{"id":"https://openalex.org/W4413263788","doi":"https://doi.org/10.1109/tcsvt.2025.3596747","title":"TH-Mamba: Spatial-Temporal Correlation Learning for Mamba-Based Talking Head Generation","display_name":"TH-Mamba: Spatial-Temporal Correlation Learning for Mamba-Based Talking Head Generation","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413263788","doi":"https://doi.org/10.1109/tcsvt.2025.3596747"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3596747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3596747","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5100696102","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-0748-3669"},"institutions":[{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Xu","raw_affiliation_strings":["School of Computer Science and Technology and Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology, Wuhan, China","School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology and Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I43922553"]},{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I43922553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061566111","display_name":"Zhengxin Yu","orcid":"https://orcid.org/0009-0004-1851-3493"},"institutions":[{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixi Yu","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I43922553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103140908","display_name":"Kui Jiang","orcid":"https://orcid.org/0000-0002-4055-7503"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kui Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","School of Computer Science and Technology, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073213620","display_name":"Xiaocheng Feng","orcid":"https://orcid.org/0000-0001-6011-0496"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaocheng Feng","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","School of Computer Science and Technology, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051264473","display_name":"Chia\u2010Wen Lin","orcid":"https://orcid.org/0000-0002-9097-2318"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Wen Lin","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan","Department of Electrical Engineering, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100696102"],"corresponding_institution_ids":["https://openalex.org/I43922553"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26573134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"3","first_page":"2744","last_page":"2756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9707000255584717,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12290","display_name":"Human Motion and Animation","score":0.9700000286102295,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5194865465164185},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.42475682497024536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32705366611480713},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22063389420509338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5194865465164185},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.42475682497024536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32705366611480713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22063389420509338},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3596747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3596747","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6667938962","display_name":null,"funder_award_id":"62376201","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2395639500","https://openalex.org/W2593414223","https://openalex.org/W2604379605","https://openalex.org/W2738406145","https://openalex.org/W2944294033","https://openalex.org/W2950689937","https://openalex.org/W2960274051","https://openalex.org/W2963081548","https://openalex.org/W3006410788","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3099284785","https://openalex.org/W3165405144","https://openalex.org/W3174658753","https://openalex.org/W3175779516","https://openalex.org/W3186090335","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4200631136","https://openalex.org/W4210657261","https://openalex.org/W4281730245","https://openalex.org/W4283818626","https://openalex.org/W4297095647","https://openalex.org/W4304080398","https://openalex.org/W4382240211","https://openalex.org/W4385682917","https://openalex.org/W4386066256","https://openalex.org/W4386072021","https://openalex.org/W4386363058","https://openalex.org/W4390872116","https://openalex.org/W4390872769","https://openalex.org/W4391164079","https://openalex.org/W4392824768","https://openalex.org/W4392931432","https://openalex.org/W4396214353","https://openalex.org/W4399665715","https://openalex.org/W4400238700","https://openalex.org/W4402742556","https://openalex.org/W4402917159","https://openalex.org/W4402979798","https://openalex.org/W4402982696","https://openalex.org/W4403081627","https://openalex.org/W4403422565","https://openalex.org/W4403760842","https://openalex.org/W4403842425","https://openalex.org/W4414404693","https://openalex.org/W7133192266"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Talking":[0,189],"head":[1,10,199],"generation":[2],"aims":[3],"to":[4,57,84,113,142,173],"synthesize":[5],"high-quality":[6,197],"and":[7,17,29,38,48,63,70,101,146,160,170,178,206,225],"lip-synchronized":[8],"talking":[9,198],"videos":[11],"from":[12,45,88],"the":[13,24,30,36,41,59,89,94,98,102,115,152,157,164,175,182,204,210,219],"given":[14],"portrait":[15],"images":[16],"audio.":[18],"However,":[19],"previous":[20],"methods":[21],"directly":[22],"learn":[23],"alignment":[25],"between":[26,97],"lip":[27],"movements":[28],"driven":[31],"audio,":[32],"barely":[33],"focusing":[34],"on":[35,156,203],"fidelity":[37],"continuity":[39],"of":[40,61,212],"generated":[42,99],"videos,":[43],"suffering":[44],"visual":[46,144],"distortions":[47,145],"jitter.":[49,147],"To":[50],"deal":[51],"with":[52,132,138],"this":[53],"issue,":[54],"we":[55,78,150,185],"propose":[56],"promote":[58,174],"consistency":[60],"audio":[62,133],"image":[64],"by":[65,223],"exploring":[66],"their":[67],"spatiotemporal":[68,74,130],"relations,":[69],"construct":[71,186],"a":[72,139,187],"Mamba-based":[73],"fusion":[75],"scheme.":[76],"Specifically,":[77],"devise":[79],"an":[80,107],"Intra-frame":[81],"Mamba":[82,109,191],"module":[83,110],"characterize":[85],"facial":[86],"features":[87,134],"source":[90,104],"image,":[91],"which":[92,121,216],"encourages":[93],"content":[95,168],"consistence":[96],"frame":[100],"current":[103,220],"frame.":[105],"Meanwhile,":[106],"Inter-frame":[108],"is":[111,232],"designed":[112],"excavate":[114],"complementary":[116],"information":[117],"across":[118],"sequential":[119],"frames,":[120],"provides":[122],"clues":[123],"for":[124,196],"better":[125],"motion":[126,161],"simulation.":[127],"The":[128,230],"aggregated":[129],"representation":[131],"are":[135],"then":[136],"aligned":[137],"deformation":[140],"network":[141],"alleviate":[143],"In":[148],"addition,":[149],"investigate":[151],"practical":[153],"composite":[154],"constraints":[155],"structure,":[158],"details,":[159],"aspects,":[162],"involving":[163],"keypoint":[165],"constraint,":[166,169],"multi-scale":[167],"displacement":[171],"constraint":[172],"training":[176],"stability":[177],"model":[179],"performance.":[180],"With":[181],"above":[183],"strategies,":[184],"novel":[188],"Head":[190],"network,":[192],"termed":[193],"as":[194],"TH-Mamba":[195],"generation.":[200],"Extensive":[201],"experiments":[202],"HDTF":[205],"Mead-Neutral":[207],"datasets":[208],"verify":[209],"superiority":[211],"our":[213],"proposed":[214],"TH-Mamba,":[215],"significantly":[217],"outperforms":[218],"state-of-the-art":[221],"method":[222],"0.78dB":[224],"1.55dB":[226],"in":[227],"PSNR,":[228],"respectively.":[229],"demo":[231],"available":[233],"at":[234],"https://github.com/YZX-codesky/TH-Mamba.":[235]},"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-10-10T00:00:00"}