{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T22:16:45Z","timestamp":1781734605276,"version":"3.54.5"},"reference-count":178,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T00:00:00Z","timestamp":1744675200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T00:00:00Z","timestamp":1744675200000},"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":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s13735-025-00363-x","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T10:45:51Z","timestamp":1744713951000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep multimodal learning for time series analysis in social computing: a survey"],"prefix":"10.1007","volume":"14","author":[{"given":"Chao","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yakun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianzhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaize","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guandong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongwen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,15]]},"reference":[{"key":"363_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107280","volume":"93","author":"S Nayak","year":"2021","unstructured":"Nayak S, Nagesh B, Routray A, Sarma M (2021) A human\u2013computer interaction framework for emotion recognition through time-series thermal video sequences. Comput Electr Eng 93:107280","journal-title":"Comput Electr Eng"},{"issue":"6","key":"363_CR2","doi-asserted-by":"publisher","first-page":"1660","DOI":"10.1109\/TCSS.2022.3156792","volume":"9","author":"Q Yu","year":"2022","unstructured":"Yu Q, Sun L (2022) LPClass: lightweight personalized sensor data classification in computational social systems. IEEE Trans Comput Soc Syst 9(6):1660\u20131670","journal-title":"IEEE Trans Comput Soc Syst"},{"issue":"4","key":"363_CR3","doi-asserted-by":"publisher","first-page":"1951","DOI":"10.1109\/TCSS.2022.3219781","volume":"10","author":"E Kafeza","year":"2022","unstructured":"Kafeza E, Rompolas G, Kyriazidis S, Makris C (2022) Time-series clustering for determining behavioral-based brand loyalty of users across social media. IEEE Trans Comput Soc Syst 10(4):1951\u20131965","journal-title":"IEEE Trans Comput Soc Syst"},{"issue":"6","key":"363_CR4","doi-asserted-by":"publisher","first-page":"172988142097608","DOI":"10.1177\/1729881420976082","volume":"17","author":"L Xia","year":"2020","unstructured":"Xia L, Chen G, Xu X, Cui J, Gao Y (2020) Audiovisual speech recognition: a review and forecast. Int J Adv Robot Syst 17(6):1729881420976082","journal-title":"Int J Adv Robot Syst"},{"issue":"9","key":"363_CR5","doi-asserted-by":"publisher","first-page":"1635","DOI":"10.1109\/JPROC.2015.2459017","volume":"103","author":"AK Katsaggelos","year":"2015","unstructured":"Katsaggelos AK, Bahaadini S, Molina R (2015) Audiovisual fusion: challenges and new approaches. Proc IEEE 103(9):1635\u20131653","journal-title":"Proc IEEE"},{"key":"363_CR6","doi-asserted-by":"crossref","unstructured":"Ekambaram V, Manglik K, Mukherjee S, Sajja SSK, Dwivedi S, Raykar V (2020) Attention based multi-modal new product sales time-series forecasting. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery and data mining, pp 3110\u20133118","DOI":"10.1145\/3394486.3403362"},{"key":"363_CR7","doi-asserted-by":"crossref","unstructured":"Wang J, Yang C, Guo Z, Li X, Wang W (2023) An end-to-end mandarin audio-visual speech recognition model with a feature enhancement module. In: 2023 IEEE international conference on systems, man, and cybernetics (SMC). IEEE, pp 572\u2013577","DOI":"10.1109\/SMC53992.2023.10394108"},{"key":"363_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2020.108971","volume":"348","author":"R Yan","year":"2021","unstructured":"Yan R, Li F, Zhou DD, Ristaniemi T, Cong F (2021) Automatic sleep scoring: a deep learning architecture for multi-modality time series. J Neurosci Methods 348:108971","journal-title":"J Neurosci Methods"},{"issue":"9","key":"363_CR9","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.1109\/JPROC.2015.2460697","volume":"103","author":"D Lahat","year":"2015","unstructured":"Lahat D, Adali T, Jutten C (2015) Multimodal data fusion: an overview of methods, challenges, and prospects. Proc IEEE 103(9):1449\u20131477","journal-title":"Proc IEEE"},{"issue":"12","key":"363_CR10","doi-asserted-by":"publisher","first-page":"8717","DOI":"10.1109\/TPAMI.2018.2889052","volume":"44","author":"T Afouras","year":"2018","unstructured":"Afouras T, Chung JS, Senior A, Vinyals O, Zisserman A (2018) Deep audio-visual speech recognition. IEEE Trans Pattern Anal Mach Intell 44(12):8717\u20138727","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"363_CR11","doi-asserted-by":"crossref","unstructured":"Liu Z, Tang H, Amini A, Yang X, Mao H, Rus D.L, Han S (2023) Bevfusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: 2023 IEEE international conference on robotics and automation (ICRA). IEEE, pp 2774\u20132781","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"363_CR12","doi-asserted-by":"crossref","unstructured":"Wang C, Ma C, Zhu M, Yang X (2021) Pointaugmenting: cross-modal augmentation for 3D object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11794\u201311803","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"363_CR13","doi-asserted-by":"crossref","unstructured":"Wu D, Shao L (2014) Multimodal dynamic networks for gesture recognition. In: Proceedings of the 22nd ACM international conference on multimedia, pp 945\u2013948","DOI":"10.1145\/2647868.2654969"},{"key":"363_CR14","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The kitti vision benchmark suite. