{"id":"https://openalex.org/W4417113899","doi":"https://doi.org/10.1145/3769748.3773364","title":"Detection-Aware Inference for Robust Talking-Head Video Generation","display_name":"Detection-Aware Inference for Robust Talking-Head Video Generation","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417113899","doi":"https://doi.org/10.1145/3769748.3773364"},"language":null,"primary_location":{"id":"doi:10.1145/3769748.3773364","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769748.3773364","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769748.3773364","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3769748.3773364","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120721013","display_name":"Seyyedhamid Azimidokht","orcid":"https://orcid.org/0009-0006-1503-8652"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Seyyedhamid Azimidokht","raw_affiliation_strings":["CMVS, University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0009-0006-1503-8652","affiliations":[{"raw_affiliation_string":"CMVS, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080498990","display_name":"Fang Kang","orcid":"https://orcid.org/0009-0004-3810-0717"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Fang Kang","raw_affiliation_strings":["CMVS, University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0009-0004-3810-0717","affiliations":[{"raw_affiliation_string":"CMVS, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yueyi Yang","orcid":"https://orcid.org/0000-0002-4948-1058"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yueyi Yang","raw_affiliation_strings":["CMVS, University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-4948-1058","affiliations":[{"raw_affiliation_string":"CMVS, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100763975","display_name":"Haoyu Chen","orcid":"https://orcid.org/0000-0003-3267-2664"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Haoyu Chen","raw_affiliation_strings":["CMVS, University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0003-3267-2664","affiliations":[{"raw_affiliation_string":"CMVS, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120721013"],"corresponding_institution_ids":["https://openalex.org/I98381234"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38209861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7766000032424927,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7766000032424927,"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/T11448","display_name":"Face recognition and analysis","score":0.1753000020980835,"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":0.006399999838322401,"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/robustness","display_name":"Robustness (evolution)","score":0.7494999766349792},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6733999848365784},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49410000443458557},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3107999861240387},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3095000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7911999821662903},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7494999766349792},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6733999848365784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.605400025844574},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2992829110","wikidata":"https://www.wikidata.org/wiki/Q3921615","display_name":"First generation","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769748.3773364","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769748.3773364","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769748.3773364","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3769748.3773364","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769748.3773364","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769748.3773364","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7353025116","display_name":null,"funder_award_id":"352788","funder_id":"https://openalex.org/F4320323692","funder_display_name":"Oulun Yliopisto"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320323692","display_name":"Oulun Yliopisto","ror":"https://ror.org/03yj89h83"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417113899.pdf","grobid_xml":"https://content.openalex.org/works/W4417113899.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2944294033","https://openalex.org/W3081492798","https://openalex.org/W4225922995","https://openalex.org/W4321101505","https://openalex.org/W4386072021","https://openalex.org/W4402727795","https://openalex.org/W4410393390","https://openalex.org/W4411245043","https://openalex.org/W4415432858"],"related_works":[],"abstract_inverted_index":{"Talking-head":[0],"video":[1],"generation":[2,115,135],"has":[3],"seen":[4],"significant":[5],"progress":[6],"with":[7,25],"the":[8,33,44,59,114],"rise":[9],"of":[10,116],"multimodal":[11,140],"and":[12,72,87,99,132,142],"multiethnic":[13],"datasets;":[14],"however,":[15],"existing":[16],"systems":[17],"still":[18],"suffer":[19],"from":[20],"stability":[21],"issues":[22],"when":[23,103],"dealing":[24],"occluded":[26,83],"or":[27,84],"partially":[28],"missing":[29],"facial":[30,79,104],"regions":[31,80],"in":[32,128],"input.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"present":[39],"our":[40,62],"model":[41,63],"developed":[42],"for":[43,138],"ACM":[45],"Multimedia":[46],"Asia":[47],"2025":[48],"Grand":[49],"Challenge":[50],"on":[51],"Multimodal":[52],"Multiethnic":[53],"Talking-Head":[54],"Video":[55],"Generation.":[56],"Built":[57],"upon":[58],"Hallo2":[60],"framework,":[61],"introduces":[64],"two":[65],"key":[66],"improvements":[67],"to":[68],"enhance":[69],"inference":[70,97],"robustness":[71],"usability.":[73],"First,":[74],"it":[75,109],"detects":[76],"cases":[77],"where":[78],"are":[81],"heavily":[82],"incompletely":[85],"detected":[86],"automatically":[88],"substitutes":[89],"a":[90,121,129],"static":[91],"image":[92],"across":[93],"all":[94],"frames,":[95],"preventing":[96],"failures":[98],"maintaining":[100],"visual":[101],"consistency":[102],"information":[105],"is":[106],"insufficient.":[107],"Second,":[108],"supports":[110],"multi-input":[111],"inference,":[112],"enabling":[113],"multiple":[117],"talking-head":[118,134],"videos":[119],"within":[120],"single":[122],"execution":[123],"process.":[124],"These":[125],"modifications":[126],"result":[127],"more":[130],"reliable":[131],"flexible":[133],"pipeline,":[136],"suitable":[137],"diverse":[139],"datasets":[141],"large-scale":[143],"evaluation.":[144]},"counts_by_year":[],"updated_date":"2026-03-10T14:07:55.174380","created_date":"2025-12-08T00:00:00"}
