{"id":"https://openalex.org/W7131242895","doi":"https://doi.org/10.1109/vcip67698.2025.11396818","title":"Ges-QA: A Multidimensional Quality Assessment Dataset for Audio-to-3D Gesture Generation","display_name":"Ges-QA: A Multidimensional Quality Assessment Dataset for Audio-to-3D Gesture Generation","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7131242895","doi":"https://doi.org/10.1109/vcip67698.2025.11396818"},"language":null,"primary_location":{"id":"doi:10.1109/vcip67698.2025.11396818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","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/A5126666568","display_name":"Zhilin 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":"Zhilin Gao","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070920267","display_name":"Yunhao Li","orcid":"https://orcid.org/0000-0002-5359-2930"},"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":"Yunhao Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019148813","display_name":"Sijing Wu","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":"Sijing Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101983011","display_name":"Yuqin Cao","orcid":"https://orcid.org/0000-0002-5087-6559"},"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":"Yuqin Cao","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126679174","display_name":"Huiyu Duan","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":"Huiyu Duan","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126740280","display_name":"Guangtao Zhai","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":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.5828999876976013,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.5828999876976013,"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":0.13660000264644623,"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/T11309","display_name":"Music and Audio Processing","score":0.10329999774694443,"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/gesture","display_name":"Gesture","score":0.8500999808311462},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.5418000221252441},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4966999888420105},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4413999915122986},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.43540000915527344},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.39239999651908875},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38499999046325684},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.36719998717308044}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8500999808311462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516000270843506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5812000036239624},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.5418000221252441},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.3296999931335449},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32330000400543213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3012000024318695},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27379998564720154}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip67698.2025.11396818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2978956737","https://openalex.org/W3153832461","https://openalex.org/W3175300676","https://openalex.org/W3196208130","https://openalex.org/W3196974791","https://openalex.org/W3206996142","https://openalex.org/W4221142137","https://openalex.org/W4312560592","https://openalex.org/W4327662052","https://openalex.org/W4372304597","https://openalex.org/W4383750585","https://openalex.org/W4386066305","https://openalex.org/W4386071707","https://openalex.org/W4386075984","https://openalex.org/W4386590515","https://openalex.org/W4386597151","https://openalex.org/W4392903179","https://openalex.org/W4402703119","https://openalex.org/W4402704505","https://openalex.org/W4402727140","https://openalex.org/W4402753998","https://openalex.org/W4403511263","https://openalex.org/W4403780616","https://openalex.org/W4403792047","https://openalex.org/W4407250330","https://openalex.org/W4409346387","https://openalex.org/W4413156691","https://openalex.org/W4415025762","https://openalex.org/W4415366882","https://openalex.org/W4415541184","https://openalex.org/W4415541207","https://openalex.org/W4416965721"],"related_works":[],"abstract_inverted_index":{"The":[0],"Audio-to-3D-Gesture":[1],"(A2G)":[2],"task":[3],"exhibits":[4],"significant":[5],"potential":[6],"across":[7],"domains":[8],"including":[9],"virtual":[10],"reality,":[11],"computer":[12],"graphics,":[13],"and":[14,49,82,121,136],"3D":[15,39,57,122],"animation":[16],"production.":[17],"However,":[18],"current":[19],"evaluation":[20],"metrics,":[21],"such":[22],"as":[23],"Fr\u00e9chet":[24],"Gesture":[25],"Distance":[26],"or":[27],"Beat":[28],"Constancy,":[29],"fail":[30],"at":[31],"reflecting":[32],"the":[33,37,69,94,98,101],"human":[34,47,58],"preference":[35,48],"of":[36,100],"generated":[38,95],"gestures.":[40],"To":[41],"cope":[42],"with":[43,76,104,115],"this":[44,65],"problem,":[45],"exploring":[46],"an":[50],"objective":[51],"quality":[52,81],"assessment":[53],"metric":[54],"for":[55,79,118],"AI-generated":[56],"gestures":[59,96],"is":[60],"becoming":[61],"increasingly":[62],"significant.":[63],"In":[64],"paper,":[66],"we":[67,86,108],"introduce":[68],"Ges-QA":[70,106],"dataset,":[71,107],"which":[72,125],"includes":[73],"1,400":[74],"samples":[75],"multidimensional":[77],"scores":[78],"gesture":[80],"audio-gesture":[83],"consistency.":[84],"Moreover,":[85],"collect":[87],"binary":[88],"classification":[89],"labels":[90],"to":[91],"determine":[92],"whether":[93],"match":[97],"emotions":[99],"audio.":[102],"Equipped":[103],"our":[105,146],"propose":[109],"a":[110],"multi-modal":[111],"transformer-based":[112],"neural":[113],"network":[114],"3":[116],"branches":[117],"video,":[119],"audio":[120],"skeleton":[123],"modalities,":[124],"can":[126],"score":[127],"A2G":[128],"contents":[129],"in":[130],"multiple":[131],"dimensions.":[132],"Comparative":[133],"experimental":[134],"results":[135],"ablation":[137],"studies":[138],"demonstrate":[139],"that":[140],"Ges-QAer":[141],"yields":[142],"state-of-the-art":[143],"performance":[144],"on":[145],"dataset.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-25T00:00:00"}