{"id":"https://openalex.org/W4392910795","doi":"https://doi.org/10.1109/icassp48485.2024.10446837","title":"Adaptive Super Resolution for One-Shot Talking-Head Generation","display_name":"Adaptive Super Resolution for One-Shot Talking-Head Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910795","doi":"https://doi.org/10.1109/icassp48485.2024.10446837"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5024413169","display_name":"Luchuan Song","orcid":"https://orcid.org/0000-0002-0126-1259"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luchuan Song","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079498468","display_name":"Pinxin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pinxin Liu","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033440540","display_name":"Guojun Yin","orcid":"https://orcid.org/0000-0001-8260-5449"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojun Yin","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064805926","display_name":"Chenliang Xu","orcid":"https://orcid.org/0000-0002-2183-822X"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenliang Xu","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5826,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90230001,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4115","last_page":"4119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11408","display_name":"Advanced Optical Imaging Technologies","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9878000020980835,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6685620546340942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6340267658233643},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5611433982849121},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.42279529571533203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3501136302947998},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3495522439479828},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10712620615959167},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0890393853187561}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6685620546340942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6340267658233643},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5611433982849121},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.42279529571533203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3501136302947998},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3495522439479828},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10712620615959167},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0890393853187561},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1860567963","display_name":null,"funder_award_id":"1909912","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7760877873","display_name":null,"funder_award_id":"HR00112220003","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2952773607","https://openalex.org/W2962770929","https://openalex.org/W2962974533","https://openalex.org/W2963644257","https://openalex.org/W3008823916","https://openalex.org/W3128081663","https://openalex.org/W3180770160","https://openalex.org/W3193882757","https://openalex.org/W3197199219","https://openalex.org/W3204087723","https://openalex.org/W3204971388","https://openalex.org/W3205994442","https://openalex.org/W4210657261","https://openalex.org/W4288088427","https://openalex.org/W4310379947","https://openalex.org/W4312473638","https://openalex.org/W4312722235","https://openalex.org/W4386066083","https://openalex.org/W4386072021","https://openalex.org/W4390872713","https://openalex.org/W6767264202"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0,42,157],"one-shot":[1,118],"talking-head":[2,8,97],"generation":[3,99],"learns":[4],"to":[5,64],"synthesize":[6],"a":[7,46,146],"video":[9,98,104,134,161],"with":[10],"one":[11],"source":[12,49,119],"portrait":[13],"image":[14,36,48],"under":[15],"the":[16,55,58,66,85,117,140],"driving":[17],"of":[18,44,57,68,142],"same":[19],"or":[20,34],"different":[21],"identity":[22],"video.":[23],"Usually":[24],"these":[25],"methods":[26,62],"require":[27],"plane-based":[28],"pixel":[29,51],"transformations":[30],"via":[31,127],"Jacobin":[32],"matrices":[33],"facial":[35],"warps":[37],"for":[38],"novel":[39],"poses":[40],"generation.":[41],"constraints":[43],"using":[45],"single":[47],"and":[50,83,121,154,159],"displacements":[52],"often":[53],"compromise":[54],"clarity":[56],"synthesized":[59,69],"images.":[60],"Some":[61],"try":[63],"improve":[65],"quality":[67,141],"videos":[70,144],"by":[71,111,152],"introducing":[72],"additional":[73,106],"super-resolution":[74,113],"modules,":[75],"but":[76],"this":[77,90],"will":[78],"undoubtedly":[79],"increase":[80],"computational":[81],"consumption":[82],"destroy":[84],"original":[86],"data":[87],"distribution.":[88],"In":[89],"work,":[91],"we":[92,115],"propose":[93],"an":[94,128],"adaptive":[95],"high-quality":[96],"method,":[100],"which":[101],"synthesizes":[102],"high-resolution":[103],"without":[105],"pre-trained":[107],"modules.":[108],"Specifically,":[109],"inspired":[110],"existing":[112],"methods,":[114],"down-sample":[116],"image,":[120],"then":[122],"adaptively":[123],"reconstruct":[124],"high-frequency":[125],"details":[126],"encoder-decoder":[129],"module,":[130],"resulting":[131],"in":[132],"enhanced":[133],"clarity.":[135],"Our":[136],"method":[137],"consistently":[138],"improves":[139],"generated":[143],"through":[145],"straightforward":[147],"yet":[148],"effective":[149],"strategy,":[150],"substantiated":[151],"quantitative":[153],"qualitative":[155],"evaluations.":[156],"code":[158],"demo":[160],"are":[162],"available":[163],"on:":[164],"https://github.com/Songluchuan/AdaSR-TalkingHead/.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
