{"id":"https://openalex.org/W7147556576","doi":"https://doi.org/10.1109/tvcg.2026.3679899","title":"Int3DNet: Scene-Motion Cross Attention Network for 3D Intention Prediction in Mixed Reality","display_name":"Int3DNet: Scene-Motion Cross Attention Network for 3D Intention Prediction in Mixed Reality","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7147556576","doi":"https://doi.org/10.1109/tvcg.2026.3679899","pmid":"https://pubmed.ncbi.nlm.nih.gov/41921170"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2026.3679899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3679899","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"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 Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5104261934","display_name":"Taewook Ha","orcid":"https://orcid.org/0009-0004-7946-8577"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taewook Ha","raw_affiliation_strings":["KAIST UVR Lab., Korea"],"raw_orcid":"https://orcid.org/0009-0004-7946-8577","affiliations":[{"raw_affiliation_string":"KAIST UVR Lab., Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132637372","display_name":"Woojin Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155543","display_name":"K+S (Germany)","ror":"https://ror.org/04kfnx806","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210155543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Woojin Cho","raw_affiliation_strings":["KAIST KI-ITC PMRC, Germany"],"raw_orcid":"https://orcid.org/0009-0003-4615-5630","affiliations":[{"raw_affiliation_string":"KAIST KI-ITC PMRC, Germany","institution_ids":["https://openalex.org/I4210155543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132579805","display_name":"Dooyoung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155543","display_name":"K+S (Germany)","ror":"https://ror.org/04kfnx806","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210155543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dooyoung Kim","raw_affiliation_strings":["KAIST KI-ITC ARRC, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6003-2181","affiliations":[{"raw_affiliation_string":"KAIST KI-ITC ARRC, Germany","institution_ids":["https://openalex.org/I4210155543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023177829","display_name":"Woontack Woo","orcid":"https://orcid.org/0000-0002-5501-4421"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woontack Woo","raw_affiliation_strings":["KAIST UVR Lab and KAIST KI-ITC ARRC, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST UVR Lab and KAIST KI-ITC ARRC, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33858075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"5","first_page":"4185","last_page":"4195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.5250999927520752,"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":0.5250999927520752,"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":0.17229999601840973,"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/T11431","display_name":"Action Observation and Synchronization","score":0.04179999977350235,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.6884999871253967},{"id":"https://openalex.org/keywords/mixed-reality","display_name":"Mixed reality","score":0.6049000024795532},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6035000085830688},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.5460000038146973},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.48649999499320984},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3970000147819519},{"id":"https://openalex.org/keywords/human-behavior","display_name":"Human behavior","score":0.3370000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8492000102996826},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.6884999871253967},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6211000084877014},{"id":"https://openalex.org/C206776904","wikidata":"https://www.wikidata.org/wiki/Q1758389","display_name":"Mixed reality","level":3,"score":0.6049000024795532},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6035000085830688},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5060999989509583},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.323199987411499},{"id":"https://openalex.org/C72568745","wikidata":"https://www.wikidata.org/wiki/Q12812953","display_name":"Human-centered computing","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C150140777","wikidata":"https://www.wikidata.org/wiki/Q960648","display_name":"Point of interest","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C20864712","wikidata":"https://www.wikidata.org/wiki/Q667800","display_name":"Biological motion","level":3,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2026.3679899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3679899","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"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 Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:41921170","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41921170","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1870415031","display_name":null,"funder_award_id":"RS-2024-00397663","funder_id":"https://openalex.org/F4320319144","funder_display_name":"Indian Institute of Technology, Patna"},{"id":"https://openalex.org/G2935700165","display_name":null,"funder_award_id":"CRC21015","funder_id":"https://openalex.org/F4320325370","funder_display_name":"National Research Council of Science and Technology"},{"id":"https://openalex.org/G4432275012","display_name":null,"funder_award_id":"RS-2025-02304167","funder_id":"https://openalex.org/F4320322064","funder_display_name":"Korea Institute for Advancement of Technology"}],"funders":[{"id":"https://openalex.org/F4320319144","display_name":"Indian Institute of Technology, Patna","ror":"https://ror.org/01ft5vz71"},{"id":"https://openalex.org/F4320322064","display_name":"Korea Institute for Advancement of Technology","ror":"https://ror.org/015w1qa96"},{"id":"https://openalex.org/F4320325370","display_name":"National Research Council of Science and Technology","ror":"https://ror.org/058rymf81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,85],"propose":[1],"Int3DNet,":[2],"a":[3,59,72,131],"scene-aware":[4],"network":[5],"that":[6,75],"predicts":[7],"3D":[8,146],"intention":[9,22,32,81,141,147,169],"areas":[10,148],"directly":[11,76],"from":[12,150],"scene":[13,68,154],"geometry":[14],"and":[15,45,51,67,90,112,119,153,162],"head-hand":[16,151],"motion":[17,65,152],"cues,":[18],"enabling":[19,157],"robust":[20],"human":[21],"prediction":[23,33],"without":[24],"explicit":[25],"object-level":[26],"perception.":[27],"In":[28],"Mixed":[29],"Reality":[30],"(MR),":[31],"is":[34],"critical":[35],"as":[36],"it":[37],"enables":[38],"the":[39,78,83,114,125],"system":[40],"to":[41,109],"anticipate":[42],"user":[43,54],"actions":[44],"respond":[46],"proactively,":[47],"reducing":[48],"interaction":[49,159],"delays":[50],"ensuring":[52],"seamless":[53,158],"experiences.":[55],"Our":[56],"method":[57,129],"employs":[58],"cross":[60],"attention":[61],"fusion":[62],"of":[63,107,127,133,168],"sparse":[64],"cues":[66],"point":[69],"clouds,":[70],"offering":[71],"novel":[73],"approach":[74],"interprets":[77],"user's":[79],"spatial":[80],"within":[82],"scene.":[84],"evaluated":[86],"Int3DNet":[87,143],"on":[88,140],"MoGaze":[89],"CIRCLE":[91],"datasets,":[92],"which":[93],"are":[94],"public":[95],"datasets":[96],"for":[97],"full-body":[98],"human-scene":[99],"interactions,":[100],"showing":[101],"consistent":[102],"performance":[103],"across":[104],"time":[105],"horizons":[106],"up":[108],"1500":[110],"ms":[111],"outperforming":[113],"baselines,":[115],"even":[116],"in":[117],"diverse":[118],"unseen":[120],"scenes.":[121],"Moreover,":[122],"we":[123],"demonstrate":[124],"usability":[126],"proposed":[128],"through":[130,165],"demonstration":[132],"efficient":[134],"visual":[135],"question":[136],"answering":[137],"(VQA)":[138],"based":[139],"areas.":[142,170],"provides":[144],"reliable":[145],"derived":[149],"geometry,":[155],"thus":[156],"between":[160],"humans":[161],"MR":[163],"systems":[164],"proactive":[166],"processing":[167]},"counts_by_year":[],"updated_date":"2026-05-20T06:11:20.791850","created_date":"2026-04-02T00:00:00"}