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 3354\u20133361","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"363_CR15","doi-asserted-by":"crossref","unstructured":"Jiang P, Osteen P, Wigness M, Saripalli S (2021) Rellis-3d dataset: data, benchmarks and analysis. In: 2021 IEEE international conference on robotics and automation (ICRA). IEEE, pp 1110\u20131116","DOI":"10.1109\/ICRA48506.2021.9561251"},{"key":"363_CR16","doi-asserted-by":"crossref","unstructured":"Suarez J, Murphy RR (2012) Hand gesture recognition with depth images: a review. In: 2012 IEEE RO-MAN: the 21st IEEE international symposium on robot and human interactive communication. IEEE, pp 411\u2013417","DOI":"10.1109\/ROMAN.2012.6343787"},{"key":"363_CR17","first-page":"10421","volume":"35","author":"T Liang","year":"2022","unstructured":"Liang T, Xie H, Yu K, Xia Z, Lin Z, Wang Y, Tang T, Wang B, Tang Z (2022) Bevfusion: a simple and robust lidar-camera fusion framework. Advances in neural information processing systems 35:10421\u201310434","journal-title":"Advances in neural information processing systems"},{"key":"363_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101819","volume":"97","author":"Z Chen","year":"2023","unstructured":"Chen Z, Ma M, Li T, Wang H, Li C (2023) Long sequence time-series forecasting with deep learning: a survey. Inf Fusion 97:101819. https:\/\/doi.org\/10.1016\/j.inffus.2023.101819","journal-title":"Inf Fusion"},{"key":"363_CR19","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1007\/s10618-016-0483-9","volume":"31","author":"A Bagnall","year":"2017","unstructured":"Bagnall A, Lines J, Bostrom A, Large J, Keogh E (2017) The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min Knowl Discov 31:606\u2013660","journal-title":"Data Min Knowl Discov"},{"key":"363_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47578-3_1","volume-title":"An introduction to outlier analysis","author":"CC Aggarwal","year":"2017","unstructured":"Aggarwal CC, Aggarwal CC (2017) An introduction to outlier analysis. Springer, Berlin"},{"issue":"6","key":"363_CR21","doi-asserted-by":"publisher","first-page":"3159","DOI":"10.1109\/TCSS.2022.3219825","volume":"10","author":"C Lu","year":"2022","unstructured":"Lu C, Zheng W, Lian H, Zong Y, Tang C, Li S, Zhao Y (2022) Speech emotion recognition via an attentive time-frequency neural network. IEEE Trans Comput Soc Syst 10(6):3159\u20133168","journal-title":"IEEE Trans Comput Soc Syst"},{"issue":"5","key":"363_CR22","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1109\/TCSS.2021.3073964","volume":"8","author":"P Ray","year":"2021","unstructured":"Ray P, Ganguli B, Chakrabarti A (2021) A hybrid approach of Bayesian structural time series with LSTM to identify the influence of news sentiment on short-term forecasting of stock price. IEEE Trans Comput Soc Syst 8(5):1153\u20131162","journal-title":"IEEE Trans Comput Soc Syst"},{"issue":"3","key":"363_CR23","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TII.2015.2411226","volume":"11","author":"B Liu","year":"2015","unstructured":"Liu B, Li J, Chen C, Tan W, Chen Q, Zhou M (2015) Efficient motif discovery for large-scale time series in healthcare. IEEE Trans Ind Inform 11(3):583\u2013590","journal-title":"IEEE Trans Ind Inform"},{"key":"363_CR24","unstructured":"Tang W, Long G, Liu L, Zhou T, Blumenstein M, Jiang J (2021) Omni-scale CNNs: a simple and effective kernel size configuration for time series classification. In: International conference on learning representations"},{"issue":"6","key":"363_CR25","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","volume":"34","author":"H Ismail Fawaz","year":"2020","unstructured":"Ismail Fawaz H, Lucas B, Forestier G, Pelletier C, Schmidt DF, Weber J, Webb GI, Idoumghar L, Muller P-A, Petitjean F (2020) Inceptiontime: finding alexnet for time series classification. Data Min Knowl Discov 34(6):1936\u20131962","journal-title":"Data Min Knowl Discov"},{"issue":"8","key":"363_CR26","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"363_CR27","doi-asserted-by":"crossref","unstructured":"Cho K, Van\u00a0Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation. arXiv preprint arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"key":"363_CR28","doi-asserted-by":"crossref","unstructured":"Chowdhury R.R, Zhang X, Shang J, Gupta R.K, Hong D (2022) Tarnet: task-aware reconstruction for time-series transformer. In: Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, pp 212\u2013220","DOI":"10.1145\/3534678.3539329"},{"key":"363_CR29","doi-asserted-by":"crossref","unstructured":"Zerveas G, Jayaraman S, Patel D, Bhamidipaty A, Eickhoff C (2021) A transformer-based framework for multivariate time series representation learning. