{"id":"https://openalex.org/W4399418467","doi":"https://doi.org/10.1145/3652583.3657618","title":"YawnNet: A Visual-Centric Approach for Yawning Detection","display_name":"YawnNet: A Visual-Centric Approach for Yawning Detection","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418467","doi":"https://doi.org/10.1145/3652583.3657618"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3657618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657618","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657618","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657618","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ruoxi Sun","orcid":"https://orcid.org/0009-0002-5180-2954"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruoxi Sun","raw_affiliation_strings":["School of Future Science and Engineering, Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-5180-2954","affiliations":[{"raw_affiliation_string":"School of Future Science and Engineering, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099043579","display_name":"Xinyu Yang","orcid":"https://orcid.org/0009-0009-8319-4851"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Yang","raw_affiliation_strings":["School of Future Science and Engineering, Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-8319-4851","affiliations":[{"raw_affiliation_string":"School of Future Science and Engineering, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077424950","display_name":"C. Stella Qian","orcid":"https://orcid.org/0009-0001-9632-0433"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Qian","raw_affiliation_strings":["School of Future Science and Engineering, Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-9632-0433","affiliations":[{"raw_affiliation_string":"School of Future Science and Engineering, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058983421","display_name":"Chenyu Zhu","orcid":"https://orcid.org/0009-0000-6240-9985"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Zhu","raw_affiliation_strings":["School of Future Science and Engineering, Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-6240-9985","affiliations":[{"raw_affiliation_string":"School of Future Science and Engineering, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514608","display_name":"Wei Sui","orcid":"https://orcid.org/0009-0005-5182-5621"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Sui","raw_affiliation_strings":["Horizon Robotics, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-5182-5621","affiliations":[{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052763223","display_name":"Zeyd Boukhers","orcid":"https://orcid.org/0000-0001-9778-9164"},"institutions":[{"id":"https://openalex.org/I4210110507","display_name":"Fraunhofer Institute for Applied Information Technology","ror":"https://ror.org/01ak24c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210110507","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zeyd Boukhers","raw_affiliation_strings":["Fraunhofer Institute for Applied Information Technology &amp; University Hospital of Cologne, Sankt Augustin, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9778-9164","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Applied Information Technology &amp; University Hospital of Cologne, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210110507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037082005","display_name":"Cong Yang","orcid":"https://orcid.org/0000-0002-8314-0935"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Yang","raw_affiliation_strings":["School of Future Science and Engineering, Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8314-0935","affiliations":[{"raw_affiliation_string":"School of Future Science and Engineering, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":0.6865,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68275434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1140","last_page":"1144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9944999814033508,"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":0.9944999814033508,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9904000163078308,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9623000025749207,"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":0.7706253528594971},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7502660751342773},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.7022976279258728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6461685299873352},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5088303685188293},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5083786845207214},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.505277693271637},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.47898030281066895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4046397805213928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3332785964012146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706253528594971},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7502660751342773},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7022976279258728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6461685299873352},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5088303685188293},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5083786845207214},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.505277693271637},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.47898030281066895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4046397805213928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3332785964012146},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3652583.3657618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657618","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657618","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:null:publica/475605","is_oa":true,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/475605","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.1145/3652583.3657618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657618","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657618","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.4399999976158142,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418467.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2031527075","https://openalex.org/W2052842045","https://openalex.org/W2094726855","https://openalex.org/W2101956459","https://openalex.org/W2117666185","https://openalex.org/W2135365681","https://openalex.org/W2785509179","https://openalex.org/W2805556738","https://openalex.org/W2913033828","https://openalex.org/W3138516171","https://openalex.org/W4312503329","https://openalex.org/W4320801554"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W2281134365","https://openalex.org/W4310746709","https://openalex.org/W4385574037","https://openalex.org/W4386075645","https://openalex.org/W3134175397"],"abstract_inverted_index":{"Yawning":[0],"detection":[1,53],"is":[2],"actively":[3],"used":[4],"in":[5,30,139],"multimedia":[6],"applications":[7],"such":[8],"as":[9],"driver":[10],"fatigue":[11],"assessment":[12],"and":[13,19,36,41,58,72,113,118,134,146,148,153],"status":[14],"monitoring.":[15],"However,":[16],"the":[17,76,100,109,122],"accuracy":[18,107],"robustness":[20,140],"of":[21,102],"existing":[22],"yawning":[23,52],"detectors":[24],"are":[25],"limited":[26],"due":[27],"to":[28,90,127],"variations":[29],"environments":[31],"(especially":[32],"lights),":[33],"facial":[34],"expressions,":[35],"confusion":[37,142],"behaviours":[38],"(e.g.,":[39],"talking":[40],"eating).":[42],"This":[43],"paper":[44],"introduces":[45],"a":[46,65,82,136],"transformer-based":[47],"method,":[48],"YawnNet,":[49],"for":[50],"accurate":[51],"by":[54,116],"leveraging":[55],"spatial-temporal":[56],"encoding":[57],"local":[59,93],"cues.":[60,94],"In":[61],"particular,":[62],"YawnNet":[63],"contains":[64],"data":[66],"processing":[67],"stage":[68],"with":[69],"temporal":[70],"downsampling":[71],"cube":[73],"embedding":[74],"on":[75,87,121,131,141],"input":[77],"sequence.":[78],"Moreover,":[79],"it":[80],"includes":[81],"Swin-Transformer":[83],"block":[84],"that":[85],"operates":[86],"fine-grained":[88],"patches":[89],"uncover":[91],"short-range":[92],"Through":[95],"comprehensive":[96],"experiments,":[97],"we":[98],"demonstrate":[99],"advantages":[101],"YawnNet:":[103],"(1)":[104],"significantly":[105],"higher":[106],"than":[108],"state-of-the-art":[110],"Dense-LSTM":[111],"(precision":[112],"recall":[114],"increased":[115],"2.3%":[117],"4.2%,":[119],"respectively)":[120],"FatigueView":[123],"dataset,":[124],"(2)":[125],"close":[126],"real-time":[128],"(30":[129],"FPS":[130],"RTX":[132],"3090),":[133],"(3)":[135],"marked":[137],"improvement":[138],"behaviours,":[143],"invariance":[144],"(resolution":[145],"orientation)":[147],"complex":[149],"scenarios":[150],"(occlusion,":[151],"over-":[152],"underexpose).":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
