{"id":"https://openalex.org/W4404953707","doi":"https://doi.org/10.1109/humanoids58906.2024.10769830","title":"Diffusing in Someone Else\u2019s Shoes: Robotic Perspective-Taking with Diffusion","display_name":"Diffusing in Someone Else\u2019s Shoes: Robotic Perspective-Taking with Diffusion","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4404953707","doi":"https://doi.org/10.1109/humanoids58906.2024.10769830"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids58906.2024.10769830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids58906.2024.10769830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/Humanoids58906.2024.10769830","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067780112","display_name":"Josua Spisak","orcid":null},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Josua Spisak","raw_affiliation_strings":["University of Hamburg,Knowledge Technology (WTM) group,Department of Informatics,Hamburg,Germany,22527"],"affiliations":[{"raw_affiliation_string":"University of Hamburg,Knowledge Technology (WTM) group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040045142","display_name":"Matthias Kerzel","orcid":"https://orcid.org/0000-0002-1378-0435"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Kerzel","raw_affiliation_strings":["University of Hamburg,Knowledge Technology (WTM) group,Department of Informatics,Hamburg,Germany,22527"],"affiliations":[{"raw_affiliation_string":"University of Hamburg,Knowledge Technology (WTM) group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["University of Hamburg,Knowledge Technology (WTM) group,Department of Informatics,Hamburg,Germany,22527"],"affiliations":[{"raw_affiliation_string":"University of Hamburg,Knowledge Technology (WTM) group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067780112"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":0.98,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77912612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.944100022315979,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.944100022315979,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9401000142097473,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9375,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.8103077411651611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7319091558456421},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.7009084224700928},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6547205448150635},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.643572986125946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5916716456413269},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5813977718353271},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5753107666969299},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5501079559326172},{"id":"https://openalex.org/keywords/first-person","display_name":"First person","score":0.4686281979084015},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4526793360710144},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22911402583122253},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19850704073905945},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0806916356086731},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07277742028236389}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.8103077411651611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7319091558456421},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7009084224700928},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6547205448150635},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.643572986125946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916716456413269},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5813977718353271},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5753107666969299},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5501079559326172},{"id":"https://openalex.org/C3018176237","wikidata":"https://www.wikidata.org/wiki/Q5397000","display_name":"First person","level":2,"score":0.4686281979084015},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4526793360710144},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22911402583122253},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19850704073905945},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0806916356086731},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07277742028236389},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/humanoids58906.2024.10769830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids58906.2024.10769830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:17208263","is_oa":true,"landing_page_url":"https://doi.org/10.1109/Humanoids58906.2024.10769830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/technicalDocumentation"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:17208263","is_oa":true,"landing_page_url":"https://doi.org/10.1109/Humanoids58906.2024.10769830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/technicalDocumentation"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1560270123","https://openalex.org/W1901129140","https://openalex.org/W1998952763","https://openalex.org/W2132326677","https://openalex.org/W2133665775","https://openalex.org/W2591957724","https://openalex.org/W2771461682","https://openalex.org/W2810307462","https://openalex.org/W2962793481","https://openalex.org/W2963021791","https://openalex.org/W2963073614","https://openalex.org/W3036167779","https://openalex.org/W3037767967","https://openalex.org/W3121370741","https://openalex.org/W4224992933","https://openalex.org/W4226125322","https://openalex.org/W4281485151","https://openalex.org/W4292794845","https://openalex.org/W4297812239","https://openalex.org/W4312358791","https://openalex.org/W4312553711","https://openalex.org/W4312933868","https://openalex.org/W4386939539","https://openalex.org/W4388145436","https://openalex.org/W4390872435","https://openalex.org/W4390873752","https://openalex.org/W4401415042","https://openalex.org/W6712127269","https://openalex.org/W6734502593","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6788990321","https://openalex.org/W6809664228","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6854829563"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W4387104524"],"abstract_inverted_index":{"Humanoid":[0],"robots":[1,86],"can":[2],"benefit":[3],"from":[4,13,51,55,64,90,119,131],"their":[5],"similarity":[6],"to":[7,21,36,42,48,59,117,126,154],"the":[8,27,30,34,44,91,115,120,128,132,138,145,148,156],"human":[9,32],"shape":[10],"by":[11,87,124],"learning":[12,31,125],"humans.":[14,74],"When":[15],"humans":[16,19],"teach":[17],"other":[18,170],"how":[20,41,60],"perform":[22,43],"actions,":[23],"they":[24],"often":[25,83],"demonstrate":[26],"actions":[28],"and":[29,140,144,162],"imitates":[33],"demonstration":[35,53],"get":[37],"an":[38,99],"idea":[39],"of":[40,142,158],"action.":[45],"Being":[46],"able":[47],"mentally":[49],"transfer":[50],"a":[52,56,65,78,109],"seen":[54],"third-person":[57,121,133,160],"perspective":[58,67,130],"it":[61,81],"should":[62],"look":[63],"first-person":[66,92,129,164],"is":[68,77,82],"fundamental":[69],"for":[70,85,98],"this":[71,76,174],"ability":[72],"in":[73,173],"As":[75],"challenging":[79],"task,":[80],"simplified":[84],"creating":[88],"demonstrations":[89,96,122,161],"perspective.":[93,134],"Creating":[94],"these":[95],"allows":[97,152],"easier":[100],"imitation":[101],"but":[102],"requires":[103],"more":[104],"effort.":[105],"Therefore,":[106],"we":[107],"introduce":[108],"novel":[110],"diffusion":[111],"model":[112,136],"that":[113],"enables":[114],"robot":[116],"learn":[118],"directly":[123],"generate":[127],"The":[135],"translates":[137],"size":[139],"rotations":[141],"objects":[143],"environment":[146],"between":[147],"two":[149],"perspectives.":[150],"This":[151],"us":[153],"utilise":[155],"benefits":[157],"easy-to-produce":[159],"easy-to-imitate":[163],"demonstrations.":[165],"Our":[166],"approach":[167],"significantly":[168],"outperforms":[169],"image-to-image":[171],"models":[172],"task.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
