{"id":"https://openalex.org/W1998891211","doi":"https://doi.org/10.1145/2388676.2388760","title":"Audio-visual robot command recognition","display_name":"Audio-visual robot command recognition","publication_year":2012,"publication_date":"2012-10-22","ids":{"openalex":"https://openalex.org/W1998891211","doi":"https://doi.org/10.1145/2388676.2388760","mag":"1998891211"},"language":"en","primary_location":{"id":"doi:10.1145/2388676.2388760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2388676.2388760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Multimodal interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00768761","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063541182","display_name":"Jordi S\u00e0nchez-Riera","orcid":"https://orcid.org/0000-0002-4803-5742"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jordi Sanchez-Riera","raw_affiliation_strings":["INRIA Rhone Alpes, Montbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rhone Alpes, Montbonnot, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["INRIA Rhone Alpes, Montbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rhone Alpes, Montbonnot, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078307335","display_name":"Radu Horaud","orcid":"https://orcid.org/0000-0001-5232-024X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["INRIA Rhone Alpes, Montbonnor, France","INRIA Rhone Alpes, Montbonnor, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rhone Alpes, Montbonnor, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"INRIA Rhone Alpes, Montbonnor, France#TAB#","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"371","last_page":"378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9902999997138977,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7899739742279053},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6868337988853455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6211493611335754},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5842035412788391},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5597921013832092},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5515652298927307},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5323610305786133},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3536505103111267},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.10336405038833618}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899739742279053},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6868337988853455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6211493611335754},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5842035412788391},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5597921013832092},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5515652298927307},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5323610305786133},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3536505103111267},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.10336405038833618},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2388676.2388760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2388676.2388760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Multimodal interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00768761v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00768761","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dl.acm.org/citation.cfm?doid=2388676.2388760","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00768761v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00768761","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dl.acm.org/citation.cfm?doid=2388676.2388760","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W64067223","https://openalex.org/W1506806321","https://openalex.org/W1603096025","https://openalex.org/W1604034532","https://openalex.org/W1975143133","https://openalex.org/W2011699475","https://openalex.org/W2020163092","https://openalex.org/W2025954386","https://openalex.org/W2054199123","https://openalex.org/W2056197638","https://openalex.org/W2074392550","https://openalex.org/W2107456423","https://openalex.org/W2118440833","https://openalex.org/W2119090229","https://openalex.org/W2130239535","https://openalex.org/W2137492562","https://openalex.org/W2741744871","https://openalex.org/W4206109287","https://openalex.org/W6664090525"],"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/W2120801881","https://openalex.org/W1982853263","https://openalex.org/W1974473538","https://openalex.org/W2020010749","https://openalex.org/W2911691005"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,10,13,36,41,46,53,65,68,96],"problem":[4],"of":[5,12,45,67,82],"audio-visual":[6,59,79],"command":[7],"recognition":[8,80],"in":[9,99],"framework":[11],"D-META":[14],"Grand":[15],"Challenge1.":[16],"Temporal":[17],"and":[18,26,94],"non-temporal":[19],"learning":[20],"models":[21],"are":[22,38],"trained":[23],"on":[24,40,89],"visual":[25],"auditory":[27],"descriptors.":[28],"In":[29],"order":[30],"to":[31,87,91],"set":[32],"a":[33],"proper":[34],"baseline,":[35],"methods":[37],"tested":[39],"\"Robot":[42],"Gestures\"":[43],"scenario":[44],"publicly":[47],"available":[48],"RAVEL":[49],"data":[50],"set,":[51],"following":[52],"leave-one-out":[54],"cross-validation":[55],"strategy.":[56],"The":[57,74],"classification-level":[58],"fusion":[60],"strategy":[61],"allows":[62],"for":[63],"compensating":[64],"errors":[66],"unimodal":[69],"(audio":[70],"or":[71],"vision)":[72],"classifiers.":[73],"obtained":[75],"results":[76],"(an":[77],"average":[78],"rate":[81],"almost":[83],"80%)":[84],"encourage":[85],"us":[86],"investigate":[88],"how":[90],"further":[92],"develop":[93],"improve":[95],"methodology":[97],"described":[98],"this":[100],"paper.":[101]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}