{"id":"https://openalex.org/W4389666191","doi":"https://doi.org/10.1109/iros55552.2023.10342417","title":"MoEmo Vision Transformer: Integrating Cross-Attention and Movement Vectors in 3D Pose Estimation for HRI Emotion Detection","display_name":"MoEmo Vision Transformer: Integrating Cross-Attention and Movement Vectors in 3D Pose Estimation for HRI Emotion Detection","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666191","doi":"https://doi.org/10.1109/iros55552.2023.10342417"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018509489","display_name":"David C. Jeong","orcid":"https://orcid.org/0000-0002-8829-3578"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David C. Jeong","raw_affiliation_strings":["Santa Clara University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Clara University","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071823645","display_name":"Tianma Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianma Shen","raw_affiliation_strings":["Santa Clara University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Clara University","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000327138","display_name":"Hongji Liu","orcid":"https://orcid.org/0000-0003-1324-0700"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongji Liu","raw_affiliation_strings":["Santa Clara University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Clara University","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089262860","display_name":"Raghav Kapoor","orcid":"https://orcid.org/0000-0002-1030-7423"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghav Kapoor","raw_affiliation_strings":["Santa Clara University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Clara University","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113069979","display_name":"Casey Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Casey Nguyen","raw_affiliation_strings":["Santa Clara University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Clara University","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394717","display_name":"Song Liu","orcid":"https://orcid.org/0009-0003-0941-6619"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Liu","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007901785","display_name":"Christopher Kitts","orcid":"https://orcid.org/0000-0001-8078-9360"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher A. Kitts","raw_affiliation_strings":["Santa Clara University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Clara University","institution_ids":["https://openalex.org/I16269868"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6069,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77467987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9846","last_page":"9852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9984999895095825,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/computer-science","display_name":"Computer science","score":0.7743484973907471},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7580825090408325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6876047849655151},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5845410227775574},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4883841872215271},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45411351323127747},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.43655237555503845},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4175388813018799},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3759879171848297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7743484973907471},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7580825090408325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6876047849655151},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5845410227775574},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4883841872215271},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45411351323127747},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.43655237555503845},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4175388813018799},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3759879171848297},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1987768879","https://openalex.org/W2013548868","https://openalex.org/W2066806063","https://openalex.org/W2073246097","https://openalex.org/W2082494017","https://openalex.org/W2107340807","https://openalex.org/W2141973273","https://openalex.org/W2153082786","https://openalex.org/W2157936707","https://openalex.org/W2162104245","https://openalex.org/W2194775991","https://openalex.org/W2502868508","https://openalex.org/W2559085405","https://openalex.org/W2594167370","https://openalex.org/W2739474071","https://openalex.org/W2765218414","https://openalex.org/W2798503473","https://openalex.org/W2888816955","https://openalex.org/W2908176280","https://openalex.org/W2909438955","https://openalex.org/W2910193695","https://openalex.org/W2946410230","https://openalex.org/W2962730651","https://openalex.org/W2963037989","https://openalex.org/W2972850892","https://openalex.org/W2975420824","https://openalex.org/W2979477292","https://openalex.org/W2980440809","https://openalex.org/W3014929318","https://openalex.org/W3098061148","https://openalex.org/W3105394152","https://openalex.org/W3105907928","https://openalex.org/W3111984990","https://openalex.org/W3138516171","https://openalex.org/W3167491448","https://openalex.org/W3209114384","https://openalex.org/W4246502257","https://openalex.org/W4289639555","https://openalex.org/W4292794012","https://openalex.org/W4312797994","https://openalex.org/W4312799843","https://openalex.org/W4312986439","https://openalex.org/W4313171337","https://openalex.org/W4385245566","https://openalex.org/W4386076485","https://openalex.org/W6602263454","https://openalex.org/W6739901393","https://openalex.org/W6765758572","https://openalex.org/W6784333009","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2066003895","https://openalex.org/W2537963312","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W4287179229","https://openalex.org/W3205513966","https://openalex.org/W3120459843","https://openalex.org/W4366547574","https://openalex.org/W3200191727"],"abstract_inverted_index":{"Emotion":[0],"detection":[1,16,66,180],"presents":[2],"challenges":[3],"to":[4,29,56,103,147,158,172],"intelligent":[5],"human-robot":[6],"interaction":[7],"(URI).":[8],"Foundational":[9],"deep":[10],"learning":[11],"techniques":[12],"used":[13],"in":[14],"emotion":[15,65,93,160,179],"are":[17],"limited":[18],"by":[19],"information-constrained":[20],"datasets":[21],"or":[22],"models":[23],"that":[24,84,181],"lack":[25],"the":[26,38,39,48,110,122,127,169,183],"necessary":[27],"complexity":[28],"learn":[30],"interactions":[31],"between":[32,113],"input":[33],"data":[34,82],"elements,":[35],"such":[36],"as":[37],"variance":[40],"of":[41,88,116,124,131,138],"human":[42,64,73,89,97,133],"emotions":[43],"across":[44,76],"different":[45],"contexts.":[46,101,140],"In":[47],"current":[49,184],"effort,":[50],"we":[51,167],"introduce":[52],"1)":[53],"MoEmo":[54,170],"(Motion":[55],"Emotion),":[57],"a":[58,81,143,155],"cross-attention":[59,125,144],"vision":[60],"transformer":[61],"(ViT)":[62],"for":[63],"within":[67],"robotics":[68],"systems":[69],"based":[70,95],"on":[71,96,126],"3D":[72],"pose":[74],"estimations":[75],"various":[77],"contexts,":[78],"and":[79,91,99,118,135,151,176],"2)":[80],"set":[83],"offers":[85],"full-body":[86,132],"videos":[87],"movement":[90,114,129,149],"corresponding":[92],"labels":[94],"gestures":[98,117],"environmental":[100,119,139],"Compared":[102],"existing":[104],"approaches,":[105],"our":[106,163],"method":[107],"effectively":[108],"leverages":[109],"subtle":[111],"connections":[112],"vectors":[115,130,150],"contexts":[120,153],"through":[121],"use":[123],"extracted":[128],"gestures/poses":[134],"feature":[136],"maps":[137],"We":[141],"implement":[142],"fusion":[145],"model":[146],"combine":[148],"environment":[152],"into":[154],"joint":[156],"representation":[157],"derive":[159],"estimation.":[161],"Leveraging":[162],"Naturalistic":[164],"Motion":[165],"Database,":[166],"train":[168],"system":[171],"jointly":[173],"analyze":[174],"motion":[175],"context,":[177],"yielding":[178],"outperforms":[182],"state-of-the-art.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2023-12-14T00:00:00"}