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery and data mining, pp 2114\u20132124","DOI":"10.1145\/3447548.3467401"},{"key":"363_CR30","doi-asserted-by":"crossref","unstructured":"Yue Z, Wang Y, Duan J, Yang T, Huang C, Tong Y, Xu B (2021) Ts2Vec: towards universal representation of time series. arXiv preprint arXiv:2106.10466","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"363_CR31","doi-asserted-by":"crossref","unstructured":"Eldele E, Ragab M, Chen Z, Wu M, Kwoh C.K, Li X, Guan C (2021) Time-series representation learning via temporal and contextual contrasting. In: Proceedings of the thirtieth international joint conference on artificial intelligence, IJCAI-21. International joint conferences on artificial intelligence organization, pp 2352\u20132359","DOI":"10.24963\/ijcai.2021\/324"},{"key":"363_CR32","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.neunet.2019.04.014","volume":"116","author":"F Karim","year":"2019","unstructured":"Karim F, Majumdar S, Darabi H, Harford S (2019) Multivariate LSTM-FCNs for time series classification. Neural Netw 116:237\u2013245","journal-title":"Neural Netw"},{"key":"363_CR33","unstructured":"Wu H, Hu T, Liu Y, Zhou H, Wang J, Long M (2023) TimesNet: temporal 2D-variation modeling for general time series analysis. In: International conference on learning representations"},{"key":"363_CR34","unstructured":"Nie Y, Nguyen N.H, Sinthong P, Kalagnanam J (2022) A time series is worth 64 words: long-term forecasting with transformers. arXiv preprint arXiv:2211.14730"},{"key":"363_CR35","doi-asserted-by":"crossref","unstructured":"Zeng A, Chen M, Zhang L, Xu Q (2023) Are transformers effective for time series forecasting? In: Proceedings of the AAAI conference on artificial intelligence, vol 37, pp 11121\u201311128","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"363_CR36","unstructured":"Zhou T, Ma Z, Wen Q, Wang X, Sun L, Jin R (2022) FEDformer: frequency enhanced decomposed transformer for long-term series forecasting. In: International conference on machine learning. PMLR, pp 27268\u201327286"},{"issue":"6","key":"363_CR37","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","volume":"34","author":"D Ramachandram","year":"2017","unstructured":"Ramachandram D, Taylor GW (2017) Deep multimodal learning: a survey on recent advances and trends. IEEE Signal Process Mag 34(6):96\u2013108","journal-title":"IEEE Signal Process Mag"},{"key":"363_CR38","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58948-6_3","volume-title":"Innovative learning environments in STEM higher education: opportunities, challenges, and looking forward","author":"B Bouchey","year":"2021","unstructured":"Bouchey B, Castek J, Thygeson J (2021) Multimodal learning. In: Ryoo J, Winkelmann K (eds) Innovative learning environments in STEM higher education: opportunities, challenges, and looking forward. Springer, Cham, pp 35\u201354"},{"key":"363_CR39","doi-asserted-by":"publisher","first-page":"63373","DOI":"10.1109\/ACCESS.2019.2916887","volume":"7","author":"W Guo","year":"2019","unstructured":"Guo W, Wang J, Wang S (2019) Deep multimodal representation learning: a survey. IEEE Access 7:63373\u201363394","journal-title":"IEEE Access"},{"key":"363_CR40","doi-asserted-by":"crossref","unstructured":"Zhang S-F, Zhai J-H, Xie B-J, Zhan Y, Wang X (2019) Multimodal representation learning: advances, trends and challenges. In: 2019 international conference on machine learning and cybernetics (ICMLC). IEEE, pp 1\u20136","DOI":"10.1109\/ICMLC48188.2019.8949228"},{"issue":"3","key":"363_CR41","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1109\/JSTSP.2020.2987728","volume":"14","author":"C Zhang","year":"2020","unstructured":"Zhang C, Yang Z, He X, Deng L (2020) Multimodal intelligence: representation learning, information fusion, and applications. IEEE J Sel Top Signal Process 14(3):478\u2013493","journal-title":"IEEE J Sel Top Signal Process"},{"key":"363_CR42","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-1600-9","volume-title":"Representation learning for natural language processing","author":"Z Liu","year":"2023","unstructured":"Liu Z, Lin Y, Sun M (2023) Representation learning for natural language processing. Springer, Berlin"},{"key":"363_CR43","doi-asserted-by":"crossref","unstructured":"Qian R, Meng T, Gong B, Yang M-H, Wang H, Belongie S, Cui Y (2021) Spatiotemporal contrastive video representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6964\u20136974","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"363_CR44","doi-asserted-by":"crossref","unstructured":"Won M, Chun S, Nieto O, Serrc X (2020) Data-driven harmonic filters for audio representation learning. In: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 536\u2013540","DOI":"10.1109\/ICASSP40776.2020.9053669"},{"issue":"DB1","key":"363_CR45","first-page":"1","volume":"2021","author":"PP Liang","year":"2021","unstructured":"Liang PP, Lyu Y, Fan X, Wu Z, Cheng Y, Wu J, Chen L, Wu P, Lee MA, Zhu Y et al (2021) Multibench: multiscale benchmarks for multimodal representation learning. Adv Neural Inf Process Syst 2021(DB1):1","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"363_CR46","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis T, Ahuja C, Morency L-P (2018) Multimodal machine learning: a survey and taxonomy. IEEE Trans Pattern Anal Mach Intell 41(2):423\u2013443","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"363_CR47","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.patrec.2013.07.003","volume":"36","author":"M Turk","year":"2014","unstructured":"Turk M (2014) Multimodal interaction: a review. Pattern Recogn Lett 36:189\u2013195","journal-title":"Pattern Recogn Lett"},{"issue":"9","key":"363_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3649447","volume":"56","author":"F Zhao","year":"2024","unstructured":"Zhao F, Zhang C, Geng B (2024) Deep multimodal data fusion. ACM Comput Surv 56(9):1\u201336","journal-title":"ACM Comput Surv"},{"key":"363_CR49","doi-asserted-by":"crossref","unstructured":"Ye Y, Xie Y, Zhang J, Chen Z, Wu Q, Xia Y (2024) Continual self-supervised learning: towards universal multi-modal medical data representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11114\u201311124","DOI":"10.1109\/CVPR52733.2024.01057"},{"key":"363_CR50","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.inffus.2021.12.003","volume":"81","author":"A Rahate","year":"2022","unstructured":"Rahate A, Walambe R, Ramanna S, Kotecha K (2022) Multimodal co-learning: challenges, applications with datasets, recent advances and future directions. Inf Fusion 81:203\u2013239","journal-title":"Inf Fusion"},{"key":"363_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107024","volume":"97","author":"BK Iwana","year":"2020","unstructured":"Iwana BK, Uchida S (2020) Time series classification using local distance-based features in multi-modal fusion networks. Pattern Recogn 97:107024","journal-title":"Pattern Recogn"},{"key":"363_CR52","unstructured":"Wang Z, Oates T (2015) Encoding time series as images for visual inspection and classification using tiled convolutional neural networks. In: Workshops at the twenty-ninth AAAI conference on artificial intelligence"},{"key":"363_CR53","doi-asserted-by":"crossref","unstructured":"Ferraro A, Galli A, Moscato V, Sperl\u00ed G (2020) A novel approach for predictive maintenance combining GAF encoding strategies and deep networks. In: 2020 IEEE 6th international conference on dependability in sensor, cloud and big data systems and application (DependSys). IEEE, pp 127\u2013132","DOI":"10.1109\/DependSys51298.2020.00027"},{"key":"363_CR54","doi-asserted-by":"crossref","unstructured":"Jiang H, Liu L, Lian C (2022) Multi-modal fusion transformer for multivariate time series classification. In: 2022 14th international conference on advanced computational intelligence (ICACI). IEEE, pp 284\u2013288","DOI":"10.1109\/ICACI55529.2022.9837525"},{"key":"363_CR55","unstructured":"Wu H, Hu T, Liu Y, Zhou H, Wang J, Long M (2022) TimesNet: Temporal 2D-variation modeling for general time series analysis. In: The eleventh international conference on learning representations"},{"key":"363_CR56","doi-asserted-by":"crossref","unstructured":"Yang C, Wang X, Yao L, Long G, Xu G (2023) From time series to multi-modality: classifying multivariate time series via both 1D and 2D representations. In: International conference on advanced data mining and applications. Springer, pp 19\u201333","DOI":"10.1007\/978-3-031-46661-8_2"},{"key":"363_CR57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127214","volume":"573","author":"W Homenda","year":"2023","unstructured":"Homenda W, Jastrzkebska A, Pedrycz W, Wrzesie M (2023) Time series classification with their image representation. Neurocomputing 573:127214","journal-title":"Neurocomputing"},{"key":"363_CR58","doi-asserted-by":"publisher","first-page":"2151","DOI":"10.1109\/TPAMI.2023.3333838","volume":"46","author":"H Li","year":"2023","unstructured":"Li H, Sima C, Dai J, Wang W, Lu L, Wang H, Zeng J, Li Z, Yang J, Deng H et al (2023) Delving into the devils of bird\u2019s-eye-view perception: a review, evaluation and recipe. IEEE Trans Pattern Anal Mach Intell 46:2151\u20132170","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"363_CR59","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122836","volume":"242","author":"J Zhao","year":"2023","unstructured":"Zhao J, Zhao W, Deng B, Wang