{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T04:36:02Z","timestamp":1754195762640,"version":"3.37.3"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s11042-023-15254-8","type":"journal-article","created":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T11:45:40Z","timestamp":1684151140000},"page":"2349-2382","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["An empirical framework for detecting speaking modes using ensemble classifier"],"prefix":"10.1007","volume":"83","author":[{"given":"Sadia","family":"Afroze","sequence":"first","affiliation":[]},{"given":"Md. Rajib","family":"Hossain","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8806-708X","authenticated-orcid":false,"given":"Mohammed Moshiul","family":"Hoque","sequence":"additional","affiliation":[]},{"given":"M. Ali Akber","family":"Dewan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,13]]},"reference":[{"key":"15254_CR1","doi-asserted-by":"publisher","first-page":"136243","DOI":"10.1109\/ACCESS.2020.3009898","volume":"8","author":"AH Abdel-Gawad","year":"2020","unstructured":"Abdel-Gawad AH, Said LA, Radwan AG (2020) Optimized edge detection technique for brain tumor detection in mr images. IEEE Access 8:136243\u2013136259","journal-title":"IEEE Access"},{"key":"15254_CR2","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.compbiomed.2017.08.022","volume":"89","author":"UR Acharya","year":"2017","unstructured":"Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adam M, Gertych A, Tan RS (2017) A deep convolutional neural network model to classify heartbeats. Comput Biol Med 89:389\u2013396","journal-title":"Comput Biol Med"},{"key":"15254_CR3","doi-asserted-by":"crossref","unstructured":"Afroze S, Hoque MM (2019) Talking vs non-talking: A vision based approach to detect human speaking mode. In: International conference on electrical, computer and communication engineering. IEEE, pp 1\u20136","DOI":"10.1109\/ECACE.2019.8679311"},{"key":"15254_CR4","doi-asserted-by":"crossref","unstructured":"Afroze S, Hoque MM (2020) Towards lip motion based speaking mode detection using residual neural networks. In: International conference on soft computing and pattern recognition (soCPar), pp 166\u2013175","DOI":"10.1007\/978-3-030-73689-7_17"},{"issue":"18","key":"15254_CR5","doi-asserted-by":"publisher","first-page":"25877","DOI":"10.1007\/s11042-022-12100-1","volume":"81","author":"M Aljabri","year":"2022","unstructured":"Aljabri M, AlAmir M, AlGhamdi M, Abdel-Mottaleb M, Collado-Mesa F (2022) Towards a better understanding of annotation tools for medical imaging: a survey. Multimed Tools Appl 81(18):25877\u201325911. https:\/\/doi.org\/10.1007\/s11042-022-12100-1","journal-title":"Multimed Tools Appl"},{"key":"15254_CR6","doi-asserted-by":"crossref","unstructured":"Ayllon D, Chou T-S, King A, Shen Y (2021) Identification and engagement of passive subjects in multiparty conversations by a humanoid robot. In: Companion of the 2021 ACM\/IEEE international conference on human-robot interaction, pp 535\u2013539","DOI":"10.1145\/3434074.3447229"},{"key":"15254_CR7","unstructured":"Bendris M, Charlet D, Chollet G (2010) Lip activity detection for talking faces classification in tv-content. In: International conference on machine vision, pp 187\u2013190"},{"key":"15254_CR8","doi-asserted-by":"crossref","unstructured":"Bonastre J-F, Anguera X, Sierra GH, Bousquet P-M (2011) Speaker modeling using local binary decisions. In: Conference of the international speech communication association","DOI":"10.21437\/Interspeech.2011-4"},{"issue":"9","key":"15254_CR9","doi-asserted-by":"publisher","first-page":"5329","DOI":"10.1007\/s11042-015-2848-2","volume":"75","author":"E Boutellaa","year":"2016","unstructured":"Boutellaa E, Boulkenafet Z, Komulainen J, Hadid A (2016) Audiovisual synchrony assessment for replay attack detection in talking face biometrics. Multimed Tools Appl 75(9):5329\u20135343","journal-title":"Multimed Tools Appl"},{"key":"15254_CR10","doi-asserted-by":"crossref","unstructured":"Bouvier C, Benoit A, Caplier A, Coulon P-Y (2008) Open or closed mouth state detection: static supervised classification based on log-polar signature. In: International conference on advanced concepts for intelligent vision systems, pp 1093\u20131102. Springer","DOI":"10.1007\/978-3-540-88458-3_99"},{"issue":"1","key":"15254_CR11","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/s11042-021-11077-7","volume":"81","author":"B Breve","year":"2022","unstructured":"Breve B, Cirillo S, Cuofano M, Desiato D (2022) Enhancing spatial perception through sound: mapping human movements into midi. Multimed Tools Appl 81(1):73\u201394. https:\/\/doi.org\/10.1007\/s11042-021-11077-7","journal-title":"Multimed Tools Appl"},{"key":"15254_CR12","doi-asserted-by":"publisher","unstructured":"Breve B, Cirillo S, Desiato D, Cuofano M (2020) Perceiving space through sound: mapping human movements into midi. In: International Distributed Multimedia Systems Conference on Visualization and Visual Languages (DMSVIVA), pp 49\u201356. https:\/\/doi.org\/10.18293\/DMSVIVA20-011","DOI":"10.18293\/DMSVIVA20-011"},{"issue":"5","key":"15254_CR13","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/0895-4356(93)90018-V","volume":"46","author":"T Byrt","year":"1993","unstructured":"Byrt T, Bishop J, Carlin JB (1993) Bias, prevalence and kappa. J Clin Epidemiol 46(5):423\u2013429","journal-title":"J Clin Epidemiol"},{"key":"15254_CR14","doi-asserted-by":"crossref","unstructured":"Chakravarty P, Mirzaei S, Tuytelaars T, Hamme HV (2015) Who\u2019s speaking? audio-supervised classification of active speakers in video. In: Proceedings of the 2015 ACM on international conference on multimodal interaction, pp 87\u201390","DOI":"10.1145\/2818346.2820780"},{"key":"15254_CR15","doi-asserted-by":"publisher","unstructured":"Chang S (ed.) (2020) The 26th International DMS Conference on Visualization and Visual Languages, DMSVIVA 2020, KSIR Virtual Conference Center, USA, July 7-8, 2020. https:\/\/doi.org\/10.18293\/DMSVIVA2020","DOI":"10.18293\/DMSVIVA2020"},{"issue":"3","key":"15254_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"C-C Chang","year":"2011","unstructured":"Chang C-C, Lin C-J (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1\u201327","journal-title":"ACM Trans Intell Syst Technol"},{"key":"15254_CR17","doi-asserted-by":"crossref","unstructured":"Chowdhury DP, Kumari R, Bakshi S, Sahoo MN, Das A (2021) Lip as biometric and beyond: a survey. Multimed Tools Appl, pp 1\u201335","DOI":"10.1007\/s11042-021-11613-5"},{"key":"15254_CR18","doi-asserted-by":"crossref","unstructured":"DeVellis RF (2005) Inter-rater reliability. In: Encyclopedia of social measurement, pp 317\u2013322","DOI":"10.1016\/B0-12-369398-5\/00095-5"},{"key":"15254_CR19","doi-asserted-by":"publisher","first-page":"118727","DOI":"10.1109\/ACCESS.2019.2936663","volume":"7","author":"W Deng","year":"2019","unstructured":"Deng W, Wu R (2019) Real-time driver-drowsiness detection system using facial features. IEEE Access 7:118727\u2013118738","journal-title":"IEEE Access"},{"key":"15254_CR20","doi-asserted-by":"crossref","unstructured":"Dhakate KR, Dash R (2020) Distracted driver detection using stacking ensemble. In: IEEE International Students\u2019 Conference on Electrical, Electronics and Computer Science (SCEECS) , pp 1\u20135. IEEE","DOI":"10.1109\/SCEECS48394.2020.184"},{"key":"15254_CR21","unstructured":"Diaz JFM, Lerasle F, Lionel Pibre F (2021) Isabelle: Audio-video detection of the active speaker in meetings. In: IEEE 25Th international conference on