{"id":"https://openalex.org/W7204593671","doi":"https://doi.org/10.48550/arxiv.2608.27039","title":"Multi-Person Human Motion Forecasting in Complex Scenes","display_name":"Multi-Person Human Motion Forecasting in Complex Scenes","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204593671","doi":"https://doi.org/10.48550/arxiv.2608.27039"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.27039","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27039","pdf_url":"https://arxiv.org/pdf/2608.27039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.27039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066957105","display_name":"Serdar Ozsoy","orcid":"https://orcid.org/0000-0003-1765-4708","observed_orcids":["https://orcid.org/0000-0003-1765-4708"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ozsoy, Serdar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028937864","display_name":"Lars Doorenbos","orcid":"https://orcid.org/0000-0002-0231-9950","observed_orcids":["https://orcid.org/0000-0002-0231-9950"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Doorenbos, Lars","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012240246","display_name":"J\u00fcergen Gall","orcid":"https://orcid.org/0000-0002-9447-3399","observed_orcids":["https://orcid.org/0000-0002-9447-3399"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gall, Juergen","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":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.22380000352859497,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.22380000352859497,"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/T12290","display_name":"Human Motion and Animation","score":0.17569999396800995,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.16660000383853912,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/complex-scenes","display_name":"complex scenes","score":0.6859999895095825},{"id":"https://openalex.org/keywords/conditional-diffusion-models","display_name":"conditional diffusion models","score":0.7110000252723694},{"id":"https://openalex.org/keywords/social-interaction-modeling","display_name":"social interaction modeling","score":0.8489999771118164},{"id":"https://openalex.org/keywords/motion-history","display_name":"motion history","score":0.8569999933242798},{"id":"https://openalex.org/keywords/long-term-trajectory-prediction","display_name":"long-term trajectory prediction","score":0.6579999923706055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713699996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6927000284194946},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5730999708175659},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4097000062465668},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3725000023841858},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3684999942779541},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27039","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27039","pdf_url":"https://arxiv.org/pdf/2608.27039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.27039","doi":"https://doi.org/10.48550/arxiv.2608.27039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27039","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.27039","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27039","pdf_url":"https://arxiv.org/pdf/2608.27039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7009332776069641}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurately":[0],"forecasting":[1],"the":[2,12,18,85,91,121,131],"movement":[3],"of":[4,17],"people":[5],"in":[6,90,123],"complex":[7,103],"scenes":[8],"requires":[9],"reasoning":[10],"over":[11],"past":[13],"and":[14,28,57,79,106,126,141,151],"present":[15],"state":[16],"entire":[19],"environment.":[20],"In":[21],"this":[22],"context,":[23],"effectively":[24],"incorporating":[25],"object":[26,58],"information":[27],"social":[29,81,104],"interactions":[30,86],"into":[31,60],"a":[32,47,61,80,94],"unified":[33],"framework":[34],"remains":[35],"particularly":[36],"challenging.":[37],"To":[38],"address":[39],"this,":[40],"we":[41],"propose":[42],"Object-Conditioned":[43],"Social":[44],"Diffusion":[45],"(OCSD),":[46],"conditional":[48],"diffusion":[49],"model":[50,97],"that":[51,69,83,115],"integrates":[52],"motion":[53],"history,":[54],"multi-person":[55],"interactions,":[56,105],"cues":[59],"single":[62],"framework.":[63],"OCSD":[64,116],"uses":[65],"an":[66],"object-conditioning":[67],"mechanism":[68],"modulates":[70],"denoising":[71],"at":[72],"every":[73],"timestep,":[74],"enabling":[75],"fine-grained":[76],"human-object":[77],"reasoning,":[78],"encoder":[82],"models":[84],"between":[87],"all":[88],"humans":[89],"scene.":[92],"As":[93],"result,":[95],"our":[96],"naturally":[98],"handles":[99],"varying":[100],"group":[101],"sizes,":[102],"supports":[107],"sampling":[108],"multiple":[109],"plausible":[110],"futures.":[111],"Extensive":[112],"experiments":[113],"show":[114],"achieves":[117],"state-of-the-art":[118],"results":[119],"on":[120,139,145],"Humans":[122],"Kitchens":[124],"(HiK)":[125],"HOI-M3":[127,146],"benchmarks.":[128],"It":[129],"reduces":[130],"two-second":[132],"path":[133],"error":[134],"by":[135],"121.5":[136],"mm":[137,143],"(31.3%)":[138],"HiK":[140],"130.5":[142],"(33.2%)":[144],"compared":[147],"to":[148],"prior":[149],"work,":[150],"produces":[152],"more":[153],"realistic":[154],"long-term":[155],"forecasts.":[156]},"counts_by_year":[],"updated_date":"2026-09-24T07:57:37.273135","created_date":"2026-08-29T00:00:00"}