{"id":"https://openalex.org/W7123353024","doi":"https://doi.org/10.1109/lsp.2026.3652960","title":"HuMo3D: Intention-Driven Dual-Branch Multimodal Human Motion Prediction in 3D Scenes","display_name":"HuMo3D: Intention-Driven Dual-Branch Multimodal Human Motion Prediction in 3D Scenes","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123353024","doi":"https://doi.org/10.1109/lsp.2026.3652960"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2026.3652960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3652960","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5122870319","display_name":"Yi Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I163151501","display_name":"Hangzhou Normal University","ror":"https://ror.org/014v1mr15","country_code":"CN","type":"education","lineage":["https://openalex.org/I163151501"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Lin","raw_affiliation_strings":["School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China","institution_ids":["https://openalex.org/I163151501"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100583138","display_name":"Wangjie Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I163151501","display_name":"Hangzhou Normal University","ror":"https://ror.org/014v1mr15","country_code":"CN","type":"education","lineage":["https://openalex.org/I163151501"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangjie Xia","raw_affiliation_strings":["School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China","institution_ids":["https://openalex.org/I163151501"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122907794","display_name":"Ting Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I163151501","display_name":"Hangzhou Normal University","ror":"https://ror.org/014v1mr15","country_code":"CN","type":"education","lineage":["https://openalex.org/I163151501"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Yu","raw_affiliation_strings":["School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4348-2671","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China","institution_ids":["https://openalex.org/I163151501"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5122870319"],"corresponding_institution_ids":["https://openalex.org/I163151501"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06452798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"614","last_page":"618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.5615000128746033,"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":0.5615000128746033,"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":0.2587999999523163,"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":0.029100000858306885,"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/motion","display_name":"Motion (physics)","score":0.7002000212669373},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6721000075340271},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6327000260353088},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6172999739646912},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6013000011444092},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.5874000191688538},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5570999979972839},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4108000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137999773025513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7166000008583069},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7002000212669373},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6721000075340271},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6327000260353088},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.5874000191688538},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5360000133514404},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4108000099658966},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3513999879360199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2026.3652960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3652960","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3292031857","display_name":null,"funder_award_id":"62002314","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7345075855","display_name":null,"funder_award_id":"62572164","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1735317348","https://openalex.org/W2126314688","https://openalex.org/W2275295007","https://openalex.org/W2798685833","https://openalex.org/W2963065614","https://openalex.org/W2963158576","https://openalex.org/W2963165299","https://openalex.org/W2963324990","https://openalex.org/W2963548793","https://openalex.org/W2964203186","https://openalex.org/W2978956737","https://openalex.org/W2983925976","https://openalex.org/W3034423770","https://openalex.org/W3034696014","https://openalex.org/W3040942941","https://openalex.org/W3091146265","https://openalex.org/W3111771376","https://openalex.org/W3169575318","https://openalex.org/W3207857704","https://openalex.org/W4214677627","https://openalex.org/W4285036875","https://openalex.org/W4312272780","https://openalex.org/W4312637963","https://openalex.org/W4384917104","https://openalex.org/W4385245566","https://openalex.org/W4390872223","https://openalex.org/W4391165368","https://openalex.org/W4395069639","https://openalex.org/W4402753661","https://openalex.org/W4402816986","https://openalex.org/W4403182266","https://openalex.org/W4409366569","https://openalex.org/W4412030766","https://openalex.org/W4413145383"],"related_works":[],"abstract_inverted_index":{"Human":[0],"motion":[1,79,113,125],"prediction":[2,114],"is":[3],"a":[4,51],"fundamental":[5],"task":[6],"for":[7],"enabling":[8],"intelligent":[9],"systems":[10],"to":[11,94,134],"anticipate":[12],"human":[13,32,58,78,124],"behavior":[14],"in":[15,36,122],"dynamic":[16],"environments.":[17],"Despite":[18],"significant":[19],"progress,":[20],"existing":[21],"methods":[22],"primarily":[23],"focus":[24],"on":[25,100],"human-object":[26],"interactions,":[27],"often":[28],"neglecting":[29],"the":[30,69,75,84,101,117,135],"underlying":[31],"intention,":[33],"which":[34,73,88],"results":[35],"predictions":[37],"that":[38,55,108],"violate":[39],"real-world":[40],"spatial":[41],"and":[42,80,83,103,130],"semantic":[43],"constraints.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"HuMo3D,":[50],"dual-branch":[52],"multimodal":[53],"framework":[54,64],"explicitly":[56],"integrates":[57],"intention":[59],"with":[60],"scene":[61,81],"geometry.":[62],"Our":[63],"introduces":[65],"two":[66],"key":[67],"components:":[68],"Trajectory":[70],"Intention":[71,86],"Learner,":[72,87],"captures":[74],"relationship":[76],"between":[77],"geometry,":[82],"Pose":[85],"dynamically":[89],"prioritizes":[90],"potential":[91],"interaction":[92],"regions":[93],"model":[95],"pose-intention":[96],"relationships.":[97],"Extensive":[98],"experiments":[99],"MoGaze":[102],"GIMO":[104],"benchmark":[105],"dataset":[106],"show":[107],"HuMo3D":[109],"significantly":[110],"outperforms":[111],"state-of-the-art":[112],"methods,":[115],"highlighting":[116],"importance":[118],"of":[119],"intention-aware":[120],"modeling":[121],"3D":[123],"prediction.":[126],"For":[127],"more":[128],"details":[129],"code,":[131],"please":[132],"refer":[133],"project":[136],"page.":[137]},"counts_by_year":[],"updated_date":"2026-01-29T23:13:10.619473","created_date":"2026-01-14T00:00:00"}