{"id":"https://openalex.org/W2980364600","doi":"https://doi.org/10.1145/3340555.3356093","title":"Multimodal Driver Interaction with Gesture, Gaze and Speech","display_name":"Multimodal Driver Interaction with Gesture, Gaze and Speech","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2980364600","doi":"https://doi.org/10.1145/3340555.3356093","mag":"2980364600"},"language":"en","primary_location":{"id":"doi:10.1145/3340555.3356093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340555.3356093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5055108209","display_name":"Abdul Rafey Aftab","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Abdul Rafey Aftab","raw_affiliation_strings":["Universit\u00e4t des Saarlandes, Germany","Universit?t des Saarlandes, Germany"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t des Saarlandes, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Universit?t des Saarlandes, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055108209"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":1.1859,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.7983987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"487","last_page":"492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8221856355667114},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7671041488647461},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.7039325833320618},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.5837528705596924},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5487396121025085},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.5421460866928101},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.509989857673645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4993600845336914},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49841928482055664},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4932998716831207},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.417856901884079},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3976231515407562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3594047725200653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221856355667114},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7671041488647461},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7039325833320618},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.5837528705596924},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5487396121025085},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.5421460866928101},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.509989857673645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4993600845336914},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49841928482055664},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4932998716831207},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.417856901884079},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3976231515407562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3594047725200653},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3340555.3356093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340555.3356093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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":41,"referenced_works":["https://openalex.org/W197969300","https://openalex.org/W205819775","https://openalex.org/W581956982","https://openalex.org/W1517003397","https://openalex.org/W1524154260","https://openalex.org/W1581457308","https://openalex.org/W1598796236","https://openalex.org/W1628789162","https://openalex.org/W1896788142","https://openalex.org/W1972706598","https://openalex.org/W2041649634","https://openalex.org/W2052101136","https://openalex.org/W2091713044","https://openalex.org/W2113123816","https://openalex.org/W2118185621","https://openalex.org/W2137940226","https://openalex.org/W2138988042","https://openalex.org/W2142624305","https://openalex.org/W2143612262","https://openalex.org/W2155217597","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2184540135","https://openalex.org/W2245388892","https://openalex.org/W2259130772","https://openalex.org/W2293649818","https://openalex.org/W2508491668","https://openalex.org/W2542287130","https://openalex.org/W2567215512","https://openalex.org/W2624162241","https://openalex.org/W2769832462","https://openalex.org/W2782978053","https://openalex.org/W2790400419","https://openalex.org/W2792764867","https://openalex.org/W2892360234","https://openalex.org/W2908619437","https://openalex.org/W2916979304","https://openalex.org/W2964010806","https://openalex.org/W4244097747","https://openalex.org/W4256321336","https://openalex.org/W6677496868"],"related_works":["https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735","https://openalex.org/W2014028898"],"abstract_inverted_index":{"The":[0,119],"ever-growing":[1],"research":[2,52],"in":[3,22,44],"computer":[4],"vision":[5],"has":[6,79],"created":[7],"new":[8],"avenues":[9],"for":[10,37,57,63,99,111,116,130],"user":[11,38],"interaction.":[12],"Speech":[13],"commands":[14],"and":[15,96,139],"gesture":[16,90],"recognition":[17],"are":[18],"already":[19],"being":[20],"applied":[21,71],"various":[23],"touch-based":[24],"inputs.":[25],"It":[26,141],"is,":[27],"therefore,":[28],"foreseeable,":[29],"that":[30,83],"the":[31,41,58,64,100,107,117,131,134,149,154,157],"use":[32,59,86],"of":[33,54,60,67,87,102,133,156],"multimodal":[34,61],"input":[35],"methods":[36,56],"interaction":[39],"is":[40],"next":[42],"phase":[43],"development.":[45],"In":[46],"this":[47],"paper,":[48],"I":[49],"propose":[50],"a":[51,73,88,112],"plan":[53,121],"novel":[55],"inputs":[62],"semantic":[65],"interpretation":[66],"human-computer":[68],"interaction,":[69],"specifically":[70],"to":[72,80,152],"car":[74],"driver.":[75,118,158],"A":[76],"fusion":[77,132,150],"methodology":[78],"be":[81],"designed":[82],"adequately":[84],"makes":[85],"recognized":[89],"(specifically":[91],"finger":[92],"pointing),":[93],"eye":[94],"gaze":[95],"head":[97,138],"pose":[98],"identification":[101],"reference":[103],"objects,":[104],"while":[105],"using":[106],"semantics":[108],"from":[109,146],"speech":[110,147],"natural":[113],"interactive":[114],"environment":[115],"proposed":[120],"includes":[122],"different":[123],"techniques":[124],"based":[125],"on":[126],"artificial":[127],"neural":[128],"networks":[129],"camera-based":[135],"modalities":[136],"(gaze,":[137],"gesture).":[140],"then":[142],"combines":[143],"features":[144],"extracted":[145],"with":[148],"algorithm":[151],"determine":[153],"intent":[155]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
