{"id":"https://openalex.org/W7134835413","doi":"https://doi.org/10.1145/3757279.3785601","title":"Embodied Referring Expression Comprehension in Human-Robot Interaction","display_name":"Embodied Referring Expression Comprehension in Human-Robot Interaction","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134835413","doi":"https://doi.org/10.1145/3757279.3785601"},"language":null,"primary_location":{"id":"doi:10.1145/3757279.3785601","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757279.3785601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","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/A5103919696","display_name":"Mofijul Islam","orcid":null},"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":"Md Mofijul Islam","raw_affiliation_strings":["University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0000-0003-4207-5863","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092354762","display_name":"Alexi Gladstone","orcid":null},"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":"Alexi Gladstone","raw_affiliation_strings":["University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0009-0006-6294-5888","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019860863","display_name":"Sujan Sarker","orcid":"https://orcid.org/0000-0001-8784-8933"},"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":"Sujan Sarker","raw_affiliation_strings":["University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0000-0001-8784-8933","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128634899","display_name":"Ganesh Nanduru","orcid":null},"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":"Ganesh Nanduru","raw_affiliation_strings":["University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0009-0008-7633-875X","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128686345","display_name":"Md Fahim","orcid":null},"institutions":[{"id":"https://openalex.org/I205746353","display_name":"University of Dhaka","ror":"https://ror.org/05wv2vq37","country_code":"BD","type":"education","lineage":["https://openalex.org/I205746353"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md Fahim","raw_affiliation_strings":["University of Dhaka, Dhaka, Bangladesh"],"raw_orcid":"https://orcid.org/0009-0001-6139-5283","affiliations":[{"raw_affiliation_string":"University of Dhaka, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I205746353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128631915","display_name":"Keyan Du","orcid":null},"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":"Keyan Du","raw_affiliation_strings":["University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0009-0004-5277-2835","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128658652","display_name":"Aman Chadha","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aman Chadha","raw_affiliation_strings":["Apple, Cupertino, USA"],"raw_orcid":"https://orcid.org/0000-0001-6621-9003","affiliations":[{"raw_affiliation_string":"Apple, Cupertino, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"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, USA"],"raw_orcid":"https://orcid.org/0000-0003-0133-1234","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":null,"issue":null,"first_page":"503","last_page":"512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.43220001459121704,"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"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.43220001459121704,"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/T11431","display_name":"Action Observation and Synchronization","score":0.38199999928474426,"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/T12090","display_name":"Language and cultural evolution","score":0.024000000208616257,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5390999913215637},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5087000131607056},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27480000257492065},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.2727000117301941},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.26420000195503235}],"concepts":[{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4307999908924103},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4239000082015991},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.35830000042915344},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757279.3785601","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757279.3785601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.463807612657547,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G6228245218","display_name":"CAREER: Enhancing Adaptability in Multimodal Human-Robot Interaction","funder_award_id":"2441587","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2002827238","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2495266147","https://openalex.org/W2560730294","https://openalex.org/W2962749469","https://openalex.org/W2963446712","https://openalex.org/W2964184826","https://openalex.org/W2990113535","https://openalex.org/W3034758614","https://openalex.org/W3111771376","https://openalex.org/W3133191957","https://openalex.org/W3213454282","https://openalex.org/W4361281660","https://openalex.org/W4390873527","https://openalex.org/W4392633941","https://openalex.org/W4396570834","https://openalex.org/W4399478460","https://openalex.org/W4402727885","https://openalex.org/W4415736163","https://openalex.org/W7133196460"],"related_works":[],"abstract_inverted_index":{"As":[0],"robots":[1,187],"enter":[2],"human":[3,15,190],"workspaces,":[4],"there":[5],"is":[6,27],"a":[7,31,60,75,98,169],"crucial":[8],"need":[9],"for":[10,130],"them":[11,122,158],"to":[12,30,104,126,151,180],"comprehend":[13],"embodied":[14,39,79,106,153,182],"instructions,":[16],"enabling":[17],"intuitive":[18],"and":[19,59,81,91,120,144,172],"fluent":[20],"human-robot":[21],"interaction":[22],"(HRI).":[23],"However,":[24],"accurate":[25],"comprehension":[26,185],"challenging":[28],"due":[29],"lack":[32],"of":[33,56,78,176],"large-scale":[34,76],"datasets":[35,46],"that":[36,146],"capture":[37,152],"natural":[38],"interactions":[40,83,154],"in":[41,88,186],"diverse":[42,86],"HRI":[43],"settings.":[44,93],"Existing":[45],"suffer":[47],"from":[48],"perspective":[49],"bias,":[50],"single-view":[51],"data":[52],"collection,":[53],"inadequate":[54],"coverage":[55],"nonverbal":[57,82],"gestures,":[58],"predominant":[61],"focus":[62],"on":[63,137],"indoor":[64,90],"environments.":[65,191],"To":[66],"address":[67],"these":[68],"issues,":[69],"we":[70,95],"present":[71],"the":[72,174],"Refer360":[73,142,167],"dataset,":[74,143],"dataset":[77],"verbal":[80],"collected":[84],"across":[85],"viewpoints":[87],"both":[89],"outdoor":[92],"Additionally,":[94],"introduce":[96],"MuRes,":[97],"multimodal":[99,148],"guided":[100,177],"residual":[101,178],"module":[102],"designed":[103],"improve":[105],"referring":[107,183],"expression":[108,184],"comprehension.":[109],"MuRes":[110,160],"acts":[111],"as":[112,168],"an":[113],"information":[114],"bottleneck,":[115],"extracting":[116],"salient":[117],"modality-specific":[118],"signals":[119],"reinforcing":[121],"into":[123],"pre-trained":[124],"representations":[125],"form":[127],"complementary":[128],"features":[129],"downstream":[131],"tasks.":[132],"We":[133],"conduct":[134],"extensive":[135],"experiments":[136],"four":[138],"datasets,":[139],"including":[140],"our":[141],"demonstrate":[145],"current":[147],"models":[149],"fail":[150],"comprehensively;":[155],"however,":[156],"augmenting":[157],"with":[159],"consistently":[161],"improves":[162],"performance.":[163],"These":[164],"findings":[165],"establish":[166],"valuable":[170],"benchmark":[171],"exhibit":[173],"potential":[175],"learning":[179],"advance":[181],"operating":[188],"within":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-11T00:00:00"}
