{"id":"https://openalex.org/W4320060446","doi":"https://doi.org/10.1145/3536221.3557037","title":"MIDriveSafely: Multimodal Interaction for Drive Safely","display_name":"MIDriveSafely: Multimodal Interaction for Drive Safely","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4320060446","doi":"https://doi.org/10.1145/3536221.3557037"},"language":"en","primary_location":{"id":"doi:10.1145/3536221.3557037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3536221.3557037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal 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/A5013493484","display_name":"Denis Ivanko","orcid":"https://orcid.org/0000-0003-0412-7765"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Denis Ivanko","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation"],"raw_orcid":"https://orcid.org/0000-0003-0412-7765","affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016499776","display_name":"Alexey Kashevnik","orcid":"https://orcid.org/0000-0001-6503-1447"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Kashevnik","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation"],"raw_orcid":"https://orcid.org/0000-0001-6503-1447","affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008249311","display_name":"Dmitry Ryumin","orcid":"https://orcid.org/0000-0002-7935-0569"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry Ryumin","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation"],"raw_orcid":"https://orcid.org/0000-0002-7935-0569","affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079074073","display_name":"Andrey Kitenko","orcid":"https://orcid.org/0000-0002-4178-8485"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey Kitenko","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation"],"raw_orcid":"https://orcid.org/0000-0002-4178-8485","affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036332146","display_name":"Alexandr Axyonov","orcid":"https://orcid.org/0000-0002-7479-2851"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexandr Axyonov","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation"],"raw_orcid":"https://orcid.org/0000-0002-7479-2851","affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015710362","display_name":"Igor Lashkov","orcid":"https://orcid.org/0000-0001-6418-4660"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Igor Lashkov","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation"],"raw_orcid":"https://orcid.org/0000-0001-6418-4660","affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032870944","display_name":"Alexey Karpov","orcid":"https://orcid.org/0000-0003-3424-652X"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Karpov","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation"],"raw_orcid":"https://orcid.org/0000-0003-3424-652X","affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory (SMIL), St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), Russian Federation","institution_ids":["https://openalex.org/I1313323035"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1313323035"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"733","last_page":"735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11373","display_name":"Sleep and Work-Related Fatigue","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T11373","display_name":"Sleep and Work-Related Fatigue","score":0.9983000159263611,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.996999979019165,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.6794075965881348},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.6436884999275208},{"id":"https://openalex.org/keywords/voice-command-device","display_name":"Voice command device","score":0.578904390335083},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.5752214789390564},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5282365679740906},{"id":"https://openalex.org/keywords/mobile-phone","display_name":"Mobile phone","score":0.510365903377533},{"id":"https://openalex.org/keywords/entertainment","display_name":"Entertainment","score":0.47613289952278137},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.46707016229629517},{"id":"https://openalex.org/keywords/audio-feedback","display_name":"Audio feedback","score":0.4408213794231415},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.42529284954071045},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4126625955104828},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3568081855773926},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3030783534049988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19398117065429688},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16395515203475952},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1455899477005005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794075965881348},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.6436884999275208},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.578904390335083},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.5752214789390564},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5282365679740906},{"id":"https://openalex.org/C2777421447","wikidata":"https://www.wikidata.org/wiki/Q17517","display_name":"Mobile phone","level":2,"score":0.510365903377533},{"id":"https://openalex.org/C512170562","wikidata":"https://www.wikidata.org/wiki/Q173799","display_name":"Entertainment","level":2,"score":0.47613289952278137},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.46707016229629517},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.4408213794231415},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.42529284954071045},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4126625955104828},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3568081855773926},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3030783534049988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19398117065429688},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16395515203475952},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1455899477005005},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3536221.3557037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3536221.3557037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2889178707","https://openalex.org/W2980364600","https://openalex.org/W2997089994","https://openalex.org/W3008517613","https://openalex.org/W3014095462","https://openalex.org/W3093679471","https://openalex.org/W3128764679","https://openalex.org/W3206138552","https://openalex.org/W4200386182"],"related_works":["https://openalex.org/W2068964259","https://openalex.org/W2013013717","https://openalex.org/W66256988","https://openalex.org/W4302857920","https://openalex.org/W1987340722","https://openalex.org/W199123384","https://openalex.org/W2739856905","https://openalex.org/W4239305747","https://openalex.org/W4205486898","https://openalex.org/W2166331011"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,21,38,56,81,158,171],"novel":[6],"multimodal":[7,125,148],"interaction":[8],"application":[9,23],"to":[10,58,77,100,109,155,165],"help":[11],"car":[12],"drivers":[13,167],"and":[14,121,168],"increase":[15],"their":[16],"road":[17],"safety.":[18],"MIDriveSafely":[19,113,140,152],"is":[20,96,134],"mobile":[22],"that":[24],"provides":[25],"the":[26,59,130,163,166],"following":[27],"functions:":[28],"(1)":[29],"detect":[30],"dangerous":[31,137],"situations":[32],"based":[33,67],"on":[34,68],"video":[35],"information":[36],"from":[37],"smartphone":[39,82],"front-facing":[40],"camera,":[41],"such":[42,86],"as":[43,87],"drowsiness/sleepiness,":[44],"phone":[45],"usage":[46],"while":[47],"driving,":[48],"eating,":[49],"smoking,":[50],"unfastened":[51],"seat":[52],"belt,":[53],"etc.;":[54],"gives":[55],"feedback":[57,164],"driver":[60,144],"(2)":[61],"provide":[62,73],"entertainment":[63],"(e.g.":[64],"rock-paper-scissors":[65],"game,":[66],"automatic":[69],"speech":[70,117],"recognition),":[71],"(3)":[72],"voice":[74],"control":[75],"capabilities":[76],"navigation/multimedia":[78],"systems":[79,85],"of":[80],"(potentially":[83],"vehicle":[84],"lighting":[88],"conditions/climate":[89],"control).":[90],"Speech":[91],"recognition":[92,118],"in":[93,157],"driving":[94],"conditions":[95],"highly":[97],"challenging":[98],"due":[99],"acoustic":[101],"noises,":[102],"active":[103],"head":[104],"turns,":[105],"pose":[106],"variations,":[107],"distance":[108],"recording":[110],"devices,":[111],"etc.":[112],"incorporates":[114],"driver's":[115],"audio-visual":[116],"(DAVIS)":[119],"system":[120,133],"uses":[122],"it":[123],"for":[124,136],"interaction.":[126],"Along":[127],"with":[128],"this,":[129],"original":[131],"DriveSafely":[132],"used":[135],"state":[138],"detection.":[139],"improves":[141],"upon":[142],"existing":[143],"monitoring":[145],"applications":[146],"using":[147],"(mainly":[149],"audio-visual)":[150],"information.":[151],"motivates":[153],"people":[154],"drive":[156],"safer":[159],"manner":[160],"by":[161,169],"providing":[162],"creating":[170],"fun":[172],"user":[173],"experience.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