Z, Zhang F, Zheng W, Cao W, Nan J, Lian Y, Burke AF (2023) Autonomous driving system: a comprehensive survey. Expert Syst Appl 242:122836","journal-title":"Expert Syst Appl"},{"key":"363_CR60","unstructured":"Huang K, Shi B, Li X, Li X, Huang S, Li Y (2022) Multi-modal sensor fusion for auto driving perception: a survey. arXiv preprint arXiv:2202.02703"},{"key":"363_CR61","unstructured":"Geiger A, Lenzp UR (2012) Are we ready for autonomous driving. In: Proceedings of 2012 IEEE conference on computer vision and pattern recognition"},{"key":"363_CR62","doi-asserted-by":"crossref","unstructured":"Sun P, Kretzschmar H, Dotiwalla X, Chouard A, Patnaik V, Tsui P, Guo J, Zhou Y, Chai Y, Caine Bet\u00a0al (2020) Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2446\u20132454","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"363_CR63","doi-asserted-by":"crossref","unstructured":"Caesar H, Bankiti V, Lang AH, Vora S, Liong VE, Xu Q, Krishnan A, Pan Y, Baldan G, Beijbom O (2020) nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11621\u201311631","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"363_CR64","doi-asserted-by":"crossref","unstructured":"Huang X, Cheng X, Geng Q, Cao B, Zhou D, Wang P, Lin Y, Yang R (2018) The apolloscape dataset for autonomous driving. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 954\u2013960","DOI":"10.1109\/CVPRW.2018.00141"},{"key":"363_CR65","doi-asserted-by":"crossref","unstructured":"Xiao P, Shao Z, Hao S, Zhang Z, Chai X, Jiao J, Li Z, Wu J, Sun K, Jiang K et\u00a0al (2021) Pandaset: advanced sensor suite dataset for autonomous driving. In: 2021 IEEE international intelligent transportation systems conference (ITSC). IEEE, pp 3095\u20133101","DOI":"10.1109\/ITSC48978.2021.9565009"},{"key":"363_CR66","doi-asserted-by":"crossref","unstructured":"Yan Z, Sun L, Krajn\u00edk T, Ruichek Y (2020) Eu long-term dataset with multiple sensors for autonomous driving. In: 2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 10697\u201310704","DOI":"10.1109\/IROS45743.2020.9341406"},{"key":"363_CR67","doi-asserted-by":"crossref","unstructured":"Pham Q-H, Sevestre P, Pahwa RS, Zhan H, Pang CH, Chen Y, Mustafa A, Chandrasekhar V, Lin J (2020) A* 3D dataset: towards autonomous driving in challenging environments. In: 2020 IEEE international conference on robotics and automation (ICRA). IEEE, pp 2267\u20132273","DOI":"10.1109\/ICRA40945.2020.9197385"},{"key":"363_CR68","doi-asserted-by":"crossref","unstructured":"Wang Z, Jia K (2019) Frustum convnet: sliding frustums to aggregate local point-wise features for a modal 3d object detection. In: 2019 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 1742\u20131749","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"363_CR69","unstructured":"Mao J, Niu M, Jiang C, Chen J, Liang X, Li Y, Ye C, Zhang W, Li Z, Yu J et\u00a0al: One million scenes for autonomous driving: once dataset. In: Thirty-fifth conference on neural information processing systems datasets and benchmarks track (Round 1)"},{"key":"363_CR70","doi-asserted-by":"crossref","unstructured":"Pan X, Xia Z, Song S, Li LE, Huang G (2021) 3D object detection with pointformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7463\u20137472","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"363_CR71","doi-asserted-by":"crossref","unstructured":"Huang J, Ye Y, Liang Z, Shan Y, Du D (2023) Detecting as labeling: rethinking lidar-camera fusion in 3d object detection. arXiv preprint arXiv:2311.07152","DOI":"10.1007\/978-3-031-72670-5_25"},{"key":"363_CR72","first-page":"18442","volume":"35","author":"Y Li","year":"2022","unstructured":"Li Y, Chen Y, Qi X, Li Z, Sun J, Jia J (2022) Unifying voxel-based representation with transformer for 3D object detection. Adv Neural Inf Process Syst 35:18442\u201318455","journal-title":"Adv Neural Inf Process Syst"},{"key":"363_CR73","doi-asserted-by":"crossref","unstructured":"Hu A, Murez Z, Mohan N, Dudas S, Hawke J, Badrinarayanan V, Cipolla R, Kendall A (2021) Fiery: future instance prediction in bird\u2019s-eye view from surround monocular cameras. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 15273\u201315282","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"363_CR74","unstructured":"Zhang Y, Zhu Z, Zheng W, Huang J, Huang G, Zhou J, Lu J (2022) Beverse: unified perception and prediction in birds-eye-view for vision-centric autonomous driving. arXiv preprint arXiv:2205.09743"},{"key":"363_CR75","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"363_CR76","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3366245","author":"Z Rao","year":"2024","unstructured":"Rao Z, Cai Y, Wang H, Lian Y, Zhong Y, Chen L, Li Y (2024) Enhancing autonomous driving: a low-cost monocular end-to-end framework with multi-task integration and temporal fusion. IEEE Tran Intell Veh. https:\/\/doi.org\/10.1109\/TIV.2024.3366245","journal-title":"IEEE Tran Intell Veh"},{"issue":"2","key":"363_CR77","first-page":"469","volume":"13","author":"M