pattern recognition (ICPR)"},{"key":"15254_CR22","doi-asserted-by":"publisher","first-page":"15750","DOI":"10.1109\/ACCESS.2017.2735019","volume":"5","author":"C Du","year":"2017","unstructured":"Du C, Gao S (2017) Image segmentation-based multi-focus image fusion through multi-scale convolutional neural network. IEEE Access 5:15750\u201315761","journal-title":"IEEE Access"},{"key":"15254_CR23","doi-asserted-by":"crossref","unstructured":"Everingham MR, Sivic J, Zisserman A (2006) Hello! my name is... buffy-automatic naming of characters in tv video. In: The british machine vision conference (BMVC)","DOI":"10.5244\/C.20.92"},{"key":"15254_CR24","doi-asserted-by":"publisher","first-page":"101294","DOI":"10.1016\/j.jup.2021.101294","volume":"73","author":"G-F Fan","year":"2021","unstructured":"Fan G-F, Yu M, Dong S-Q, Yeh Y-H, Hong W-C (2021) Forecasting short-term electricity load using hybrid support vector regression with grey catastrophe and random forest modeling. Utilities Policy 73:101294. https:\/\/doi.org\/10.1016\/j.jup.2021.101294","journal-title":"Utilities Policy"},{"key":"15254_CR25","doi-asserted-by":"publisher","first-page":"95197","DOI":"10.1109\/ACCESS.2020.2994811","volume":"8","author":"A Fasanmade","year":"2020","unstructured":"Fasanmade A, He Y, Al-Bayatti AH, Morden JN, Aliyu SO, Alfakeeh AS, Alsayed AO (2020) A fuzzy-logic approach to dynamic bayesian severity level classification of driver distraction using image recognition. IEEE Access 8:95197\u201395207","journal-title":"IEEE Access"},{"key":"15254_CR26","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","volume":"77","author":"J Gu","year":"2018","unstructured":"Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, Liu T, Wang X, Wang G, Cai J et al (2018) Recent advances in convolutional neural networks. Pattern Recogn 77:354\u2013377","journal-title":"Pattern Recogn"},{"key":"15254_CR27","unstructured":"Haider F, Moubayed AS (2012) Towards speaker detection using lips movements for humanmachine multiparty dialogue. In: Swedish Phonetics Conference (FONETIK), pp 117\u2013120. Citeseer"},{"key":"15254_CR28","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"15254_CR29","doi-asserted-by":"crossref","unstructured":"Hossain MR, Afroze S, Siddique N, Hoque MM (2020) Automatic detection of eye cataract using deep convolution neural networks (dcnns). In: Proceedings TENSYMP, pp 1333\u20131338","DOI":"10.1109\/TENSYMP50017.2020.9231045"},{"key":"15254_CR30","doi-asserted-by":"crossref","unstructured":"Huang R, Fan M, Xing Y, Zou Y (2019) Image blur classification and unintentional blur removal, vol 7","DOI":"10.1109\/ACCESS.2019.2932124"},{"key":"15254_CR31","doi-asserted-by":"crossref","unstructured":"Huang H-Y, Lin Y-C (2013) An efficient mouth detection based on face localization and edge projection. Int J Comput Theory Eng 5(3)","DOI":"10.7763\/IJCTE.2013.V5.740"},{"key":"15254_CR32","doi-asserted-by":"crossref","unstructured":"Itoh K, Mizushima M (1997) Environmental noise reduction based on speech\/non-speech identification for hearing aids. In: IEEE International conference on acoustics, speech, and signal processing, vol 1, pp 419\u2013422","DOI":"10.1109\/ICASSP.1997.599662"},{"key":"15254_CR33","doi-asserted-by":"publisher","first-page":"114591","DOI":"10.1016\/j.eswa.2021.114591","volume":"171","author":"R Jahangir","year":"2021","unstructured":"Jahangir R, Teh YW, Nweke HF, Mujtaba G, Al-Garadi MA, Ali I (2021) Speaker identification through artificial intelligence techniques: a comprehensive review and research challenges. Expert Syst Appl 171:114591","journal-title":"Expert Syst Appl"},{"key":"15254_CR34","doi-asserted-by":"publisher","first-page":"64136","DOI":"10.1109\/ACCESS.2019.2917382","volume":"7","author":"Y Ji","year":"2019","unstructured":"Ji