{"id":"https://openalex.org/W7137871879","doi":"https://doi.org/10.1609/aaai.v40i3.37188","title":"IntentMotion: Learning Intent-Aware Human Motion from Language in 3D Scenes","display_name":"IntentMotion: Learning Intent-Aware Human Motion from Language in 3D Scenes","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137871879","doi":"https://doi.org/10.1609/aaai.v40i3.37188"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i3.37188","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37188","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.v40i3.37188","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125133005","display_name":"Wenfeng Song","orcid":null},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfeng Song","raw_affiliation_strings":["College of Computer Science, Beijing Information Science and Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing Information Science and Technology University","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000149447","display_name":"Shuguo Zheng","orcid":"https://orcid.org/0000-0001-6717-5196"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Zheng","raw_affiliation_strings":["College of Computer Science, Beijing Information Science and Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing Information Science and Technology University","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129710949","display_name":"Xinyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101613857","display_name":"Xingliang Jin","orcid":"https://orcid.org/0000-0001-9209-7804"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingliang Jin","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129713103","display_name":"Aimin Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aimin Hao","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101672546","display_name":"Fei Hou","orcid":"https://orcid.org/0000-0002-6172-3419"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Hou","raw_affiliation_strings":["Key Laboratory of System Software (CAS), State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, China\nUniversity of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of System Software (CAS), State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, China\nUniversity of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129642942","display_name":"Xia Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia Hou","raw_affiliation_strings":["College of Computer Science, Beijing Information Science and Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing Information Science and Technology University","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129677506","display_name":"Shuai Li","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Li","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, Beihang University\nZhongguancun Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University\nZhongguancun Laboratory, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":"3","first_page":"2065","last_page":"2073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.5540000200271606,"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":0.5540000200271606,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.15950000286102295,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.15000000596046448,"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/motion","display_name":"Motion (physics)","score":0.661899983882904},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6319000124931335},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6141999959945679},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.48240000009536743},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4814999997615814},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42910000681877136},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4250999987125397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778000235557556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6998999714851379},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.661899983882904},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6319000124931335},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6141999959945679},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43779999017715454},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26010000705718994}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i3.37188","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37188","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/37188","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37188","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.v40i3.37188","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37188","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":[{"id":"https://metadata.un.org/sdg/10","score":0.4763574004173279,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"human":[1,45],"motion":[2,46,93],"in":[3,25,47,130,171],"complex":[4],"3D":[5,48],"scenes":[6,49],"from":[7,50,125],"text":[8],"is":[9,87],"a":[10,40,82,91,131,145],"challenging":[11],"task":[12],"with":[13,77,90],"broad":[14],"applications.":[15],"However,":[16],"existing":[17],"methods":[18],"often":[19],"overlook":[20],"realistic":[21],"physical":[22],"contact,":[23],"resulting":[24],"visually":[26],"plausible":[27],"but":[28],"physically":[29],"unrealistic":[30],"motion,":[31,110],"e.g.,":[32],"penetration.":[33],"To":[34,104],"alleviate":[35],"this,":[36],"we":[37,111],"propose":[38,113],"IntentMotion,":[39],"novel":[41],"framework":[42],"that":[43,165],"generates":[44],"natural":[51],"language":[52,75],"instructions":[53],"by":[54,149],"explicitly":[55,72],"modeling":[56],"intent.":[57],"We":[58],"first":[59],"introduce":[60],"the":[61,106,121,126,142,159],"Intention-Guided":[62],"Contact":[63],"Field":[64],"(IGCF).":[65],"This":[66],"differentiable":[67],"voxel-based":[68],"contact":[69,79,96,128,136,172],"region":[70],"representation":[71],"aligns":[73],"parsed":[74],"roles":[76],"spatial":[78],"regions":[80],"through":[81,101],"hierarchical":[83],"attention":[84],"mechanism.":[85],"IGCF":[86,155],"jointly":[88],"trained":[89],"diffusion-based":[92],"generator,":[94],"allowing":[95],"predictions":[97],"to":[98,140,178],"adapt":[99],"dynamically":[100],"gradient":[102],"feedback.":[103],"improve":[105],"controllability":[107],"and":[108,161,176],"physics-aware":[109],"further":[112],"an":[114],"Intention-Aware":[115],"Diffusion":[116],"Model":[117],"(IADM),":[118],"which":[119],"decouples":[120],"high-level":[122],"semantic":[123,174],"planning":[124],"low-level":[127],"refinement":[129],"coarse-to-fine":[132],"process.":[133],"The":[134],"optimized":[135],"cues":[137],"are":[138],"utilized":[139],"guide":[141],"synthesis":[143],"of":[144],"coarse":[146],"trajectory,":[147],"followed":[148],"refining":[150],"detailed":[151],"pose":[152],"sequences":[153],"under":[154],"supervision.":[156],"Experiments":[157],"on":[158],"HUMANISE":[160],"LINGO":[162],"datasets":[163],"demonstrate":[164],"our":[166],"IntentMotion":[167],"outperforms":[168],"recent":[169],"baselines":[170],"accuracy,":[173],"alignment,":[175],"generalization":[177],"unseen":[179],"scenes.":[180]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