Malik","year":"2020","unstructured":"Malik M, Singh Y, Garg P, Gupta S (2020) Deep learning in healthcare system. Int J Grid Distrib Comput 13(2):469\u2013468","journal-title":"Int J Grid Distrib Comput"},{"issue":"6","key":"363_CR78","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1093\/bib\/bbx044","volume":"19","author":"R Miotto","year":"2018","unstructured":"Miotto R, Wang F, Wang S, Jiang X, Dudley JT (2018) Deep learning for healthcare: review, opportunities and challenges. Brief Bioinform 19(6):1236\u20131246","journal-title":"Brief Bioinform"},{"key":"363_CR79","unstructured":"Tsinalis O, Matthews PM, Guo Y, Zafeiriou S (2016) Automatic sleep stage scoring with single-channel EEG using convolutional neural networks. arXiv preprint arXiv:1610.01683"},{"key":"363_CR80","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1007\/s00521-012-1065-4","volume":"23","author":"S Ozcsen","year":"2013","unstructured":"Ozcsen S (2013) Classification of sleep stages using class-dependent sequential feature selection and artificial neural network. Neural Comput Appl 23:1239\u20131250","journal-title":"Neural Comput Appl"},{"key":"363_CR81","doi-asserted-by":"publisher","first-page":"781","DOI":"10.3389\/fnins.2018.00781","volume":"12","author":"A Malafeev","year":"2018","unstructured":"Malafeev A, Laptev D, Bauer S, Omlin X, Wierzbicka A, Wichniak A, Jernajczyk W, Riener R, Buhmann J, Achermann P (2018) Automatic human sleep stage scoring using deep neural networks. Front Neurosci 12:781","journal-title":"Front Neurosci"},{"issue":"12","key":"363_CR82","doi-asserted-by":"publisher","first-page":"1643","DOI":"10.1093\/jamia\/ocy131","volume":"25","author":"S Biswal","year":"2018","unstructured":"Biswal S, Sun H, Goparaju B, Westover MB, Sun J, Bianchi MT (2018) Expert-level sleep scoring with deep neural networks. J Am Med Inform Assoc 25(12):1643\u20131650","journal-title":"J Am Med Inform Assoc"},{"issue":"4","key":"363_CR83","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1109\/TNSRE.2018.2813138","volume":"26","author":"S Chambon","year":"2018","unstructured":"Chambon S, Galtier MN, Arnal PJ, Wainrib G, Gramfort A (2018) A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Trans Neural Syst Rehabil Eng 26(4):758\u2013769","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"363_CR84","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.bspc.2017.12.001","volume":"42","author":"A Sors","year":"2018","unstructured":"Sors A, Bonnet S, Mirek S, Vercueil L, Payen J-F (2018) A convolutional neural network for sleep stage scoring from raw single-channel EEG. Biomed Signal Process Control 42:107\u2013114","journal-title":"Biomed Signal Process Control"},{"issue":"5","key":"363_CR85","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1109\/TBCAS.2017.2719631","volume":"11","author":"J Zhang","year":"2017","unstructured":"Zhang J, Wu Y (2017) A new method for automatic sleep stage classification. IEEE Trans Biomed Circuits Syst 11(5):1097\u20131110","journal-title":"IEEE Trans Biomed Circuits Syst"},{"issue":"5","key":"363_CR86","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TBME.2018.2872652","volume":"66","author":"H Phan","year":"2018","unstructured":"Phan H, Andreotti F, Cooray N, Ch\u00e9n OY, De Vos M (2018) Joint classification and prediction CNN framework for automatic sleep stage classification. IEEE Trans Biomed Eng 66(5):1285\u20131296","journal-title":"IEEE Trans Biomed Eng"},{"issue":"2","key":"363_CR87","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1515\/bmt-2016-0156","volume":"63","author":"J Zhang","year":"2018","unstructured":"Zhang J, Wu Y (2018) Automatic sleep stage classification of single-channel EEG by using complex-valued convolutional neural network. Biomed Eng Biomed Tech 63(2):177\u2013190","journal-title":"Biomed Eng Biomed Tech"},{"issue":"4","key":"363_CR88","first-page":"6953","volume":"4","author":"A Sathyanarayana","year":"2016","unstructured":"Sathyanarayana A, Joty S, Fernandez-Luque L, Ofli F, Srivastava J, Elmagarmid A, Arora T, Shahrad T et al (2016) Correction of: sleep quality prediction from wearable data using deep learning. JMIR mHealth uHealth 4(4):6953","journal-title":"JMIR mHealth uHealth"},{"issue":"1","key":"363_CR89","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1038\/s41746-021-00440-5","volume":"4","author":"M Perslev","year":"2021","unstructured":"Perslev M, Darkner S, Kempfner L, Nikolic M, Jennum PJ, Igel C (2021) U-sleep: resilient high-frequency sleep staging. NPJ Digit Med 4(1):72","journal-title":"NPJ Digit Med"},{"key":"363_CR90","doi-asserted-by":"crossref","unstructured":"Yang S, Jia B, Chen Y, Huang ZA, Huang X, Lv J (2020) U-sleep: a deep neural network for automated detection of sleep arousals using multiple PSGS. In: Neural information processing: 27th international conference, ICONIP 2020, Bangkok, Thailand, November 23\u201327, 2020, Proceedings, Part III 27. Springer, pp 