{"id":"https://openalex.org/W7133485336","doi":"https://doi.org/10.1007/s44443-026-00617-6","title":"HimaTalk: robust audio-driven Tibetan talking head generation via bi-directional Mamba and spatiotemporal constraints","display_name":"HimaTalk: robust audio-driven Tibetan talking head generation via bi-directional Mamba and spatiotemporal constraints","publication_year":2026,"publication_date":"2026-03-04","ids":{"openalex":"https://openalex.org/W7133485336","doi":"https://doi.org/10.1007/s44443-026-00617-6"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-026-00617-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00617-6","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44443-026-00617-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128109161","display_name":"Tingting Du","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Du","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032527618","display_name":"Xiangzhen He","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangzhen He","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128084370","display_name":"Xianghe Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianghe Meng","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128127707","display_name":"Xue Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Ding","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128057118","display_name":"Wenhao Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Jiang","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128062898","display_name":"Xiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Wang","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210823","display_name":"Haotian Zhu","orcid":"https://orcid.org/0000-0002-7106-6782"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Zhu","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121022278","display_name":"Jingbin Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbin Hao","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128124367","display_name":"Shibiao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibiao Shi","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128100347","display_name":"Xu Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Ouyang","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128106376","display_name":"Ruilei Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruilei Shan","raw_affiliation_strings":["Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Linguistic and Cultural Computing Ministry of Education, Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing, Gansu Province Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5032527618"],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20818953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8758000135421753,"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":0.8758000135421753,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.030700000002980232,"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/T10860","display_name":"Speech and Audio Processing","score":0.0284000001847744,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4194999933242798},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.28540000319480896},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.22769999504089355},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2190999984741211}],"concepts":[{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41839998960494995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3619999885559082},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3474999964237213},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3474000096321106},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28540000319480896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2574999928474426},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.25440001487731934},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.22769999504089355},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2190999984741211}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44443-026-00617-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00617-6","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:35465ed179c345f181347defed59b047","is_oa":true,"landing_page_url":"https://doaj.org/article/35465ed179c345f181347defed59b047","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of King Saud University: Computer and Information Sciences, Vol 38, Iss 5 