{"id":"https://openalex.org/W4387446934","doi":"https://doi.org/10.1145/3610661.3616548","title":"A Methodology for Evaluating Multimodal Referring Expression Generation for Embodied Virtual Agents","display_name":"A Methodology for Evaluating Multimodal Referring Expression Generation for Embodied Virtual Agents","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4387446934","doi":"https://doi.org/10.1145/3610661.3616548"},"language":"en","primary_location":{"id":"doi:10.1145/3610661.3616548","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610661.3616548","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610661.3616548","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Cconference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3610661.3616548","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062380880","display_name":"Nada Alalyani","orcid":"https://orcid.org/0000-0002-9253-416X"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nada Alalyani","raw_affiliation_strings":["Situated Grounding and Natural Language (SIGNAL) Lab, Department of Computer Science, Colorado State University, USA"],"raw_orcid":"https://orcid.org/0000-0002-9253-416X","affiliations":[{"raw_affiliation_string":"Situated Grounding and Natural Language (SIGNAL) Lab, Department of Computer Science, Colorado State University, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021596300","display_name":"Nikhil Krishnaswamy","orcid":"https://orcid.org/0000-0001-7878-7227"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Krishnaswamy","raw_affiliation_strings":["Situated Grounding and Natural Language (SIGNAL) Lab, Department of Computer Science, Colorado State University, USA"],"raw_orcid":"https://orcid.org/0000-0001-7878-7227","affiliations":[{"raw_affiliation_string":"Situated Grounding and Natural Language (SIGNAL) Lab, Department of Computer Science, Colorado State University, USA","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I92446798"],"apc_list":null,"apc_paid":null,"fwci":0.3639,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67067987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"164","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.998199999332428,"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/embodied-cognition","display_name":"Embodied cognition","score":0.8200559616088867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6420695781707764},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5319982171058655},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40983909368515015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32195696234703064},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06142657995223999}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8200559616088867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6420695781707764},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5319982171058655},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40983909368515015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32195696234703064},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06142657995223999}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610661.3616548","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610661.3616548","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610661.3616548","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Cconference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3610661.3616548","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610661.3616548","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610661.3616548","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Cconference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387446934.pdf","grobid_xml":"https://content.openalex.org/works/W4387446934.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1598140581","https://openalex.org/W1773149199","https://openalex.org/W1956340063","https://openalex.org/W1985319867","https://openalex.org/W1987869189","https://openalex.org/W1989386832","https://openalex.org/W2104045164","https://openalex.org/W2123442489","https://openalex.org/W2134102463","https://openalex.org/W2138232041","https://openalex.org/W2150692719","https://openalex.org/W2150824314","https://openalex.org/W2166656616","https://openalex.org/W2175017070","https://openalex.org/W2489434015","https://openalex.org/W2558809543","https://openalex.org/W2600463316","https://openalex.org/W2731466267","https://openalex.org/W2892181857","https://openalex.org/W2913958523","https://openalex.org/W2930957955","https://openalex.org/W2942109448","https://openalex.org/W2963109634","https://openalex.org/W2963341956","https://openalex.org/W2998012869","https://openalex.org/W2999433551","https://openalex.org/W3034723486","https://openalex.org/W3093841559","https://openalex.org/W3201415876","https://openalex.org/W4205161929","https://openalex.org/W4247615137","https://openalex.org/W4297009332","https://openalex.org/W4391156274","https://openalex.org/W6802039548"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970"],"abstract_inverted_index":{"Robust":[0],"use":[1,86,164],"of":[2,80,114,163],"definite":[3],"descriptions":[4],"in":[5,73,112],"a":[6,39,62,74,85],"situated":[7],"space":[8],"often":[9],"involves":[10],"recourse":[11],"to":[12,23,29,50,64,69,96,130,151],"both":[13,30],"verbal":[14,36],"and":[15,32,35,57,109,119,137,160],"non-verbal":[16,34],"modalities.":[17],"For":[18],"IVAs,":[19],"virtual":[20],"agents":[21],"designed":[22],"interact":[24],"with":[25,103,167],"humans,":[26],"the":[27,66,78,104,133,139,141,146,149,168],"ability":[28,150],"recognize":[31],"generate":[33,70],"behavior":[37],"is":[38,48],"critical":[40],"capability.":[41],"To":[42],"assess":[43],"how":[44],"well":[45],"an":[46,93],"IVA":[47],"able":[49],"deploy":[51],"multimodal":[52,81],"behaviors,":[53],"including":[54],"language,":[55,155],"gesture,":[56,157],"facial":[58],"expressions,":[59],"we":[60],"propose":[61],"methodology":[63],"evaluate":[65],"agent\u2019s":[67],"capacity":[68],"object":[71,140],"references":[72,111],"situational":[75],"context,":[76],"using":[77,117,154],"domain":[79],"referring":[82,99],"expressions":[83,100],"as":[84],"case.":[87],"Our":[88],"contributions":[89],"include:":[90],"1)":[91],"developing":[92],"embodied":[94],"platform":[95],"collect":[97],"human":[98,108,142,147,161],"while":[101,165],"communicating":[102],"IVA.":[105],"2)":[106],"comparing":[107],"machine-generated":[110],"terms":[113],"evaluable":[115],"properties":[116],"subjective":[118],"objective":[120],"metrics.":[121],"3)":[122],"reporting":[123],"preliminary":[124],"results":[125],"from":[126],"trials":[127],"that":[128],"aimed":[129],"check":[131],"whether":[132],"agent":[134],"can":[135],"retrieve":[136],"disambiguate":[138],"referred":[143],"to,":[144],"if":[145],"has":[148],"correct":[152],"misunderstanding":[153],"deictic":[156],"or":[158],"both;":[159],"ease":[162],"interacting":[166],"agent.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
