{"id":"https://openalex.org/W4308234034","doi":"https://doi.org/10.1109/icip46576.2022.9897657","title":"Ventriloquist-Net: Leveraging Speech Cues for Emotive Talking Head Generation","display_name":"Ventriloquist-Net: Leveraging Speech Cues for Emotive Talking Head Generation","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308234034","doi":"https://doi.org/10.1109/icip46576.2022.9897657"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897657","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5089494843","display_name":"Deepan Das","orcid":"https://orcid.org/0000-0001-8910-5973"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Deepan Das","raw_affiliation_strings":["Technical University of Munich,Computer Vision and Artificial Intelligence,Department of Informatics,Garching,Germany","Department of Informatics, Computer Vision and Artificial Intelligence, Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Computer Vision and Artificial Intelligence,Department of Informatics,Garching,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Informatics, Computer Vision and Artificial Intelligence, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029411186","display_name":"Qadeer Khan","orcid":"https://orcid.org/0000-0001-9600-9031"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Qadeer Khan","raw_affiliation_strings":["Technical University of Munich,Computer Vision and Artificial Intelligence,Department of Informatics,Garching,Germany","Department of Informatics, Computer Vision and Artificial Intelligence, Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Computer Vision and Artificial Intelligence,Department of Informatics,Garching,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Informatics, Computer Vision and Artificial Intelligence, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087710605","display_name":"Daniel Cremers","orcid":"https://orcid.org/0000-0002-3079-7984"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Cremers","raw_affiliation_strings":["Technical University of Munich,Computer Vision and Artificial Intelligence,Department of Informatics,Garching,Germany","Department of Informatics, Computer Vision and Artificial Intelligence, Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Computer Vision and Artificial Intelligence,Department of Informatics,Garching,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Informatics, Computer Vision and Artificial Intelligence, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089494843"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10430629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":null,"first_page":"1716","last_page":"1720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991000294685364,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940999746322632,"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/emotive","display_name":"Emotive","score":0.9604955911636353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8510892391204834},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5826696157455444},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5796355605125427},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.534307599067688},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49803733825683594},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.47289955615997314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46302738785743713},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.44117921590805054},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11114034056663513}],"concepts":[{"id":"https://openalex.org/C2776215170","wikidata":"https://www.wikidata.org/wiki/Q5373820","display_name":"Emotive","level":2,"score":0.9604955911636353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510892391204834},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5826696157455444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5796355605125427},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.534307599067688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49803733825683594},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.47289955615997314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46302738785743713},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.44117921590805054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11114034056663513},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897657","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1569907127","https://openalex.org/W1800809792","https://openalex.org/W2030931454","https://openalex.org/W2091084672","https://openalex.org/W2289286917","https://openalex.org/W2604379605","https://openalex.org/W2738406145","https://openalex.org/W2803193013","https://openalex.org/W2808631503","https://openalex.org/W2944294033","https://openalex.org/W2949662773","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2964559396","https://openalex.org/W2979894294","https://openalex.org/W3019952993","https://openalex.org/W3023706973","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3095664976","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3101631197","https://openalex.org/W3104792420","https://openalex.org/W3109114891","https://openalex.org/W3180770160","https://openalex.org/W3186090335","https://openalex.org/W3192148059","https://openalex.org/W6638349531","https://openalex.org/W6737896281","https://openalex.org/W6765657114","https://openalex.org/W6776963518"],"related_works":["https://openalex.org/W3004257401","https://openalex.org/W603725405","https://openalex.org/W2263121790","https://openalex.org/W4248663371","https://openalex.org/W2137460703","https://openalex.org/W3167630016","https://openalex.org/W1966281075","https://openalex.org/W2978897034","https://openalex.org/W2786096260","https://openalex.org/W2385515133"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"Ventriloquist-Net:":[5],"A":[6],"Talking":[7],"Head":[8],"Generation":[9],"model":[10],"that":[11],"uses":[12],"only":[13,57],"a":[14,18,63],"speech":[15,39],"segment":[16],"and":[17,74,89],"single":[19],"source":[20,71],"face":[21],"image.":[22],"It":[23],"places":[24],"emphasis":[25],"on":[26,77,84],"emotive":[27],"expressions.":[28],"Cues":[29],"for":[30],"generating":[31],"these":[32],"expressions":[33],"are":[34,92],"implicitly":[35],"inferred":[36],"from":[37],"the":[38],"clip":[40],"only.":[41],"We":[42],"formulate":[43],"our":[44],"framework":[45],"to":[46,52,60],"comprise":[47],"of":[48],"independently":[49],"trained":[50],"modules":[51],"expedite":[53],"convergence.":[54],"This":[55],"not":[56],"allows":[58],"extension":[59],"datasets":[61],"in":[62],"semi-supervised":[64],"manner":[65],"but":[66],"also":[67],"facilitates":[68],"handling":[69],"in-the-wild":[70],"images.":[72],"Quantitative":[73],"qualitative":[75],"evaluations":[76],"generated":[78],"videos":[79,91],"demonstrate":[80],"state-of-the-art":[81],"performance":[82],"even":[83],"unseen":[85],"input":[86],"data.":[87],"Implementation":[88],"supplementary":[90],"available":[93],"at":[94],"https://github.com/dipnds/VentriloquistNet.":[95]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
