{"id":"https://openalex.org/W4392633941","doi":"https://doi.org/10.1145/3610977.3635006","title":"PoseTron: Enabling Close-Proximity Human-Robot Collaboration Through Multi-human Motion Prediction","display_name":"PoseTron: Enabling Close-Proximity Human-Robot Collaboration Through Multi-human Motion Prediction","publication_year":2024,"publication_date":"2024-03-10","ids":{"openalex":"https://openalex.org/W4392633941","doi":"https://doi.org/10.1145/3610977.3635006"},"language":"en","primary_location":{"id":"doi:10.1145/3610977.3635006","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610977.3635006","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3635006","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3635006","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086074961","display_name":"Mohammad Samin Yasar","orcid":"https://orcid.org/0000-0002-4684-2823"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Samin Yasar","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4684-2823","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009971165","display_name":"Md Mofijul Islam","orcid":"https://orcid.org/0000-0003-4207-5863"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md Mofijul Islam","raw_affiliation_strings":["AWS Generative AI Innovation Center, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4207-5863","affiliations":[{"raw_affiliation_string":"AWS Generative AI Innovation Center, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101779827","display_name":"Tariq Iqbal","orcid":"https://orcid.org/0000-0003-0133-1234"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tariq Iqbal","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0133-1234","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7498,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85089642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"830","last_page":"839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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":0.9988999962806702,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7750155329704285},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6765547394752502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6353275775909424},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5463212132453918},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5035421252250671},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4838075041770935},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.47108232975006104},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.4439624845981598},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.44380781054496765},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.43694767355918884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42344754934310913},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33171987533569336},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.23970147967338562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750155329704285},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6765547394752502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6353275775909424},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5463212132453918},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5035421252250671},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4838075041770935},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47108232975006104},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.4439624845981598},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.44380781054496765},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.43694767355918884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42344754934310913},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33171987533569336},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.23970147967338562},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610977.3635006","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610977.3635006","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3635006","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3610977.3635006","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610977.3635006","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3635006","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392633941.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1922715780","https://openalex.org/W1987616874","https://openalex.org/W1992461594","https://openalex.org/W2052971528","https://openalex.org/W2059993653","https://openalex.org/W2115579991","https://openalex.org/W2222794653","https://openalex.org/W2277195237","https://openalex.org/W2280090643","https://openalex.org/W2346286924","https://openalex.org/W2424778531","https://openalex.org/W2482333547","https://openalex.org/W2742822919","https://openalex.org/W2762248135","https://openalex.org/W2767263466","https://openalex.org/W2773965764","https://openalex.org/W2791581064","https://openalex.org/W2802025241","https://openalex.org/W2884642747","https://openalex.org/W2891091472","https://openalex.org/W2922464707","https://openalex.org/W2927819804","https://openalex.org/W2963524571","https://openalex.org/W2964134613","https://openalex.org/W2964203186","https://openalex.org/W2968603329","https://openalex.org/W2991451943","https://openalex.org/W2993797559","https://openalex.org/W2999968307","https://openalex.org/W3009973634","https://openalex.org/W3033920763","https://openalex.org/W3045019771","https://openalex.org/W3090449556","https://openalex.org/W3096973715","https://openalex.org/W3105214888","https://openalex.org/W3106257603","https://openalex.org/W3111771376","https://openalex.org/W3116651890","https://openalex.org/W3129900808","https://openalex.org/W3138516171","https://openalex.org/W3205254676","https://openalex.org/W4220911514","https://openalex.org/W4256224597","https://openalex.org/W4292343017","https://openalex.org/W4310113038","https://openalex.org/W4323870340","https://openalex.org/W4323871138"],"related_works":["https://openalex.org/W1992503747","https://openalex.org/W2371519816","https://openalex.org/W2043154226","https://openalex.org/W2369529107","https://openalex.org/W2329043542","https://openalex.org/W3013693939","https://openalex.org/W2109948066","https://openalex.org/W1678858522","https://openalex.org/W4388576605","https://openalex.org/W2062302545"],"abstract_inverted_index":{"As":[0],"robots":[1,11],"enter":[2],"human":[3,16],"workspaces,":[4],"there":[5],"is":[6,29],"a":[7,33,54,76,89,112,166,178],"crucial":[8],"need":[9],"for":[10,38,67,181],"to":[12,18,32,80,105,127],"understand":[13],"and":[14,21,41,63,69,123,190],"predict":[15,128],"motion":[17,100,183],"achieve":[19],"safe":[20,189],"fluent":[22],"human-robot":[23,70],"collaboration":[24],"(HRC).":[25],"However,":[26],"accurate":[27],"prediction":[28,161,184],"challenging":[30],"due":[31],"lack":[34],"of":[35,44,99,173],"large-scale":[36],"datasets":[37],"close-proximity":[39],"HRC":[40],"the":[42,82,94,124,140,157,171],"absence":[43],"generalizable":[45],"algorithms.":[46,86,145],"To":[47],"overcome":[48],"these":[49],"challenges,":[50],"we":[51,73,164],"present":[52],"INTERACT,":[53],"comprehensive":[55,167],"multimodal":[56,114],"dataset":[57,142],"covering":[58],"3-D":[59],"Skeleton,":[60],"RGB+D,":[61],"gaze,":[62],"robot":[64,186],"joint":[65],"data":[66],"human-human":[68],"collaboration.":[71],"Additionally,":[72],"introduce":[74],"PoseTron,":[75],"novel":[77,113],"transformer-based":[78],"architecture":[79],"address":[81],"gap":[83],"in":[84,93,188],"learning":[85],"PoseTron":[87,134,150],"introduces":[88],"conditional":[90],"attention":[91,115],"mechanism":[92],"encoder":[95,125],"enabling":[96],"efficient":[97],"weighing":[98],"information":[101],"from":[102,120],"all":[103,152,156],"agents":[104],"incorporate":[106],"team":[107],"dynamics.":[108],"The":[109,146],"decoder":[110],"features":[111],"mechanism,":[116],"which":[117],"weights":[118],"representations":[119],"different":[121],"modalities":[122],"outputs":[126],"future":[129],"motion.":[130],"We":[131],"extensively":[132],"evaluated":[133],"by":[135],"comparing":[136],"its":[137],"performance":[138],"on":[139],"INTERACT":[141],"against":[143],"state-of-the-art":[144],"results":[147],"suggest":[148],"that":[149],"outperformed":[151],"other":[153],"methods":[154],"across":[155],"scenarios,":[158],"attaining":[159],"lowest":[160],"errors.":[162],"Furthermore,":[163],"conducted":[165],"ablation":[168],"study,":[169],"emphasizing":[170],"importance":[172],"design":[174],"choices,":[175],"pointing":[176],"towards":[177],"promising":[179],"direction":[180],"integrating":[182],"with":[185],"perception":[187],"effective":[191],"HRC.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}