{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T06:17:33Z","timestamp":1778912253420,"version":"3.51.4"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T00:00:00Z","timestamp":1689120000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T00:00:00Z","timestamp":1689120000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203012"],"award-info":[{"award-number":["62203012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871123"],"award-info":[{"award-number":["61871123"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61901221"],"award-info":[{"award-number":["61901221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Anhui Polytechnic University of Technology Introduced Talent Research Startup Fund","award":["2022YQQ009"],"award-info":[{"award-number":["2022YQQ009"]}]},{"name":"Youth Foundation of Anhui Polytechnic University","award":["Xjky2022039"],"award-info":[{"award-number":["Xjky2022039"]}]},{"name":"Open Research Fund of AnHui Key Laboratory of Detection Technology and Energy Saving Devices","award":["JCKJ2022A07"],"award-info":[{"award-number":["JCKJ2022A07"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-15777-0","type":"journal-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T15:02:15Z","timestamp":1689174135000},"page":"18281-18307","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["ESDAR-net: towards high-accuracy and real-time driver action recognition for embedded systems"],"prefix":"10.1007","volume":"83","author":[{"given":"Yaocong","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Shuai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5996-503X","authenticated-orcid":false,"given":"Huicheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoyang","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingqi","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7707-7538","authenticated-orcid":false,"given":"Xiaobo","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,12]]},"reference":[{"key":"15777_CR1","unstructured":"Abouelnaga Y, Eraqi HM, Moustafa MN (2017) Real-time distracted driver posture classification. arXiv preprint arXiv:1706.09498"},{"key":"15777_CR2","doi-asserted-by":"crossref","unstructured":"Ahmed ST, Basha SM, Ramachandran M, Daneshmand M, Gandomi AH (2023) An edge-ai enabled autonomous connected ambulance route resource recommendation protocol (aca-r3) for ehealth in smart cities. IEEE Internet of Things Journal","DOI":"10.1109\/JIOT.2023.3243235"},{"issue":"10","key":"15777_CR3","doi-asserted-by":"publisher","first-page":"19 743\u2013","DOI":"10.1109\/TITS.2021.3134222","volume":"23","author":"M Ahmed","year":"2021","unstructured":"Ahmed M, Masood S, Ahmad M, Abd El-Latif AA (2021) Intelligent driver drowsiness detection for traffic safety based on multi cnn deep model and facial subsampling. IEEE Trans Intell Transp Syst 23(10):19 743--19 752","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"15777_CR4","doi-asserted-by":"crossref","unstructured":"Arnab A, Dehghani M, Heigold G, Sun C, Lu\u010di\u0107 M, Schmid C (2021) Vivit: A video vision transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6836\u20136846","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"15777_CR5","doi-asserted-by":"crossref","unstructured":"Basha SM, Ahmed ST, Iyengar NCSN, Caytiles RD (2021) Inter-locking dependency evaluation schema based on block-chain enabled federated transfer learning for autonomous vehicular systems. In: 2021 Second International Conference on Innovative Technology Convergence (CITC), pp 46\u201351. IEEE","DOI":"10.1109\/CITC54365.2021.00016"},{"key":"15777_CR6","doi-asserted-by":"publisher","unstructured":"Boujemaa KS, Berrada I, Fardousse K, Naggar O, Bourzeix F (2021) Toward road safety recommender systems: Formal concepts and technical basics. IEEE Trans Intell Transp Syst, pp 1\u201320. https:\/\/doi.org\/10.1109\/TITS.2021.3052771","DOI":"10.1109\/TITS.2021.3052771"},{"issue":"6","key":"15777_CR7","doi-asserted-by":"publisher","first-page":"3577","DOI":"10.1109\/TITS.2020.2995768","volume":"22","author":"M Cao","year":"2021","unstructured":"Cao M, Zheng L, Jia W, Liu X (2021) Joint 3d reconstruction and object tracking for traffic video analysis under iov environment. IEEE Trans Intell Transp Syst 22(6):3577\u20133591. https:\/\/doi.org\/10.1109\/TITS.2020.2995768","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"15777_CR8","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"15777_CR9","doi-asserted-by":"crossref","unstructured":"Chaudhry R, Ravichandran A, Hager G, Vidal