{"id":"https://openalex.org/W4403886146","doi":"https://doi.org/10.1145/3686215.3690153","title":"Levels of Multimodal Interaction","display_name":"Levels of Multimodal Interaction","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403886146","doi":"https://doi.org/10.1145/3686215.3690153"},"language":"en","primary_location":{"id":"doi:10.1145/3686215.3690153","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3686215.3690153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 26th International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"article","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/A5112863282","display_name":"A. K. Sinha","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anoop K. Sinha","raw_affiliation_strings":["Google, United States"],"raw_orcid":"https://orcid.org/0009-0009-9231-603X","affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078443228","display_name":"Chinmay Kulkarni","orcid":"https://orcid.org/0000-0003-4922-6601"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chinmay Kulkarni","raw_affiliation_strings":["Google, United States"],"raw_orcid":"https://orcid.org/0000-0003-4922-6601","affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016503150","display_name":"Alex Olwal","orcid":"https://orcid.org/0000-0001-7772-0530"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Olwal","raw_affiliation_strings":["Google, United States"],"raw_orcid":"https://orcid.org/0000-0001-7772-0530","affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112863282"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.3311,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67212456,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9997000098228455,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T10383","display_name":"Language, Discourse, Communication Strategies","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6262235045433044},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.5832309126853943},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41630783677101135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6262235045433044},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.5832309126853943},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41630783677101135}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3686215.3690153","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3686215.3690153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 26th International Conference on Multimodal Interaction","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":11,"referenced_works":["https://openalex.org/W2061270248","https://openalex.org/W2108729336","https://openalex.org/W2132233302","https://openalex.org/W2135643110","https://openalex.org/W2156897926","https://openalex.org/W2619383789","https://openalex.org/W2619697695","https://openalex.org/W2913305970","https://openalex.org/W3128143783","https://openalex.org/W4390462029","https://openalex.org/W6850321586"],"related_works":["https://openalex.org/W2035104213","https://openalex.org/W2240967841","https://openalex.org/W2791686160","https://openalex.org/W1513257435","https://openalex.org/W2289840258","https://openalex.org/W2503352526","https://openalex.org/W2968405290","https://openalex.org/W2960696728","https://openalex.org/W2114040463","https://openalex.org/W2053633997"],"abstract_inverted_index":{"Large":[0],"Multimodal":[1,35],"Models":[2],"(LMMs)":[3],"like":[4],"OpenAI's":[5],"GPT4o":[6],"and":[7,28,40,70,77],"Google's":[8],"Gemini,":[9],"introduced":[10],"in":[11,19,51],"2024,":[12],"process":[13],"multiple":[14,59],"modalities,":[15],"enabling":[16],"significant":[17],"advances":[18],"multimodal":[20],"interaction.":[21],"Inspired":[22],"by":[23],"frameworks":[24],"for":[25,85],"self-driving":[26],"cars":[27],"AGI,":[29],"this":[30],"paper":[31],"proposes":[32],"\"Levels":[33],"of":[34,58],"Interaction\"":[36],"to":[37,95],"guide":[38],"research":[39],"development.":[41],"The":[42],"four":[43],"levels":[44],"are:":[45],"basic":[46],"multimodality":[47,54],"(0),":[48],"single":[49],"modalities":[50],"turn-taking;":[52],"combined":[53],"(1),":[55],"fused":[56],"interpretation":[57],"modalities;":[60],"humanlike":[61,72],"(2),":[62],"natural":[63],"interaction":[64],"flow":[65],"with":[66,82,97],"additional":[67],"communication":[68],"signals;":[69],"beyond":[71],"(3),":[73],"surpassing":[74],"human":[75],"capabilities":[76],"include":[78],"underlying":[79],"hidden":[80],"signals":[81],"the":[83],"potential":[84],"transformational":[86],"human-AI":[87],"integration.":[88],"LMMs":[89],"have":[90],"progressed":[91],"from":[92],"Level":[93,98],"0":[94],"1,":[96],"2":[99],"next.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
