{"id":"https://openalex.org/W7133332037","doi":"https://doi.org/10.1016/j.patcog.2026.113415","title":"HMamba-3DFT: A hierarchical mamba framework for emotion-driven semantic 3D facial tracking","display_name":"HMamba-3DFT: A hierarchical mamba framework for emotion-driven semantic 3D facial tracking","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133332037","doi":"https://doi.org/10.1016/j.patcog.2026.113415"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2026.113415","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113415","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.patcog.2026.113415","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127994040","display_name":"Haodong Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Jin","raw_affiliation_strings":["Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China"],"raw_orcid":"https://orcid.org/0009-0003-3918-648X","affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107942398","display_name":"Muwei Jian","orcid":null},"institutions":[{"id":"https://openalex.org/I59483232","display_name":"Shandong University of Finance and Economics","ror":"https://ror.org/02e2nnq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I59483232"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Muwei Jian","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University of Finance and Economics, Jinan 250014, China"],"raw_orcid":"https://orcid.org/0000-0002-4249-2264","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University of Finance and Economics, Jinan 250014, China","institution_ids":["https://openalex.org/I59483232"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124120474","display_name":"Derui Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Derui Ding","raw_affiliation_strings":["Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China"],"raw_orcid":"https://orcid.org/0000-0001-7402-6682","affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127975690","display_name":"Hui Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hui Yu","raw_affiliation_strings":["School of Psychology and Neuroscience, University of Glasgow, Glasgow G12 8QB, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-7655-9228","affiliations":[{"raw_affiliation_string":"School of Psychology and Neuroscience, University of Glasgow, Glasgow G12 8QB, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5107942398","https://openalex.org/A5127975690"],"corresponding_institution_ids":["https://openalex.org/I59483232","https://openalex.org/I7882870"],"apc_list":{"value":2710,"currency":"USD","value_usd":2710},"apc_paid":{"value":2710,"currency":"USD","value_usd":2710},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41848292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"178","issue":null,"first_page":"113415","last_page":"113415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.6952999830245972,"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/T11448","display_name":"Face recognition and analysis","score":0.6952999830245972,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.22939999401569366,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.020999999716877937,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/facial-expression","display_name":"Facial expression","score":0.6136999726295471},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.59170001745224},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.548799991607666},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.45820000767707825},{"id":"https://openalex.org/keywords/jitter","display_name":"Jitter","score":0.42149999737739563},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.39890000224113464},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3952000141143799},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.3847000002861023},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.3458000123500824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6915000081062317},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6312000155448914},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.45820000767707825},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.3847000002861023},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C54654163","wikidata":"https://www.wikidata.org/wiki/Q5428359","display_name":"Face hallucination","level":5,"score":0.32580000162124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C2780905192","wikidata":"https://www.wikidata.org/wiki/Q2341604","display_name":"Facial muscles","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.25920000672340393},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.patcog.2026.113415","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113415","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},{"id":"pmh:oai:eprints.gla.ac.uk:381621","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/6716.html>","pdf_url":"https://eprints.gla.ac.uk/381621/1/381621.