Y, Wang S, Zhao Y, Wei J, Lu Y (2019) Fatigue state detection based on multi-index fusion and state recognition network. IEEE Access 7:64136\u201364147","journal-title":"IEEE Access"},{"issue":"4","key":"15254_CR35","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/BF00133570","volume":"1","author":"M Kass","year":"1988","unstructured":"Kass M, Witkin A, Terzopoulos D (1988) Snakes: Active contour models. Int J Comput Vis 1(4):321\u2013331","journal-title":"Int J Comput Vis"},{"issue":"37","key":"15254_CR36","doi-asserted-by":"publisher","first-page":"27039","DOI":"10.1007\/s11042-020-09260-3","volume":"79","author":"Z Kerkaou","year":"2020","unstructured":"Kerkaou Z, Ansari ME (2020) Support vector machines based stereo matching method for advanced driver assistance systems. Multimed Tools Appl 79 (37):27039\u201327055","journal-title":"Multimed Tools Appl"},{"key":"15254_CR37","doi-asserted-by":"crossref","unstructured":"Korshunov P, Halstead M, Castan D, Graciarena M, McLaren M, Burns B, Lawson A, Marcel S (2019) Tampered speaker inconsistency detection with phonetically aware audio-visual features. In: International conference on machine learning","DOI":"10.23919\/EUSIPCO.2018.8553270"},{"issue":"3","key":"15254_CR38","first-page":"148","volume":"10","author":"Z Li","year":"2016","unstructured":"Li Z, Sun G, Zhang F, Jia L, Zheng K, Zhao D (2016) Smartphone-based fatigue detection system using progressive locating method. IET 10 (3):148\u2013156","journal-title":"IET"},{"key":"15254_CR39","doi-asserted-by":"crossref","unstructured":"Li Y, Wang Z, Dai G, Wu S, Yu S, Xie Y (2017) Evaluation of realistic blurring image quality by using a shallow convolutional neural network IEEE International conference on information and automation (ICIA), pp 853\u2013857","DOI":"10.1109\/ICInfA.2017.8079022"},{"key":"15254_CR40","doi-asserted-by":"publisher","first-page":"102723","DOI":"10.1016\/j.jvcir.2019.102723","volume":"71","author":"Z Liu","year":"2020","unstructured":"Liu Z, Peng Y, Hu W (2020) Driver fatigue detection based on deeply-learned facial expression representation. J Vis Commun Image Represent 71:102723","journal-title":"J Vis Commun Image Represent"},{"key":"15254_CR41","doi-asserted-by":"publisher","first-page":"32194","DOI":"10.1007\/s10489-019-01623-0","volume":"50","author":"F Liu","year":"2020","unstructured":"Liu F, Song Q, Jin G (2020) The classification and denoising of image noise based on deep neural networks. Appl Intell 50:32194\u20132207","journal-title":"Appl Intell"},{"key":"15254_CR42","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1007\/s10489-019-01603-4","volume":"50","author":"M Lu","year":"2020","unstructured":"Lu M, Hu Y, Lu X (2020) Driver action recognition using deformable and dilated faster r-cnn with optimized region proposals. Appl Intell 50:1100\u20131111","journal-title":"Appl Intell"},{"key":"15254_CR43","doi-asserted-by":"crossref","unstructured":"Milborrow S, Nicolls F (2008) Locating facial features with an extended active shape model. In: European conference on computer vision, pp 504\u2013513. Springer","DOI":"10.1007\/978-3-540-88693-8_37"},{"key":"15254_CR44","doi-asserted-by":"publisher","first-page":"33240","DOI":"10.1109\/ACCESS.2019.2902579","volume":"7","author":"M Mittal","year":"2019","unstructured":"Mittal M, Verma A, Kaur I, Kaur B, Sharma M, Mohan LG, Roy S, Kim T-H (2019) An efficient edge detection approach to provide better edge connectivity for image analysis. IEEE Access 7:33240\u201333255","journal-title":"IEEE Access"},{"key":"15254_CR45","doi-asserted-by":"crossref","unstructured":"Nainan S, Kulkarni V (2018) Lip tracking using deformable models and geometric approaches. In: Information and communication technology for intelligent systems, pp 