{"id":"https://openalex.org/W4402915563","doi":"https://doi.org/10.1109/icip51287.2024.10647543","title":"A Comparative Study of Perceptual Quality Metrics For Audio-Driven Talking Head Videos","display_name":"A Comparative Study of Perceptual Quality Metrics For Audio-Driven Talking Head Videos","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915563","doi":"https://doi.org/10.1109/icip51287.2024.10647543"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070942166","display_name":"Weixia Zhang","orcid":"https://orcid.org/0000-0002-5835-2020"},"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":"Weixia Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044069276","display_name":"Chengguang Zhu","orcid":"https://orcid.org/0000-0002-7737-4225"},"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":"Chengguang Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113204824","display_name":"Jingnan Gao","orcid":null},"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":"Jingnan Gao","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048907728","display_name":"Yichao Yan","orcid":"https://orcid.org/0000-0003-3209-8965"},"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":"Yichao Yan","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"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":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaokang Yang","orcid":null},"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":"Xiaokang Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1218","last_page":"1224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9477999806404114,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9477999806404114,"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":0.9390000104904175,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9265999794006348,"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":0.7640586495399475},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.7040581703186035},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5915612578392029},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5340862274169922},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43689581751823425},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3820525109767914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.358337938785553},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1155448853969574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640586495399475},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7040581703186035},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5915612578392029},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5340862274169922},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43689581751823425},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3820525109767914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.358337938785553},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1155448853969574},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/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/icip51287.2024.10647543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2134963900","https://openalex.org/W2604379605","https://openalex.org/W2738406145","https://openalex.org/W2905544033","https://openalex.org/W2914217321","https://openalex.org/W2962785568","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2990730805","https://openalex.org/W3017136408","https://openalex.org/W3023338037","https://openalex.org/W3030380536","https://openalex.org/W3081492798","https://openalex.org/W3090101394","https://openalex.org/W3105164497","https://openalex.org/W3135955502","https://openalex.org/W3193919962","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4214745154","https://openalex.org/W4312818079","https://openalex.org/W4319770604","https://openalex.org/W4386076169","https://openalex.org/W6811548253","https://openalex.org/W6845298728","https://openalex.org/W6847000881","https://openalex.org/W6948150082"],"related_works":["https://openalex.org/W3097502728","https://openalex.org/W2628861693","https://openalex.org/W2113206756","https://openalex.org/W3203087560","https://openalex.org/W4361279463","https://openalex.org/W3009949491","https://openalex.org/W1927475415","https://openalex.org/W105296515","https://openalex.org/W2613352840","https://openalex.org/W4232814730"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,31],"Artificial":[4],"Intelligence":[5],"Generated":[6],"Content":[7],"(AIGC)":[8],"technology":[9],"has":[10],"propelled":[11],"audio-driven":[12],"talking":[13,32,56],"head":[14,33,57,75],"generation,":[15],"gaining":[16],"considerable":[17],"research":[18,26],"attention":[19],"for":[20],"practical":[21],"applications.":[22],"However,":[23],"performance":[24,105],"evaluation":[25,106],"lags":[27],"behind":[28],"the":[29],"development":[30],"generation":[34],"techniques.":[35],"Existing":[36],"literature":[37],"relies":[38],"on":[39,69],"heuristic":[40],"quantitative":[41],"metrics":[42,89],"without":[43],"human":[44,86,94],"validation,":[45],"hindering":[46],"accurate":[47],"progress":[48],"assessment.":[49],"To":[50],"address":[51],"this":[52],"gap,":[53],"we":[54],"collect":[55],"videos":[58],"generated":[59],"from":[60],"four":[61],"generative":[62],"methods":[63],"and":[64,74,85,107],"conduct":[65],"controlled":[66],"psychophysical":[67],"experiments":[68,79],"visual":[70],"quality,":[71],"lip-audio":[72],"synchronization,":[73],"movement":[76],"naturalness.":[77],"Our":[78],"validate":[80],"consistency":[81],"between":[82],"model":[83,108],"predictions":[84],"annotations,":[87],"identifying":[88],"that":[90],"align":[91],"better":[92],"with":[93],"opinions":[95],"than":[96],"widely-used":[97],"measures.":[98],"We":[99],"believe":[100],"our":[101],"work":[102],"will":[103],"facilitate":[104],"development,":[109],"providing":[110],"insights":[111],"into":[112],"AIGC":[113],"in":[114],"a":[115],"broader":[116],"context.":[117],"Code":[118],"is":[119],"available":[120],"at":[121],"https://github.com/zwx8981/ADTH-QA.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}