{"id":"https://openalex.org/W4387967994","doi":"https://doi.org/10.1145/3581783.3612869","title":"Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline","display_name":"Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967994","doi":"https://doi.org/10.1145/3581783.3612869"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612869","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612869","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612869","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018959868","display_name":"Zhigang Chang","orcid":"https://orcid.org/0000-0002-8565-3857"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Chang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8565-3857","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015548355","display_name":"Weitai Hu","orcid":"https://orcid.org/0009-0001-4399-2973"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weitai Hu","raw_affiliation_strings":["Du Xiaoman Financial, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-4399-2973","affiliations":[{"raw_affiliation_string":"Du Xiaoman Financial, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072334342","display_name":"Qing Yang","orcid":"https://orcid.org/0000-0002-0833-8204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Yang","raw_affiliation_strings":["Du Xiaoman Financial, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0833-8204","affiliations":[{"raw_affiliation_string":"Du Xiaoman Financial, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100775128","display_name":"Shibao Zheng","orcid":"https://orcid.org/0000-0002-5060-0210"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibao Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5060-0210","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9581","last_page":"9585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9987999796867371,"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":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.8367424011230469},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6439666748046875},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5638128519058228},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5564638376235962},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5304524302482605},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5302462577819824},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.44279390573501587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4270254373550415},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4121236801147461},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36739951372146606},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35440972447395325},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09166890382766724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367424011230469},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6439666748046875},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5638128519058228},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5564638376235962},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5304524302482605},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5302462577819824},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.44279390573501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4270254373550415},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4121236801147461},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36739951372146606},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35440972447395325},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09166890382766724},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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:10.1145/3581783.3612869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612869","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612869","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612869","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612869","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6201002723","display_name":null,"funder_award_id":"U21B2013","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387967994.pdf","grobid_xml":"https://content.openalex.org/works/W4387967994.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2107037917","https://openalex.org/W2237250383","https://openalex.org/W2752782242","https://openalex.org/W2962795401","https://openalex.org/W3081492798","https://openalex.org/W3099284785","https://openalex.org/W3101631197","https://openalex.org/W3104300620","https://openalex.org/W3154807520","https://openalex.org/W3193766423","https://openalex.org/W3204680331","https://openalex.org/W4200635747","https://openalex.org/W4225760288","https://openalex.org/W4281668669","https://openalex.org/W4312309978","https://openalex.org/W4312345918","https://openalex.org/W4312674262","https://openalex.org/W4372346571"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218"],"abstract_inverted_index":{"In":[0],"dyadic":[1],"speaker-listener":[2],"interactions,":[3],"the":[4,10,28,37,43,47,56,60,67,78,84,90,100,104,108,127],"listener's":[5,30],"head":[6,12,31,112],"reactions,":[7],"together":[8],"with":[9],"speaker's":[11,61],"movements,":[13],"form":[14],"an":[15],"important":[16],"non-verbal":[17],"semantic":[18,80],"expression.":[19],"The":[20],"listener":[21],"Head":[22,123],"generation":[23],"task":[24],"aims":[25],"to":[26,46,54],"synthesize":[27],"responsive":[29],"videos":[32],"based":[33],"on":[34,103],"audios":[35],"of":[36,42,83,110,120],"speaker":[38],"and":[39,63,88,94],"reference":[40],"images":[41],"listener.":[44],"Compared":[45],"talking-head":[48],"generation,":[49],"it":[50],"is":[51,116],"more":[52],"challenging":[53],"capture":[55],"correlation":[57],"cues":[58],"from":[59],"audio":[62,85],"visual":[64],"information.":[65],"Following":[66],"ViCo":[68],"baseline":[69],"scheme,":[70],"we":[71],"propose":[72],"a":[73,117],"high-performance":[74],"solution":[75,98],"by":[76],"enhancing":[77],"hierarchical":[79],"extraction":[81],"capability":[82],"encoder":[86],"module":[87],"improving":[89],"decoder":[91],"part,":[92],"renderer":[93],"post-processing":[95],"modules.":[96],"Our":[97],"gets":[99],"first":[101],"place":[102],"official":[105],"leaderboard":[106],"for":[107],"track":[109],"listening":[111],"generation.":[113],"This":[114],"paper":[115],"technical":[118],"report":[119],"ViCo@2023":[121],"Conversational":[122],"Generation":[124],"Challenge":[125],"at":[126],"ACM":[128],"Multimedia":[129],"2023":[130],"conference.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
