{"id":"https://openalex.org/W4283710679","doi":"https://doi.org/10.1145/3503161.3551577","title":"Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer","display_name":"Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4283710679","doi":"https://doi.org/10.1145/3503161.3551577"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3551577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551577","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.12837","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113172615","display_name":"Ailin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ailin Huang","raw_affiliation_strings":["Megvii Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megvii Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110801831","display_name":"Zhewei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhewei Huang","raw_affiliation_strings":["Megvii Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megvii Research, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008993224","display_name":"Shuchang Zhou","orcid":"https://orcid.org/0000-0002-7294-5869"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuchang Zhou","raw_affiliation_strings":["Megvii Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megvii Research, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.832,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81969792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7050","last_page":"7054"},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9975000023841858,"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":0.9889000058174133,"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/computer-science","display_name":"Computer science","score":0.8435107469558716},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6128041744232178},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.563209056854248},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.47675737738609314},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4695870280265808},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.45918363332748413},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45064741373062134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4434796869754791},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38478007912635803},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08328396081924438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8435107469558716},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6128041744232178},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.563209056854248},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.47675737738609314},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4695870280265808},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.45918363332748413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45064741373062134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4434796869754791},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38478007912635803},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08328396081924438},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3551577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551577","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.12837","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.12837","pdf_url":"https://arxiv.org/pdf/2206.12837","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.12837","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.12837","pdf_url":"https://arxiv.org/pdf/2206.12837","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2025768430","https://openalex.org/W2194775991","https://openalex.org/W2738406145","https://openalex.org/W2914217321","https://openalex.org/W2944294033","https://openalex.org/W2962770929","https://openalex.org/W2963290645","https://openalex.org/W2963372104","https://openalex.org/W2964449965","https://openalex.org/W3014859719","https://openalex.org/W3025800305","https://openalex.org/W3097792222","https://openalex.org/W3107666850","https://openalex.org/W3109908659","https://openalex.org/W3167976421","https://openalex.org/W3204680331","https://openalex.org/W3211147706"],"related_works":["https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W2772323916","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2281307425","https://openalex.org/W2464405057"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"our":[3,58],"solution":[4,29],"for":[5],"ACM":[6],"Multimedia":[7],"ViCo":[8],"2022":[9],"Conversational":[10],"Head":[11],"Generation":[12],"Challenge,":[13],"which":[14],"aims":[15],"to":[16],"generate":[17],"vivid":[18],"face-to-face":[19],"conversation":[20],"videos":[21],"based":[22],"on":[23,31],"audio":[24],"and":[25,39,52,72],"reference":[26],"images.":[27],"Our":[28,85],"focuses":[30],"training":[32],"a":[33,41],"generalized":[34],"audio-to-head":[35],"driver":[36],"using":[37,57],"regularization":[38],"assembling":[40],"high":[42],"visual":[43],"quality":[44],"renderer.":[45],"We":[46,62],"carefully":[47],"tweak":[48],"the":[49,54,67,76,82],"audio-to-behavior":[50],"model":[51],"post-process":[53],"generated":[55],"video":[56],"foreground-background":[59],"fusion":[60],"module.":[61],"get":[63],"first":[64],"place":[65,74],"in":[66,75,81],"listening":[68],"head":[69,78],"generation":[70,79],"track":[71,80],"second":[73],"talking":[77],"official":[83],"leaderboard.":[84],"code":[86],"is":[87],"available":[88],"at":[89],"https://github.com/megvii-research/MM2022-ViCoPerceptualHeadGeneration.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2022-06-30T00:00:00"}