178],"informative":[179],"facial":[180],"cues.":[181],"Extensive":[182],"experiments":[183],"conducted":[184],"on":[185],"CAS(ME<sup":[187],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[188],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">)2</sup>":[189],"dataset":[190,196],"SAMM":[193],"Long":[194],"Videos":[195],"demonstrate":[197],"that":[198],"our":[199],"MESFusion":[200],"surpasses":[202],"competitive":[203],"baselines":[204],"achieves":[206],"new":[207],"state-of-the-art":[208],"results.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}