655\u2013663","DOI":"10.1007\/978-981-13-1742-2_65"},{"key":"15254_CR46","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1007\/s10489-014-0629-7","volume":"42","author":"K Noda","year":"2015","unstructured":"Noda K, Yamaguchi Y, Nakadai K, Okuno HG, Ogata T (2015) Audio-visual speech recognition using deep learning. Appl Intell 42:722\u2013737","journal-title":"Appl Intell"},{"key":"15254_CR47","unstructured":"Omidyeganeh M, Shirmohammadi S (2014) Behnooshhariri: Yawdd: A yawning detection dataset. In: Proceedings of the 5th ACM multimedia systems conference, pp 24\u201328"},{"key":"15254_CR48","doi-asserted-by":"crossref","unstructured":"Ou C, Zhao Q, Karray F, Khatib AE (2019) Design of an end-to-end dual mode driver distraction detection system. In: International conference on image analysis and recognition, pp 199\u2013207. Springer","DOI":"10.1007\/978-3-030-27272-2_17"},{"key":"15254_CR49","doi-asserted-by":"crossref","unstructured":"Punitha A, Kalaiselvi MG, Sivaprakash A (2014) Driver fatigue monitoring system based on eye state analysis. In: International conference on circuits, power and computing technologies, pp 1405\u20131408","DOI":"10.1109\/ICCPCT.2014.7055020"},{"issue":"9","key":"15254_CR50","first-page":"1","volume":"6","author":"J Ramirez","year":"2007","unstructured":"Ramirez J, G\u00f3rriz JM, Segura JC (2007) Voice activity detection. fundamentals and speech recognition system robustness. Robust Speech Recog Understand 6(9):1\u201322","journal-title":"Robust Speech Recog Understand"},{"key":"15254_CR51","doi-asserted-by":"publisher","first-page":"61904","DOI":"10.1109\/ACCESS.2019.2914373","volume":"7","author":"M Ramzan","year":"2019","unstructured":"Ramzan M, Khan HU, Awan SM, Ismail A, Ilyas M, Mahmood A (2019) A survey on state-of-the-art drowsiness detection techniques. IEEE Access 7:61904\u201361919","journal-title":"IEEE Access"},{"key":"15254_CR52","doi-asserted-by":"crossref","unstructured":"Richter V, Carlmeyer B, Lier F, zu Borgsen SM, Schlangen D, Kummert F, Wachsmuth S, Wrede B (2016) Are you talking to me? improving the robustness of dialogue systems in a multi party hri scenario by incorporating gaze direction and lip movement of attendees. In: Proceedings of the 4th International conference on human agent interaction, pp 43\u201350","DOI":"10.1145\/2974804.2974823"},{"issue":"20","key":"15254_CR53","doi-asserted-by":"publisher","first-page":"28367","DOI":"10.1007\/s11042-022-12928-7","volume":"81","author":"G Rohith","year":"2022","unstructured":"Rohith G, Kumar LS (2022) Design of deep convolution neural networks for categorical signature classification of raw panchromatic satellite images. Multimed Tools Appl 81 (20):28367\u201328404. https:\/\/doi.org\/10.1007\/s11042-022-12928-7","journal-title":"Multimed Tools Appl"},{"key":"15254_CR54","doi-asserted-by":"crossref","unstructured":"Rongben W, Lie G, Bingliang T, Lisheng J (2004) Monitoring mouth movement for driver fatigue or distraction with one camera. In: International IEEE conference on intelligent transportation systems, pp 314\u2013319","DOI":"10.1109\/ITSC.2004.1398917"},{"issue":"6088","key":"15254_CR55","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(6088):533\u2013536","journal-title":"Nature"},{"issue":"3","key":"15254_CR56","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1504\/IJBET.2014.064651","volume":"15","author":"D Saraswathi","year":"2014","unstructured":"Saraswathi D, Srinivasan E (2014) An ensemble approach to diagnose breast cancer using fully complex-valued relaxation neural network classifier. Int J Biomed Eng Technol 15(3):243","journal-title":"Int J Biomed Eng Technol"},{"key":"15254_CR57","doi-asserted-by":"publisher","first-page":"12491","DOI":"10.1109\/ACCESS.2020.2963960","volume":"8","author":"BK