R (2009) Histograms of oriented optical flow and binet-cauchy kernels on nonlinear dynamical systems for the recognition of human actions. In: 2009 IEEE Conf Comput Vis Pattern Recognit, pp 1932\u20131939. IEEE","DOI":"10.1109\/CVPR.2009.5206821"},{"issue":"11","key":"15777_CR10","doi-asserted-by":"publisher","first-page":"7232","DOI":"10.1109\/TITS.2020.3004655","volume":"22","author":"LW Chen","year":"2021","unstructured":"Chen LW, Chen HM (2021) Driver behavior monitoring and warning with dangerous driving detection based on the internet of vehicles. IEEE Trans Intell Transp Syst 22(11):7232\u20137241. https:\/\/doi.org\/10.1109\/TITS.2020.3004655","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"4","key":"15777_CR11","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence 40(4):834\u2013848. https:\/\/doi.org\/10.1109\/TPAMI.2017.2699184","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"15777_CR12","unstructured":"Chen G, Choi W, Yu X, Han T, Chandraker M (2017) Learning efficient object detection models with knowledge distillation. In: Advances in Neural Information Processing Systems, vol 30. Curran Associates, Inc"},{"key":"15777_CR13","doi-asserted-by":"crossref","unstructured":"Chen J, Ho CM (2022) Mm-vit: Multi-modal video transformer for compressed video action recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 1910\u20131921","DOI":"10.1109\/WACV51458.2022.00086"},{"key":"15777_CR14","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne\u00a0Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 2625\u20132634","DOI":"10.21236\/ADA623249"},{"key":"15777_CR15","doi-asserted-by":"publisher","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) Centernet: Keypoint triplets for object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp 6568\u20136577. https:\/\/doi.org\/10.1109\/ICCV.2019.00667","DOI":"10.1109\/ICCV.2019.00667"},{"key":"15777_CR16","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J, He K (2019) Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"15777_CR17","unstructured":"Feichtenhofer C, Pinz A, Wildes R (2016) Spatiotemporal residual networks for video action recognition. In: Lee DD, Sugiyama M, Luxburg UV, Guyon I, Garnett R (eds) Advances in Neural Information Processing Systems 29:3468\u20133476. Curran Associates, Inc. http:\/\/papers.nips.cc\/paper\/6433-spatiotemporal-residual-networks-for-video-action-recognition.pdf"},{"key":"15777_CR18","doi-asserted-by":"publisher","unstructured":"Feichtenhofer C, Pinz A, Wildes RP (2017) Spatiotemporal multiplier networks for video action recognition. In: 2017 IEEE Conf Comput Vis Pattern Recognit (CVPR), pp 7445\u20137454. https:\/\/doi.org\/10.1109\/CVPR.2017.787","DOI":"10.1109\/CVPR.2017.787"},{"key":"15777_CR19","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)","DOI":"10.1109\/CVPR.2016.213"},{"key":"15777_CR20","doi-asserted-by":"publisher","first-page":"5363","DOI":"10.1109\/TIP.2021.3083113","volume":"30","author":"Y Feng","year":"2021","unstructured":"Feng Y, Sun X, Diao W, Li J, Gao X (2021) Double similarity distillation for semantic image segmentation. IEEE Trans Image Process 30:5363\u20135376. https:\/\/doi.org\/10.1109\/TIP.2021.3083113","journal-title":"IEEE Trans Image Process"},{"key":"15777_CR21","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"15777_CR22","unstructured":"Hinton G, Vinyals O, Dean J et al (2015) Distilling the knowledge in a neural network. arXiv preprint 2(7). arXiv:1503.02531"},{"key":"15777_CR23","unstructured":"Hoang Ngan\u00a0Le T, Zheng Y, Zhu C, Luu K, Savvides M (2016) Multiple scale faster-rcnn approach to driver\u2019s cell-phone usage and hands on steering wheel detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 46\u201353"},{"key":"15777_CR24","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint hyperimagehttp:\/\/arxiv.org\/abs\/1704.04861arXiv:1704.04861"},{"key":"15777_CR25","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-018-0994-z","author":"Y Hu","year":"2018","unstructured":"Hu Y, Lu M, Lu X (2018) Driving behaviour recognition from still images by using multi-stream fusion cnn. Mach Vis Appl. https:\/\/doi.org\/10.1007\/s00138-018-0994-z","journal-title":"Mach Vis Appl"},{"key":"15777_CR26","doi-asserted-by":"publisher","unstructured":"Hu Y, Lu M, Lu X (2020) Feature refinement for image-based driver action recognition via multi-scale attention convolutional neural network. Signal Process Image Commun 81(115):697. https:\/\/doi.org\/10.1016\/j.image.2019.115697 . http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0923 596519300980","DOI":"10.1016\/j.image.2019.115697"},{"issue":"3","key":"15777_CR27","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/s00530-020-00724-y","volume":"27","author":"Y Hu","year":"2021","unstructured":"Hu Y, Lu M, Xie C, Lu X (2021) Video-based driver action recognition via hybrid spatial-temporal deep learning framework. Multimedia Systems 27(3):483\u2013501","journal-title":"Multimedia Systems"},{"key":"15777_CR28","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"15777_CR29","doi-asserted-by":"publisher","unstructured":"Hu Y, Lu M, Lu X (2018) Spatial-temporal fusion convolutional neural network for simulated driving behavior recognition. In: 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), pp 1271\u20131277. https:\/\/doi.org\/10.1109\/ICARCV.2018.8581201","DOI":"10.1109\/ICARCV.2018.8581201"},{"key":"15777_CR30","unstructured":"Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size. arXiv preprint arXiv:1602.07360"},{"key":"15777_CR31","doi-asserted-by":"crossref","unstructured":"Joe Yue-Hei Ng, Hausknecht M, Vijayanarasimhan S, Vinyals O, Monga R, Toderici G (2015) Beyond short snippets: Deep networks for video classification. In: 2015 IEEE Conf Comput Vis Pattern Recognit (CVPR), pp 4694\u20134702","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"15777_CR32","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)","DOI":"10.1109\/CVPR.2014.223"},{"key":"15777_CR33","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-3-319-59876-5_2","volume-title":"Image Analysis and Recognition","author":"A Koesdwiady","year":"2017","unstructured":"Koesdwiady A, Bedawi SM, Ou C, Karray F (2017) End-to-end deep learning for driver distraction recognition. In: Karray F, Campilho A, Cheriet F (eds) Image Analysis and Recognition. Springer International Publishing, Cham, pp 11\u201318"},{"key":"15777_CR34","doi-asserted-by":"crossref","unstructured":"Kopuklu O, Kose N, Gunduz A, Rigoll G (2019) Resource efficient 3d convolutional neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp 0\u20130","DOI":"10.1109\/ICCVW.2019.00240"},{"key":"15777_CR35","doi-asserted-by":"crossref","unstructured":"Korbar B, Tran D, Torresani L (2019) Scsampler: Sampling salient clips from video for efficient action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","DOI":"10.1109\/ICCV.2019.00633"},{"key":"15777_CR36","volume-title":"Advances in Neural Information Processing Systems","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in Neural Information Processing Systems, vol 25. Curran Associates Inc"},{"key":"15777_CR37","volume-title":"High Performance Computing in Science and Engineering 12:571\u2013582","author":"H Kuehne","year":"2013","unstructured":"Kuehne H, Jhuang H, Stiefelhagen R, Serre T (2013) Hmdb51: A large video database for human motion recognition. In: Nagel WE, Kr\u00f6ner DH, Resch MM (eds) High Performance Computing in Science and Engineering 12:571\u2013582. Springer, Berlin Heidelberg, Berlin, Heidelberg"},{"key":"15777_CR38","doi-asserted-by":"publisher","unstructured":"Liu H, Liu W, Chi Z, Wang Y, Yu Y, Chen J, Jin T (2022) Fast human pose estimation in compressed videos. IEEE Transactions on Multimedia, pp 1\u20131. https:\/\/doi.org\/10.1109\/TMM.2022.3141888","DOI":"10.1109\/TMM.2022.3141888"},{"key":"15777_CR39","doi-asserted-by":"publisher","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: 2015 IEEE Conf Comput Vis Pattern Recognit (CVPR), pp 3431\u20133440. https:\/\/doi.org\/10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"103","key":"15777_CR40","first-page":"800","volume":"90","author":"M Lu","year":"2019","unstructured":"Lu M, Hu Y, Lu X (2019) Dilated light-head r-cnn using tri-center loss for driving behavior recognition. Image Vis Comput 90(103):800","journal-title":"Image Vis Comput"},{"issue":"4","key":"15777_CR41","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(4):1100\u20131111","journal-title":"Appl Intell"},{"key":"15777_CR42","doi-asserted-by":"crossref","unstructured":"Maji S, Bourdev L, Malik J (2011) Action recognition from a distributed representation of pose and appearance. In: CVPR 2011, pp 3177\u20133184. IEEE","DOI":"10.1109\/CVPR.2011.5995631"},{"key":"15777_CR43","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.patrec.2017.12.023","volume":"139","author":"S Masood","year":"2020","unstructured":"Masood S, Rai A, Aggarwal A, Doja MN, Ahmad M (2020) Detecting distraction of drivers using convolutional neural network. Pattern Recogn Lett 