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1016/j.patcog.2026.113415","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113415","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.45608118176460266}],"awards":[{"id":"https://openalex.org/G2217773215","display_name":null,"funder_award_id":"101130271","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G8832703587","display_name":null,"funder_award_id":"EP/Z000025/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320326185","display_name":"Taishan Scholar Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320338337","display_name":"H2020 Marie Sk\u0142odowska-Curie Actions","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2131894637","https://openalex.org/W2766596268","https://openalex.org/W2769666294","https://openalex.org/W2944006115","https://openalex.org/W3082551980","https://openalex.org/W3180794345","https://openalex.org/W4312549026","https://openalex.org/W4380839097","https://openalex.org/W4385569638","https://openalex.org/W4401829187","https://openalex.org/W4402072291","https://openalex.org/W4403936283","https://openalex.org/W4409102430","https://openalex.org/W4410393390"],"related_works":[],"abstract_inverted_index":{"\u2022":[0,10,18],"First":[1],"Mamba-based":[2],"framework":[3],"HMamba-3DFT":[4],"tailored":[5,95],"for":[6,35,82,96,239],"3D":[7,30,97,118,219],"facial":[8,16,68,83,98,119,190,194,203,220],"tracking":[9,32,99],"BSTV-Mamba":[11],"with":[12,25,193],"BSTS-Scan":[13],"capture":[14,113,155],"spatiotemporal":[15,129,141,149],"dynamics":[17,73],"Dual":[19],"optimization":[20,238],"integrates":[21],"dynamic":[22,135,169],"emotion-driven":[23,170,186,202],"modeling":[24],"semantic":[26,191],"alignment":[27,192],"Monocular":[28],"video-based":[29],"face":[31],"is":[33],"vital":[34],"interactive":[36],"pattern":[37],"recognition":[38],"and":[39,55,74,114],"human":[40],"avatars.":[41],"Most":[42],"existing":[43],"image-based":[44],"methods":[45],"fail":[46],"to":[47,173,197],"model":[48],"temporal":[49,80],"dependencies":[50],"in":[51,67,117,162],"video,":[52],"causing":[53],"jitter":[54],"inaccuracies.":[56],"Furthermore,":[57],"they":[58],"also":[59,234],"often":[60],"neglect":[61],"the":[62,92,127,134,175,199,211,217,226,230],"continuous":[63,163],"multi-modal":[64,158],"signals":[65,160],"present":[66],"videos":[69],"such":[70],"as":[71],"expression":[72],"emotional":[75,227],"cues":[76],"that":[77,216],"provide":[78],"essential":[79],"drivers":[81],"modeling.":[84,204],"To":[85,125,154],"this":[86,88],"end,":[87],"study":[89],"first":[90],"explores":[91],"Mamba":[93,104,143],"architecture":[94],"by":[100,182],"proposing":[101],"a":[102,122,139,147,168],"hierarchical":[103],"framework,":[105],"termed":[106],"HMamba-3DFT.":[107],"The":[108],"proposed":[109],"network":[110,212],"can":[111],"efficiently":[112],"track":[115],"variations":[116],"shapes":[120],"from":[121,236],"monocular":[123],"video.":[124],"exploit":[126],"global":[128],"correlations":[130],"across":[131],"frames":[132,232],"of":[133,178,201,229],"face,":[136],"we":[137,166,188],"develop":[138],"bidirectional":[140,148],"vision":[142],"(BSTV-Mamba)":[144],"module":[145],"featuring":[146],"selective":[150],"scan":[151],"(BSTS-Scan)":[152],"mechanism.":[153,171],"temporally":[156],"evolving":[157],"emotion":[159,195],"embedded":[161],"video":[164],"sequences,":[165],"introduce":[167],"Additionally,":[172],"mitigate":[174],"potential":[176],"degradation":[177],"reconstruction":[179],"fidelity":[180],"caused":[181],"an":[183],"over-reliance":[184],"on":[185,245],"cues,":[187],"integrate":[189],"driving":[196],"enhance":[198],"accuracy":[200],"This":[205],"integrated":[206],"dual-optimization":[207],"strategy":[208],"systematically":[209],"guides":[210],"during":[213],"training,":[214],"ensuring":[215],"reconstructed":[218],"mesh":[221],"not":[222],"only":[223],"accurately":[224],"captures":[225],"attributes":[228],"input":[231],"but":[233],"benefits":[235],"enhanced":[237],"more":[240],"precise":[241],"reconstruction.":[242],"Extensive":[243],"evaluations":[244],"benchmark":[246],"datasets":[247],"show":[248],"competitive":[249],"performance":[250],"against":[251],"state-of-the-art":[252],"methods.":[253]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-03-04T00:00:00"}