Savas\u0307","year":"2020","unstructured":"Savas\u0307 BK, Becerikli Y (2020) Real time driver fatigue detection system based on multi-task connn. IEEE Access 8:12491\u201312498","journal-title":"IEEE Access"},{"key":"15254_CR58","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., lecun, Y. (eds.) international conference on learning representations (ICLR)"},{"key":"15254_CR59","doi-asserted-by":"crossref","unstructured":"Song Y, Luo Y, Lin J (2011) Detection of movements of head and mouth to provide computer access for disabled. In: International conference on technologies and applications of artificial intelligence, pp 223\u2013226","DOI":"10.1109\/TAAI.2011.46"},{"key":"15254_CR60","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"15254_CR61","unstructured":"Takeuchi S, Hashiba T, Tamura S, Hayamizu S (2009) Voice activity detection based on fusion of audio and visual information. International Conference on Auditory-Visual Speech Processing (AVSP), pp 151\u2013154"},{"key":"15254_CR62","doi-asserted-by":"crossref","unstructured":"Tawalbeh S, Hammad M, AL-Smadi M (2020) KEIS@JUST at SemEval-2020 task 12: Identifying multilingual offensive tweets using weighted ensemble and fine-tuned BERT. In: Proceedings of the 14th workshop on semantic evaluation, pp 2035\u20132044","DOI":"10.18653\/v1\/2020.semeval-1.269"},{"key":"15254_CR63","doi-asserted-by":"crossref","unstructured":"Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: IEEE Computer society conference on computer vision and pattern recognition, vol 1","DOI":"10.1109\/CVPR.2001.990517"},{"key":"15254_CR64","doi-asserted-by":"crossref","unstructured":"Xia D, Zheng Y, Bai Y, Yan X, Hu Y, Li Y, Li H (2022) A parallel grid-search-based svm optimization algorithm on spark for passenger hotspot prediction. Multimed Tools Appl, pp 1\u201327","DOI":"10.1007\/s11042-022-12077-x"},{"issue":"19","key":"15254_CR65","doi-asserted-by":"publisher","first-page":"27523","DOI":"10.1007\/s11042-022-12077-x","volume":"81","author":"D Xia","year":"2022","unstructured":"Xia D, Zheng Y, Bai Y, Yan X, Hu Y, Li Y, Li H (2022) A parallel grid-search-based svm optimization algorithm on spark for passenger hotspot prediction. Multimed Tools Appl 81(19):27523\u201327549. https:\/\/doi.org\/10.1007\/s11042-022-12077-x","journal-title":"Multimed Tools Appl"},{"key":"15254_CR66","doi-asserted-by":"crossref","unstructured":"Xie W, Nagrani A, Chung JS, Zisserman A (2019) Utterance-level aggregation for speaker recognition in the wild. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 5791\u20135795. IEEE","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"15254_CR67","doi-asserted-by":"crossref","unstructured":"Yuen PC, Lai J-H, Huang Q (2004) Mouth state estimation in mobile computing environment. In: IEEE International conference on automatic face and gesture recognition, pp 705\u2013710. IEEE","DOI":"10.1109\/AFGR.2004.1301617"},{"issue":"10","key":"15254_CR68","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang K, Zhang Z, Li Z, Qiao Y (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett 23(10):1499\u20131503","journal-title":"IEEE Signal Process Lett"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15254-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15254-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15254-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T10:32:34Z","timestamp":1729420354000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15254-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,13]]},"references-count":68,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["15254"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15254-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,5,13]]},"assertion":[{"value":"22 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}