{"id":"https://openalex.org/W7137987599","doi":"https://doi.org/10.1609/aaai.v40i10.37758","title":"FantasyHSI: Video-Generation-Centric 4D Human Synthesis in Any Scene Through a Graph-Based Multi-Agent Framework","display_name":"FantasyHSI: Video-Generation-Centric 4D Human Synthesis in Any Scene Through a Graph-Based Multi-Agent Framework","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137987599","doi":"https://doi.org/10.1609/aaai.v40i10.37758"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i10.37758","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37758","pdf_url":null,"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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i10.37758","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129645859","display_name":"Lingzhou Mu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingzhou Mu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730895","display_name":"Wang Qiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697254","display_name":"Fan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695140","display_name":"Mengchao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengchao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129717408","display_name":"Mu Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mu Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129643647","display_name":"Kai Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"8116","last_page":"8124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.7465999722480774,"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":0.7465999722480774,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.07190000265836716,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06080000102519989,"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/leverage","display_name":"Leverage (statistics)","score":0.7315999865531921},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.491100013256073},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4787999987602234},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.47749999165534973},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4674000144004822},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.4514000117778778},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43639999628067017},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4185999929904938},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.413100004196167}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7315999865531921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7276999950408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5968999862670898},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.4514000117778778},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42579999566078186},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39739999175071716},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3384999930858612},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.3312000036239624},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i10.37758","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37758","pdf_url":null,"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"},{"id":"pmh:oai:ojs.aaai.org:article/37758","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37758","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37758","pdf_url":null,"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human-Scene":[0],"Interaction":[1],"(HSI)":[2],"seeks":[3],"to":[4,24,154],"generate":[5],"realistic":[6],"human":[7],"behaviors":[8],"within":[9],"complex":[10,53],"environments,":[11],"yet":[12],"it":[13],"faces":[14],"significant":[15],"challenges":[16],"in":[17,182],"handling":[18],"long-horizon,":[19],"high-level":[20,80],"tasks":[21],"and":[22,42,79,83,113,166,189],"generalizing":[23],"unseen":[25],"scenes.":[26],"To":[27,139],"address":[28],"these":[29],"limitations,":[30],"we":[31,63,95,148],"introduce":[32,96],"FantasyHSI,":[33],"a":[34,57,65,72,84,97,102],"novel":[35],"HSI":[36],"framework":[37],"centered":[38],"on":[39,170],"video":[40],"generation":[41],"multi-agent":[43,67],"systems":[44],"that":[45,87,100,176],"operates":[46],"without":[47],"paired":[48],"data.":[49],"We":[50],"model":[51],"the":[52,108,114,120,128,131,141,145,156],"interaction":[54],"process":[55],"as":[56,163],"dynamic":[58,121],"directed":[59],"graph,":[60],"upon":[61],"which":[62],"build":[64],"collaborative":[66],"system.":[68],"This":[69,117],"system":[70],"comprises":[71],"scene":[73],"navigator":[74],"agent":[75,86,99],"for":[76,119],"environmental":[77],"perception":[78],"path":[81],"planning,":[82],"planning":[85],"decomposes":[88],"long-horizon":[89,186],"goals":[90],"into":[91],"atomic":[92],"actions.":[93],"Critically,":[94],"critic":[98],"establishes":[101],"closed-loop":[103],"feedback":[104],"mechanism":[105],"by":[106,127],"evaluating":[107],"deviation":[109],"between":[110],"generated":[111,146],"actions":[112],"planned":[115],"path.":[116],"allows":[118],"correction":[122],"of":[123,130,144,184],"trajectory":[124],"drifts":[125],"caused":[126],"stochasticity":[129],"generative":[132],"model,":[133],"thereby":[134],"ensuring":[135],"long-term":[136],"logical":[137],"consistency.":[138],"enhance":[140],"physical":[142,190],"realism":[143],"motions,":[147],"leverage":[149],"Direct":[150],"Preference":[151],"Optimization":[152],"(DPO)":[153],"train":[155],"action":[157],"generator,":[158],"significantly":[159,178],"reducing":[160],"artifacts":[161],"such":[162],"limb":[164],"distortion":[165],"foot-sliding.":[167],"Extensive":[168],"experiments":[169],"our":[171],"custom":[172],"SceneBench":[173],"benchmark":[174],"demonstrate":[175],"FantasyHSI":[177],"outperforms":[179],"existing":[180],"methods":[181],"terms":[183],"generalization,":[185],"task":[187],"completion,":[188],"realism.":[191]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}