{"id":"https://openalex.org/W3211970558","doi":"https://doi.org/10.1145/3474085.3478560","title":"ViDA-MAN","display_name":"ViDA-MAN","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3211970558","doi":"https://doi.org/10.1145/3474085.3478560","mag":"3211970558"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3478560","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3478560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5046486354","display_name":"Tong Shen","orcid":"https://orcid.org/0000-0002-3513-8726"},"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":true,"raw_author_name":"Tong Shen","raw_affiliation_strings":["JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062243850","display_name":"Jiawei Zuo","orcid":null},"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":"Jiawei Zuo","raw_affiliation_strings":["JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057252678","display_name":"Fan Shi","orcid":null},"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":"Fan Shi","raw_affiliation_strings":["JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405951","display_name":"Jin Zhang","orcid":"https://orcid.org/0000-0002-2960-2115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Zhang","raw_affiliation_strings":["Migu Culture Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Migu Culture Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090597931","display_name":"Liqin Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqin Jiang","raw_affiliation_strings":["Migu Culture Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Migu Culture Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357858","display_name":"Meng Chen","orcid":"https://orcid.org/0000-0003-1797-4015"},"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":"Meng Chen","raw_affiliation_strings":["JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057050780","display_name":"Zhengchen Zhang","orcid":"https://orcid.org/0009-0005-4225-3537"},"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":"Zhengchen Zhang","raw_affiliation_strings":["JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research, 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":[{"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":"Wei Zhang","raw_affiliation_strings":["JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727205","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-9463-9168"},"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":"Xiaodong He","raw_affiliation_strings":["JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"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":"Tao Mei","raw_affiliation_strings":["JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5046486354"],"corresponding_institution_ids":["https://openalex.org/I4210103986"],"apc_list":null,"apc_paid":null,"fwci":0.5493,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66519143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973000288009644,"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":0.7752366065979004},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7209824323654175},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7198948860168457},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5793889760971069},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4914814233779907},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4562190771102905},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4444515109062195},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4393998980522156},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.43023431301116943},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28138267993927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2058059573173523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752366065979004},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7209824323654175},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7198948860168457},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5793889760971069},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4914814233779907},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4562190771102905},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4444515109062195},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4393998980522156},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.43023431301116943},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28138267993927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2058059573173523},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3478560","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3478560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2107037917","https://openalex.org/W2237250383","https://openalex.org/W2402146185","https://openalex.org/W2769666294","https://openalex.org/W2811426698","https://openalex.org/W2962974533","https://openalex.org/W2963091184","https://openalex.org/W3161959914","https://openalex.org/W4288242633"],"related_works":["https://openalex.org/W2500779211","https://openalex.org/W48079147","https://openalex.org/W326836678","https://openalex.org/W1963944933","https://openalex.org/W2563921006","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W2735573723","https://openalex.org/W3133893348"],"abstract_inverted_index":{"We":[0],"demonstrate":[1],"ViDA-MAN,":[2],"a":[3,39,93],"digital-human":[4],"agent":[5],"for":[6],"multi-modal":[7,63],"interaction,":[8],"which":[9],"offers":[10,26],"realtime":[11],"audio-visual":[12],"responses":[13],"to":[14,19,46,88],"instant":[15],"speech":[16,40],"inquiries.":[17],"Compared":[18],"traditional":[20],"text":[21],"or":[22],"voice-based":[23],"system,":[24],"ViDA-MAN":[25,60,85],"human-like":[27],"interactions":[28],"(e.g,":[29],"vivid":[30],"voice,":[31],"natural":[32],"facial":[33],"expression":[34],"and":[35],"body":[36],"gestures).":[37],"Given":[38],"request,":[41],"the":[42],"demonstration":[43],"is":[44,86],"able":[45,87],"response":[47],"with":[48,81,90],"high":[49],"quality":[50],"videos":[51],"in":[52],"sub-second":[53],"latency.":[54],"To":[55,73],"deliver":[56],"immersive":[57],"user":[58],"experience,":[59],"seamlessly":[61],"integrates":[62],"techniques":[64],"including":[65,97],"Acoustic":[66],"Speech":[67,74],"Recognition":[68],"(ASR),":[69],"multi-turn":[70],"dialog,":[71],"Text":[72],"(TTS),":[75],"talking":[76],"heads":[77],"video":[78],"generation.":[79],"Backed":[80],"large":[82],"knowledge":[83],"base,":[84],"chat":[89],"users":[91],"on":[92],"number":[94],"of":[95],"topics":[96],"chit-chat,":[98],"weather,":[99],"device":[100],"control,":[101],"News":[102],"recommendations,":[103],"booking":[104],"hotels,":[105],"as":[106,108],"well":[107],"answering":[109],"questions":[110],"via":[111],"structured":[112],"knowledge.":[113]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-11-22T00:00:00"}
