{"id":"https://openalex.org/W4385963935","doi":"https://doi.org/10.1145/3581783.3612831","title":"Learning and Evaluating Human Preferences for Conversational Head Generation","display_name":"Learning and Evaluating Human Preferences for Conversational Head Generation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385963935","doi":"https://doi.org/10.1145/3581783.3612831"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612831","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612831","pdf_url":null,"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":"preprint","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/A5006824435","display_name":"Mohan Zhou","orcid":"https://orcid.org/0000-0003-3250-4978"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mohan Zhou","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054533256","display_name":"Yalong Bai","orcid":"https://orcid.org/0000-0002-8416-9027"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yalong Bai","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441569","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-1492-8286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Gaoding AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Gaoding AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Zhao","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101517779","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0002-5990-7307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5006824435"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.3611,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59500209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9615","last_page":"9619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9970999956130981,"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":0.9952999949455261,"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/generalizability-theory","display_name":"Generalizability theory","score":0.896498441696167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7907677292823792},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6638270616531372},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6549882888793945},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6399274468421936},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6031689643859863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5448855757713318},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.5149367451667786},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4897348880767822},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4361254870891571},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4172629117965698},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4040997624397278},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.11345404386520386},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10135680437088013},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07421520352363586}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.896498441696167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907677292823792},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6638270616531372},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6549882888793945},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6399274468421936},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6031689643859863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5448855757713318},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.5149367451667786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4897348880767822},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4361254870891571},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4172629117965698},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4040997624397278},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.11345404386520386},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10135680437088013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07421520352363586},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612831","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612831","pdf_url":null,"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":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2143331230","https://openalex.org/W2979894294","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3182714435","https://openalex.org/W3186090335","https://openalex.org/W3195529437","https://openalex.org/W4225760288","https://openalex.org/W4281730245","https://openalex.org/W4297899815","https://openalex.org/W4312309978","https://openalex.org/W4312444931","https://openalex.org/W4312578889","https://openalex.org/W4312918802","https://openalex.org/W4312959196","https://openalex.org/W4319301061","https://openalex.org/W4372346571","https://openalex.org/W4386065999","https://openalex.org/W4386071653","https://openalex.org/W4386072463","https://openalex.org/W4386075487","https://openalex.org/W4386076259","https://openalex.org/W6843534333"],"related_works":["https://openalex.org/W2937325523","https://openalex.org/W4205377104","https://openalex.org/W257970033","https://openalex.org/W2911102221","https://openalex.org/W4285602503","https://openalex.org/W4281387587","https://openalex.org/W2943672508","https://openalex.org/W4383737174","https://openalex.org/W4320918405","https://openalex.org/W2591980537"],"abstract_inverted_index":{"A":[0],"reliable":[1],"and":[2,43,52,64,118,122],"comprehensive":[3],"evaluation":[4,39,74,98],"metric":[5,75,140],"that":[6],"aligns":[7],"with":[8,115],"manual":[9],"preference":[10,83],"assessments":[11],"is":[12],"crucial":[13],"for":[14,80,102,132],"conversational":[15,60,146],"head":[16,61,135,147],"video":[17],"synthesis":[18],"methods":[19],"development.":[20],"Existing":[21],"quantitative":[22,87,97],"evaluations":[23,42,88],"often":[24],"fail":[25],"to":[26,85,124],"capture":[27],"the":[28,57,86,100,108],"full":[29],"complexity":[30],"of":[31,59,110],"human":[32,82,103,116],"preference,":[33],"as":[34,95],"they":[35],"only":[36],"consider":[37],"limited":[38],"dimensions.":[40,91],"Qualitative":[41],"user":[44],"studies":[45],"offer":[46],"a":[47,71,96,129],"solution":[48],"but":[49],"are":[50],"time-consuming":[51],"labor-intensive.":[53],"This":[54],"limitation":[55],"hinders":[56],"advancement":[58],"generation":[62],"algorithms":[63],"systems.":[65],"In":[66],"this":[67,139],"paper,":[68],"we":[69],"propose":[70],"novel":[72],"learning-based":[73],"named":[76],"Preference":[77,111],"Score":[78,112],"(PS)":[79],"fitting":[81],"according":[84],"across":[89],"different":[90],"PS":[92],"can":[93],"serve":[94],"without":[99],"need":[101],"annotation.":[104],"Experimental":[105],"results":[106],"validate":[107],"superiority":[109],"in":[113,145],"aligning":[114],"perception,":[117],"also":[119],"demonstrate":[120],"robustness":[121],"generalizability":[123],"unseen":[125],"data,":[126],"making":[127],"it":[128],"valuable":[130],"tool":[131],"advancing":[133],"conversation":[134],"generation.":[136,148],"We":[137],"expect":[138],"could":[141],"facilitate":[142],"new":[143],"advances":[144],"Project":[149],"page:":[150],"https://github.com/dc3ea9f/PreferenceScore.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2023-08-18T00:00:00"}