139:79\u201385","journal-title":"Pattern Recogn Lett"},{"key":"15777_CR44","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng HT, Sun J (2018) Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp 116\u2013131","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"15777_CR45","unstructured":"Mehta S, Rastegari M (2022) Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer. In: International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=vh-0sUt8HlG"},{"key":"15777_CR46","doi-asserted-by":"crossref","unstructured":"Moslemi N, Azmi R, Soryani M (2019) Driver distraction recognition using 3d convolutional neural networks. In: 2019 4th International Conference on Pattern Recognition and Image Analysis (IPRIA), pp 145\u2013151. IEEE","DOI":"10.1109\/PRIA.2019.8786012"},{"key":"15777_CR47","unstructured":"National Bureau of Statistics (2021) Traffic accident report. https:\/\/data.stats.gov.cn"},{"issue":"3","key":"15777_CR48","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1109\/TCSVT.2018.2808685","volume":"29","author":"Y Peng","year":"2019","unstructured":"Peng Y, Zhao Y, Zhang J (2019) Two-stream collaborative learning with spatial-temporal attention for video classification. IEEE Transactions on Circuits and Systems for Video Technology 29(3):773\u2013786. https:\/\/doi.org\/10.1109\/TCSVT.2018.2808685","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"15777_CR49","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"15777_CR50","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28"},{"key":"15777_CR51","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"15777_CR52","doi-asserted-by":"crossref","unstructured":"Shou Z, Lin X, Kalantidis Y, Sevilla-Lara L, Rohrbach M, Chang SF, Yan Z (2019) Dmc-net: Generating discriminative motion cues for fast compressed video action recognition. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit, pp 1268\u20131277","DOI":"10.1109\/CVPR.2019.00136"},{"key":"15777_CR53","volume-title":"Advances in Neural Information Processing Systems 27","author":"K Simonyan","year":"2014","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Ghahramani Z, Welling M, Cortes C, Lawrence N, Weinberger KQ (eds) Advances in Neural Information Processing Systems 27. Curran Associates Inc"},{"key":"15777_CR54","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"15777_CR55","unstructured":"Soomro K, Zamir AR, Shah M (2012) UCF101: A dataset of 101 human actions classes from videos in the wild. CoRR abs\/1212.0402. http:\/\/arxiv.org\/abs\/1212.0402"},{"issue":"146","key":"15777_CR56","first-page":"10","volume":"2006","author":"S Tomar","year":"2006","unstructured":"Tomar S (2006) Converting video formats with ffmpeg. Linux journal 2006(146):10","journal-title":"Linux journal"},{"key":"15777_CR57","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"15777_CR58","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (2018) A closer look at spatiotemporal convolutions for action recognition. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 6450\u20136459","DOI":"10.1109\/CVPR.2018.00675"},{"issue":"12","key":"15777_CR59","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1109\/TCSVT.2016.2576761","volume":"27","author":"P Wang","year":"2017","unstructured":"Wang P, Cao Y, Shen C, Liu L, Shen HT (2017) Temporal pyramid pooling-based convolutional neural network for action recognition. IEEE Transactions on Circuits and Systems for Video Technology 27(12):2613\u20132622. https:\/\/doi.org\/10.1109\/TCSVT.2016.2576761","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"15777_CR60","doi-asserted-by":"crossref","unstructured":"Wang H, Schmid C (2013) Action recognition with improved trajectories. In: Proceedings of the IEEE international conference on computer vision, pp 3551\u20133558","DOI":"10.1109\/ICCV.2013.441"},{"key":"15777_CR61","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Gool LV (2016) Temporal segment networks: Towards good practices for deep action recognition. In: European conference on computer vision, Springer, pp 20\u201336","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"15777_CR62","doi-asserted-by":"crossref","unstructured":"Wu CY, Zaheer M, Hu H, Manmatha R, Smola AJ, Kr\u00e4henb\u00fchl P (2018) Compressed video action recognition. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 6026\u20136035","DOI":"10.1109\/CVPR.2018.00631"},{"key":"15777_CR63","doi-asserted-by":"publisher","unstructured":"Yan C, Coenen F, Zhang BL (2014) Driving posture recognition by joint application of motion history image and pyramid histogram of oriented gradients. In: Advances in Mechatronics, Automation and Applied Information Technologies, Advanced Materials Research 846:1102\u20131105. Trans Tech Publications. https:\/\/doi.org\/10.4028\/www.scientific.net\/AMR.846-847.1102","DOI":"10.4028\/www.scientific.net\/AMR.846-847.1102"},{"key":"15777_CR64","doi-asserted-by":"publisher","unstructured":"Yang J, Liu J, Han R, Wu J (2021) Generating and restoring private face images for internet of vehicles based on semantic features and adversarial examples. IEEE Trans Intell Transp Syst, pp 1\u201311. https:\/\/doi.org\/10.1109\/TITS.2021.3102266","DOI":"10.1109\/TITS.2021.3102266"},{"key":"15777_CR65","doi-asserted-by":"publisher","unstructured":"Yan C, Zhang B, Coenen F (2015) Driving posture recognition by convolutional neural networks. In: 2015 11th International Conference on Natural Computation (ICNC), pp 680\u2013685. https:\/\/doi.org\/10.1109\/ICNC.2015.7378072","DOI":"10.1109\/ICNC.2015.7378072"},{"key":"15777_CR66","doi-asserted-by":"crossref","unstructured":"Yu Z, Yu J, Fan J, Tao D (2017) Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the IEEE international conference on computer vision, pp 1821\u20131830","DOI":"10.1109\/ICCV.2017.202"},{"key":"15777_CR67","doi-asserted-by":"publisher","first-page":"191,138\u2013","DOI":"10.1109\/ACCESS.2020.3032344","volume":"8","author":"C Zhang","year":"2020","unstructured":"Zhang C, Li R, Kim W, Yoon D, Patras P (2020) Driver behavior recognition via interwoven deep convolutional neural nets with multi-stream inputs. Ieee Access 8:191,138--191,151","journal-title":"Ieee Access"},{"key":"15777_CR68","doi-asserted-by":"crossref","unstructured":"Zhang B, Wang L, Wang Z, Qiao Y, Wang H (2016) Real-time action recognition with enhanced motion vector cnns. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 2718\u20132726","DOI":"10.1109\/CVPR.2016.297"},{"key":"15777_CR69","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"},{"key":"15777_CR70","doi-asserted-by":"publisher","unstructured":"Zhao C, Gao Y, He J, Lian J (2012) Recognition of driving postures by multiwavelet transform and multilayer perceptron classifier. Eng Appl Artif Intell 25(8):1677\u20131686. https:\/\/doi.org\/10.1016\/j.engappai.2012.09.018 . http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0952 197612002564","DOI":"10.1016\/j.engappai.2012.09.018"},{"issue":"2","key":"15777_CR71","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1049\/iet-its.2011.0116","volume":"6","author":"CH Zhao","year":"2012","unstructured":"Zhao CH, Zhang BL, He J, Lian J (2012) Recognition of driving postures by contourlet transform and random forests. IET Intell Transp Syst 6(2):161\u2013168. https:\/\/doi.org\/10.1049\/iet-its.2011.0116","journal-title":"IET Intell Transp Syst"},{"key":"15777_CR72","doi-asserted-by":"publisher","unstructured":"Zhao CH, Zhang BL, Zhang XZ, Zhao SQ, Li HX (2013) Recognition of driving postures by combined features and random subspace ensemble of multilayer perceptron classifiers. Neural Comput & Applic 22(1):175\u2013184. https:\/\/doi.org\/10.1007\/s00521-012-1057-4","DOI":"10.1007\/s00521-012-1057-4"},{"key":"15777_CR73","doi-asserted-by":"publisher","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: 2017 IEEE Conf Comput Vis Pattern Recognit (CVPR), pp 6230\u20136239.https:\/\/doi.org\/10.1109\/CVPR.2017.660","DOI":"10.1109\/CVPR.2017.660"},{"key":"15777_CR74","doi-asserted-by":"publisher","unstructured":"Zhao C, Zhang B, Lian J, He J, Lin T, Zhang X (2011) Classification of driving postures by support vector machines. In: 2011 Sixth International Conference on Image and Graphics, pp 926\u2013930. https:\/\/doi.org\/10.1109\/ICIG.2011.184","DOI":"10.1109\/ICIG.2011.184"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15777-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15777-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15777-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T08:28:42Z","timestamp":1706689722000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15777-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,12]]},"references-count":74,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["15777"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15777-0","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,12]]},"assertion":[{"value":"19 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 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":"There is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}