{"id":"https://openalex.org/W7137920029","doi":"https://doi.org/10.1609/aaai.v40i4.37285","title":"Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","display_name":"Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137920029","doi":"https://doi.org/10.1609/aaai.v40i4.37285"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i4.37285","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37285","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37285/41247","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37285/41247","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129672169","display_name":"Liyang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liyang Chen","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129705580","display_name":"Tianxiang Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tianxiang Ma","raw_affiliation_strings":["Intelligent Creation Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Creation Team, ByteDance","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129681060","display_name":"Jiawei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiawei Liu","raw_affiliation_strings":["Intelligent Creation Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Creation Team, ByteDance","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129752426","display_name":"Bingchuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bingchuan Li","raw_affiliation_strings":["Intelligent Creation Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Creation Team, ByteDance","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101970062","display_name":"Zehao Chen","orcid":"https://orcid.org/0009-0005-3247-8417"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhuowei Chen","raw_affiliation_strings":["Intelligent Creation Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Creation Team, ByteDance","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129736793","display_name":"Lijie Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lijie Liu","raw_affiliation_strings":["Intelligent Creation Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Creation Team, ByteDance","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129723166","display_name":"Xu He","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu He","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129696786","display_name":"Gen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gen Li","raw_affiliation_strings":["Intelligent Creation Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Creation Team, ByteDance","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694545","display_name":"Qian HE","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qian He","raw_affiliation_strings":["Intelligent Creation Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Creation Team, ByteDance","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129750376","display_name":"Zhiyong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5129672169"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14306152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"4","first_page":"2939","last_page":"2947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7919999957084656,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7919999957084656,"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/T11448","display_name":"Face recognition and analysis","score":0.04879999905824661,"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":0.0348999984562397,"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/modalities","display_name":"Modalities","score":0.5831000208854675},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.5462999939918518},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.525600016117096},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4593999981880188},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4189999997615814},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3797999918460846},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3386000096797943},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.31610000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165000081062317},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.5462999939918518},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49230000376701355},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4065999984741211},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2549000084400177},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25189998745918274},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i4.37285","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37285","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37285/41247","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37285","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37285","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37285/41247","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","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/W7137920029.pdf","grobid_xml":"https://content.openalex.org/works/W7137920029.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human-Centric":[0],"Video":[1],"Generation":[2],"(HCVG)":[3],"methods":[4,19,190],"seek":[5],"to":[6,21,28,100,118,132],"synthesize":[7],"human":[8],"videos":[9],"from":[10],"multimodal":[11,59,87,164],"inputs,":[12,145],"including":[13],"text,":[14],"images,":[15],"and":[16,36,75,104,162],"audio.":[17],"Existing":[18],"struggle":[20],"effectively":[22],"coordinate":[23],"these":[24],"heterogeneous":[25],"modalities":[26],"due":[27],"two":[29],"challenges:":[30],"the":[31,37,62,79,97,102,109,115,130,149],"scarcity":[32],"of":[33,39,141],"modality-complete":[34],"data":[35,72],"difficulty":[38],"jointly":[40],"modeling":[41],"triplet":[42],"conditions":[43],"without":[44],"performance":[45],"degradation.":[46],"In":[47,96,114],"this":[48],"work,":[49],"we":[50,65,82,107,122,146,166],"present":[51],"HuMo,":[52],"a":[53,84,124,168,194],"unified":[54,195],"HCVG":[55],"framework":[56,196],"for":[57,70,160,197],"collaborative":[58,198],"control.":[60],"For":[61,78,138],"first":[63,98],"challenge,":[64,81],"construct":[66],"an":[67],"incomplete-yet-complementary":[68],"dataset":[69],"improved":[71],"utilization":[73],"efficiency":[74],"training":[76,88],"scalability.":[77],"second":[80,116],"propose":[83,123],"two-stage":[85],"progressive":[86],"paradigm":[89],"with":[90,135],"task-specific":[91],"strategies":[92],"at":[93],"each":[94],"stage.":[95],"stage,":[99,117],"balance":[101],"text-following":[103],"subject-preservation":[105],"abilities,":[106],"adopt":[108],"minimal-invasive":[110],"image":[111],"injection":[112],"strategy.":[113],"enhance":[119],"audio-visual":[120,150],"sync,":[121],"focus-by-predicting":[125],"strategy":[126,172],"that":[127,173,185],"implicitly":[128],"guides":[129],"model":[131],"associate":[133],"audio":[134],"facial":[136],"regions.":[137],"joint":[139],"learning":[140],"controllabilities":[142],"across":[143,178],"multi-modal":[144],"progressively":[147],"incorporate":[148],"sync":[151],"task,":[152],"building":[153],"on":[154],"previously":[155],"acquired":[156],"capabilities.":[157],"During":[158],"inference,":[159],"flexible":[161],"fine-grained":[163],"control,":[165],"design":[167],"stage-adaptive":[169],"Classifier-Free":[170],"Guidance":[171],"dynamically":[174],"adjusts":[175],"guidance":[176],"weights":[177],"denoising":[179],"steps.":[180],"Extensive":[181],"experimental":[182],"results":[183],"demonstrate":[184],"HuMo":[186],"surpasses":[187],"specialized":[188],"state-of-the-art":[189],"in":[191],"sub-tasks,":[192],"establishing":[193],"multimodal-conditioned":[199],"HCVG.":[200]},"counts_by_year":[],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2026-03-18T00:00:00"}