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44443-026-00617-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00617-6","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1544825641","display_name":null,"funder_award_id":"62566058","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":23,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2962785568","https://openalex.org/W2981087920","https://openalex.org/W3035719652","https://openalex.org/W3099284785","https://openalex.org/W3109715615","https://openalex.org/W3180770160","https://openalex.org/W3197199219","https://openalex.org/W4280631290","https://openalex.org/W4372347128","https://openalex.org/W4386072021","https://openalex.org/W4402726937","https://openalex.org/W4403791714","https://openalex.org/W4403842425","https://openalex.org/W4404612908","https://openalex.org/W4409369524","https://openalex.org/W4411472278","https://openalex.org/W4413145441","https://openalex.org/W4413146076","https://openalex.org/W4413147005","https://openalex.org/W4413155927"],"related_works":[],"abstract_inverted_index":{"High-fidelity":[0],"audio-driven":[1],"talking-head":[2,232],"generation":[3,125],"holds":[4],"significant":[5],"promise":[6],"for":[7,56,180,235],"digital":[8],"communication,":[9],"online":[10],"education,":[11],"and":[12,35,72,89,106,129,152,176,209,258,275],"the":[13,36,69,74,134,170,207,223,229],"preservation":[14],"of":[15,38,76,241],"minority":[16],"languages.":[17],"However,":[18],"applying":[19],"existing":[20],"diffusion-based":[21],"frameworks":[22],"to":[23,32,40,93,98,123,172,184,201,216,283,294],"low-resource":[24],"languages":[25],"like":[26],"Tibetan":[27,224],"remains":[28],"challenging,":[29],"primarily":[30],"due":[31],"data":[33],"scarcity":[34],"difficulty":[37],"generalizing":[39],"unseen":[41],"prosodic":[42],"patterns.":[43],"Current":[44],"state-of-the-art":[45,253],"systems":[46],"typically":[47],"rely":[48],"on":[49,256,261],"Transformer-based":[50],"temporal":[51,78,107,136,162,292],"attention":[52,137],"mechanisms.":[53],"While":[54],"effective":[55],"short":[57],"sequences,":[58],"these":[59,83,111],"architectures":[60],"suffer":[61],"from":[62,206],"quadratic":[63],"complexity":[64,166],"($$\\mathcal":[65,167],"{O}(T^2)$$),":[66],"which":[67],"limits":[68],"context":[70,163],"window":[71],"hinders":[73],"modeling":[75],"long-range":[77],"dependencies.":[79],"In":[80],"cross-lingual":[81,130],"transfer,":[82],"limitations":[84],"can":[85],"be":[86],"further":[87],"exacerbated,":[88],"models":[90],"may":[91],"struggle":[92],"maintain":[94],"structural":[95],"stability,":[96],"leading":[97],"artifacts":[99],"such":[100],"as":[101],"motion":[102],"stiffness,":[103],"background":[104],"warping,":[105],"flickering.":[108],"To":[109],"address":[110],"limitations,":[112],"we":[113,190],"present":[114],"HimaTalk":[115,251],"(Himalayan":[116],"Talking":[117,225],"Head),":[118],"a":[119,140,147,192,196,210,262],"unified":[120],"framework":[121,268],"designed":[122],"optimize":[124],"quality,":[126],"computational":[127],"efficiency,":[128],"generalization.":[131],"We":[132,220],"replace":[133],"standard":[135],"layer":[138],"with":[139,154,164,243],"Bidirectional":[141],"Mamba":[142],"Motion":[143],"Module.":[144],"By":[145],"employing":[146],"dual":[148],"scanning":[149],"mechanism":[150],"(forward":[151],"backward)":[153],"learnable":[155],"gated":[156],"fusion,":[157],"this":[158],"module":[159],"captures":[160],"global":[161],"linear":[165],"{O}(T)$$),":[168],"enabling":[169],"model":[171,297],"incorporate":[173],"both":[174],"past":[175],"future":[177],"audio":[178],"cues":[179],"smoother":[181],"transitions.":[182],"Furthermore,":[183],"ensure":[185],"robustness":[186],"against":[187],"domain":[188],"shifts,":[189],"introduce":[191],"spatiotemporal":[193],"dual-constraint":[194],"strategy:":[195],"facial":[197],"region-weighted":[198],"spatial":[199],"loss":[200,215],"effectively":[202],"decouple":[203],"foreground":[204],"dynamics":[205],"background,":[208],"latent":[211],"second-order":[212],"difference":[213],"consistency":[214],"suppress":[217],"high-frequency":[218],"jitter.":[219],"also":[221],"release":[222],"Head":[226],"Dataset":[227],"(TTHD),":[228],"first":[230],"high-definition":[231],"video":[233,242],"dataset":[234],"Tibetan,":[236],"comprising":[237],"approximately":[238,280],"40":[239],"hours":[240],"diverse":[244],"emotional":[245],"expressions.":[246],"Extensive":[247],"experiments":[248],"demonstrate":[249],"that":[250],"achieves":[252],"zero-shot":[254],"performance":[255],"TTHD":[257],"competitive":[259],"results":[260],"comparable":[263,287],"real-world":[264],"dataset.":[265],"Notably,":[266],"our":[267],"reduces":[269],"peak":[270],"memory":[271],"usage":[272],"by":[273,279],"35%":[274],"increases":[276],"inference":[277],"speed":[278],"45%":[281],"compared":[282],"temporal-attention":[284],"baselines":[285],"under":[286],"settings,":[288],"while":[289],"delivering":[290],"superior":[291],"coherence":[293],"unidirectional":[295],"state-space":[296],"(SSM)":[298],"approaches.":[299]},"counts_by_year":[],"updated_date":"2026-06-02T06:17:35.589633","created_date":"2026-03-05T00:00:00"}
