{"id":"https://openalex.org/W4400647750","doi":"https://doi.org/10.1109/iv55156.2024.10588839","title":"Do You Act Like You Talk? Exploring Pose-based Driver Action Classification with Speech Recognition Networks","display_name":"Do You Act Like You Talk? Exploring Pose-based Driver Action Classification with Speech Recognition Networks","publication_year":2024,"publication_date":"2024-06-02","ids":{"openalex":"https://openalex.org/W4400647750","doi":"https://doi.org/10.1109/iv55156.2024.10588839"},"language":"en","primary_location":{"id":"doi:10.1109/iv55156.2024.10588839","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iv55156.2024.10588839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","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/A5095905891","display_name":"Pablo Pardo-Decimavilla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pablo Pardo-Decimavilla","raw_affiliation_strings":["University of Alcalá (UAH),Electronics Departament,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alcalá (UAH),Electronics Departament,Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077780013","display_name":"Luis M. Bergasa","orcid":"https://orcid.org/0000-0002-0087-3077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luis M. Bergasa","raw_affiliation_strings":["University of Alcalá (UAH),Electronics Departament,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alcalá (UAH),Electronics Departament,Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067490426","display_name":"Santiago Montiel-Mar\u00edn","orcid":"https://orcid.org/0009-0000-5492-0839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santiago Montiel-Mar\u00edn","raw_affiliation_strings":["University of Alcalá (UAH),Electronics Departament,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alcalá (UAH),Electronics Departament,Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044375454","display_name":"Miguel Antunes","orcid":"https://orcid.org/0009-0008-5627-5325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miguel Antunes","raw_affiliation_strings":["University of Alcalá (UAH),Electronics Departament,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alcalá (UAH),Electronics Departament,Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081175757","display_name":"\u00c1ngel Llamazares","orcid":"https://orcid.org/0000-0001-8273-5163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00c1ngel Llamazares","raw_affiliation_strings":["University of Alcalá (UAH),Electronics Departament,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alcalá (UAH),Electronics Departament,Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09131102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"179","issue":null,"first_page":"1395","last_page":"1400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9812999963760376,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9812999963760376,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9368000030517578,"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":0.7559142112731934},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6630730628967285},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6177912354469299},{"id":"https://openalex.org/keywords/speech-act","display_name":"Speech act","score":0.5531972050666809},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.538358747959137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5160176753997803},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.432373970746994},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1260964274406433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559142112731934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6630730628967285},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6177912354469299},{"id":"https://openalex.org/C2984865316","wikidata":"https://www.wikidata.org/wiki/Q25481968","display_name":"Speech act","level":2,"score":0.5531972050666809},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.538358747959137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5160176753997803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.432373970746994},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1260964274406433},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv55156.2024.10588839","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iv55156.2024.10588839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2301363727","https://openalex.org/W2559085405","https://openalex.org/W2606294640","https://openalex.org/W2607707631","https://openalex.org/W2896950454","https://openalex.org/W2963076818","https://openalex.org/W2963820951","https://openalex.org/W2972818416","https://openalex.org/W2990503944","https://openalex.org/W2990892171","https://openalex.org/W2992308087","https://openalex.org/W3007328579","https://openalex.org/W3015537910","https://openalex.org/W3097777922","https://openalex.org/W3117504282","https://openalex.org/W3158114938","https://openalex.org/W4212774754","https://openalex.org/W4281779489","https://openalex.org/W4286285614","https://openalex.org/W4312560592","https://openalex.org/W4385302099","https://openalex.org/W4386275562","https://openalex.org/W4390873156","https://openalex.org/W4390874170","https://openalex.org/W6766978945","https://openalex.org/W6794211498","https://openalex.org/W6803840252","https://openalex.org/W6838276489"],"related_works":["https://openalex.org/W2393335312","https://openalex.org/W3150208086","https://openalex.org/W2376466940","https://openalex.org/W3002287546","https://openalex.org/W2390960669","https://openalex.org/W2374130554","https://openalex.org/W2349303462","https://openalex.org/W2373707372","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"Recognizing":[0],"distractions":[1],"on":[2,81,101],"the":[3,58,61,102,115,121,129],"road":[4],"is":[5,47,79],"crucial":[6],"to":[7,26,97,109],"reduce":[8],"traffic":[9],"accidents.":[10],"Video-based":[11],"networks":[12,136],"are":[13,17,24],"typically":[14],"used,":[15],"but":[16],"limited":[18],"by":[19],"their":[20],"computational":[21],"cost":[22],"and":[23,49,67,120,131],"vulnerable":[25],"viewpoint":[27,51,124],"changes.":[28,125],"In":[29],"this":[30],"paper,":[31],"we":[32,113],"propose":[33],"a":[34,91],"novel":[35],"approach":[36],"for":[37],"pose-based":[38,138],"driver":[39],"action":[40,139],"classification":[41],"using":[42],"speech":[43,86,134],"recognition":[44,87,135],"networks,":[45],"which":[46],"lighter":[48],"more":[50],"invariant":[52],"that":[53],"video-based":[54],"one.":[55],"We":[56,89],"leverage":[57],"similarity":[59],"in":[60,137],"encoding":[62],"of":[63,93,117,123,133],"information":[64,119],"between":[65],"audio":[66],"pose":[68],"data,":[69],"representing":[70],"poses":[71],"as":[72],"key":[73],"points":[74],"over":[75],"time.":[76],"Our":[77,126],"architecture":[78],"based":[80],"Squeezeformer,":[82],"an":[83],"efficient":[84],"attentionbased":[85],"network.":[88],"introduce":[90],"selection":[92],"data":[94],"augmentation":[95],"techniques":[96],"enhance":[98],"generalization.":[99],"Experiments":[100],"Drive&Act":[103],"dataset":[104],"demonstrate":[105],"superior":[106],"performance":[107],"compared":[108],"state-of-the-art":[110],"methods.":[111],"Additionally,":[112],"explore":[114],"integration":[116],"object":[118],"impact":[122],"results":[127],"highlight":[128],"effectiveness":[130],"robustness":[132],"classification.":[140]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}