629\u2013640","DOI":"10.1007\/978-3-030-63836-8_52"},{"key":"363_CR91","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.compbiomed.2018.10.010","volume":"103","author":"X Zhang","year":"2018","unstructured":"Zhang X, Kou W, Eric I, Chang C, Gao H, Fan Y, Xu Y (2018) Sleep stage classification based on multi-level feature learning and recurrent neural networks via wearable device. Comput Biol Med 103:71\u201381","journal-title":"Comput Biol Med"},{"issue":"9","key":"363_CR92","doi-asserted-by":"publisher","first-page":"048","DOI":"10.1093\/sleep\/zsaa048","volume":"43","author":"P Fonseca","year":"2020","unstructured":"Fonseca P, Gilst MM, Radha M, Ross M, Moreau A, Cerny A, Anderer P, Long X, Dijk JP, Overeem S (2020) Automatic sleep staging using heart rate variability, body movements, and recurrent neural networks in a sleep disordered population. Sleep 43(9):048","journal-title":"Sleep"},{"issue":"6","key":"363_CR93","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.1109\/TBME.2020.3020381","volume":"68","author":"H Phan","year":"2020","unstructured":"Phan H, Ch\u00e9n OY, Koch P, Lu Z, McLoughlin I, Mertins A, De Vos M (2020) Towards more accurate automatic sleep staging via deep transfer learning. IEEE Trans Biomed Eng 68(6):1787\u20131798","journal-title":"IEEE Trans Biomed Eng"},{"key":"363_CR94","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.future.2020.03.019","volume":"109","author":"X Chen","year":"2020","unstructured":"Chen X, He J, Wu X, Yan W, Wei W (2020) Sleep staging by bidirectional long short-term memory convolution neural network. Future Gener Comput Syst 109:188\u2013196","journal-title":"Future Gener Comput Syst"},{"issue":"5","key":"363_CR95","doi-asserted-by":"publisher","first-page":"041","DOI":"10.1093\/sleep\/zsy041","volume":"41","author":"A Patanaik","year":"2018","unstructured":"Patanaik A, Ong JL, Gooley JJ, Ancoli-Israel S, Chee MW (2018) An end-to-end framework for real-time automatic sleep stage classification. Sleep 41(5):041","journal-title":"Sleep"},{"issue":"11","key":"363_CR96","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1093\/sleep\/zsz159","volume":"42","author":"L Zhang","year":"2019","unstructured":"Zhang L, Fabbri D, Upender R, Kent D (2019) Automated sleep stage scoring of the sleep heart health study using deep neural networks. Sleep 42(11):159","journal-title":"Sleep"},{"issue":"3","key":"363_CR97","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1109\/TNSRE.2019.2896659","volume":"27","author":"H Phan","year":"2019","unstructured":"Phan H, Andreotti F, Cooray N, Ch\u00e9n OY, De Vos M (2019) Seqsleepnet: end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging. IEEE Trans Neural Syst Rehabil Eng 27(3):400\u2013410","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"363_CR98","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122551","volume":"240","author":"S Lee","year":"2024","unstructured":"Lee S, Yu Y, Back S, Seo H, Lee K (2024) Sleepyco: automatic sleep scoring with feature pyramid and contrastive learning. Expert Syst Appl 240:122551","journal-title":"Expert Syst Appl"},{"key":"363_CR99","unstructured":"Lipton ZC, Kale DC, Elkan C, Wetzel R (2015) Learning to diagnose with LSTM recurrent neural networks. arXiv preprint arXiv:1511.03677"},{"key":"363_CR100","doi-asserted-by":"crossref","unstructured":"Cheng Y, Wang F, Zhang P, Hu J (2016) Risk prediction with electronic health records: a deep learning approach. In: Proceedings of the 2016 SIAM international conference on data mining. SIAM, pp 432\u2013440","DOI":"10.1137\/1.9781611974348.49"},{"key":"363_CR101","unstructured":"Choi E, Bahadori MT, Schuetz A, Stewart WF, Sun J (2016) Doctor AI: predicting clinical events via recurrent neural networks. In: Machine learning for healthcare conference. PMLR, pp 301\u2013318"},{"key":"363_CR102","unstructured":"Razavian N, Marcus J, Sontag D (2016) Multi-task prediction of disease onsets from longitudinal laboratory tests. In: Machine learning for healthcare conference. PMLR, pp 73\u2013100"},{"issue":"1","key":"363_CR103","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1038\/s41746-023-00970-0","volume":"7","author":"M Guevara","year":"2024","unstructured":"Guevara M, Chen S, Thomas S, Chaunzwa TL, Franco I, Kann BH, Moningi S, Qian JM, Goldstein M, Harper S et al (2024) Large language models to identify social determinants of health in electronic health records. NPJ Digit Med 7(1):6","journal-title":"NPJ Digit Med"},{"key":"363_CR104","doi-asserted-by":"crossref","unstructured":"Shi W, Xu R, Zhuang Y, Yu Y, Zhang J, Wu H, Zhu Y, Ho J, Yang C, Wang MD (2024) Ehragent: code empowers large language models for complex tabular reasoning on electronic health records. arXiv preprint arXiv:2401.07128","DOI":"10.18653\/v1\/2024.emnlp-main.1245"},{"key":"363_CR105","first-page":"99","volume":"20","author":"I Matthews","year":"1998","unstructured":"Matthews I, Cootes T, Cox S, Harvey R, Bangham JA (1998) Lipreading using shape, shading and scale. Proc Inst Acoust 20:99\u2013106","journal-title":"Proc Inst Acoust"},{"key":"363_CR106","unstructured":"Collobert R, Puhrsch C, Synnaeve G (2016) Wav2letter: an end-to-end convnet-based speech recognition system. arxiv. arXiv preprint arXiv:1609.03193"},{"issue":"5","key":"363_CR107","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"M Cooke","year":"2006","unstructured":"Cooke M, Barker J, Cunningham S, Shao X (2006) An audio-visual corpus for speech perception and automatic speech recognition. J Acoust Soc Am 120(5):2421\u20132424","journal-title":"J Acoust Soc Am"},{"key":"363_CR108","unstructured":"Cox SJ, Harvey RW, Lan Y, Newman JL, Theobald B-J (2008) The challenge of multispeaker lip-reading. In: AVSP. Citeseer, pp 179\u2013184"},{"issue":"7","key":"363_CR109","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/TMM.2009.2030637","volume":"11","author":"G Zhao","year":"2009","unstructured":"Zhao G, Barnard M, Pietikainen M (2009) Lipreading with local spatiotemporal descriptors. IEEE Trans Multimed 11(7):1254\u20131265","journal-title":"IEEE Trans Multimed"},{"key":"363_CR110","unstructured":"Afouras T, Chung JS, Zisserman A (2018) LRS3-TED: a large-scale dataset for visual speech recognition. arXiv preprint arXiv:1809.00496"},{"key":"363_CR111","doi-asserted-by":"crossref","unstructured":"Yang S, Zhang Y, Feng D, Yang M, Wang C, Xiao J, Long K, Shan S, Chen X (2019) LRW-1000: a naturally-distributed large-scale benchmark for lip reading in the wild. In: 2019 14th IEEE international conference on automatic face and gesture recognition (FG 2019). IEEE, pp 1\u20138","DOI":"10.1109\/FG.2019.8756582"},{"key":"363_CR112","doi-asserted-by":"crossref","unstructured":"Son\u00a0Chung J, Senior A, Vinyals O, Zisserman A (2017) Lip reading sentences in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6447\u20136456","DOI":"10.1109\/CVPR.2017.367"},{"key":"363_CR113","unstructured":"Chung J, Zisserman A (2017) Lip reading in profile. In: Ritish machine vision conference, 2017. British machine vision association and society for pattern recognition"},{"key":"363_CR114","doi-asserted-by":"crossref","unstructured":"Petridis S, Stafylakis T, Ma P, Cai F, Tzimiropoulos G, Pantic M (2018) End-to-end audiovisual speech recognition. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 6548\u20136552","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"363_CR115","doi-asserted-by":"crossref","unstructured":"Petridis S, Stafylakis T, Ma P, Tzimiropoulos G, Pantic M (2018) Audio-visual speech recognition with a hybrid CTC\/attention architecture. In: 2018 IEEE spoken language technology workshop (SLT). IEEE, pp 513\u2013520","DOI":"10.1109\/SLT.2018.8639643"},{"key":"363_CR116","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":"363_CR117","doi-asserted-by":"crossref","unstructured":"Wang J, Guo Z, Yang C, Li X, Cui Z (2023) Multi-scale hybrid fusion network for mandarin audio-visual speech recognition. In: 2023 IEEE international conference on multimedia and expo (ICME). IEEE, pp 642\u2013647","DOI":"10.1109\/ICME55011.2023.00116"},{"key":"363_CR118","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"S Gao","year":"2019","unstructured":"Gao S, Cheng M-M, Zhao K, Zhang X-Y, Yang M-H, Torr PH (2019) Res2Net: a new multi-scale backbone architecture. IEEE Trans Pattern Anal Mach Intell 43:652\u2013662","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"363_CR119","doi-asserted-by":"crossref","unstructured":"Serdyuk D, Braga O, Siohan O (2021) Audio-visual speech recognition is worth 32 times 32 times 8 voxels. In: 2021 IEEE automatic speech recognition and understanding workshop (ASRU). IEEE, pp 796\u2013802","DOI":"10.1109\/ASRU51503.2021.9688191"},{"key":"363_CR120","doi-asserted-by":"crossref","unstructured":"Xu G, Yang S, Li W, Wang S, Wei G, Yuan J, Gao J (2022) Channel-wise AV-fusion attention for multi-channel audio-visual speech recognition. In: ICASSP 2022-2022 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 9251\u20139255","DOI":"10.1109\/ICASSP43922.2022.9747535"},{"key":"363_CR121","doi-asserted-by":"crossref","unstructured":"Yu W, Zeiler S, Kolossa D (2021) Fusing information streams in end-to-end audio-visual speech recognition. In: ICASSP 2021-2021 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 3430\u20133434","DOI":"10.1109\/ICASSP39728.2021.9414553"},{"key":"363_CR122","doi-asserted-by":"crossref","unstructured":"Gulati A, Qin J, Chiu C-C, Parmar N, Zhang Y, Yu J, Han W, Wang S, Zhang Z, Wu Y et\u00a0al (2020) Conformer: convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"363_CR123","doi-asserted-by":"crossref","unstructured":"Ma P, Petridis S, Pantic M (2021) End-to-end audio-visual speech recognition with conformers. In: ICASSP 2021-2021 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 7613\u20137617","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"363_CR124","doi-asserted-by":"crossref","unstructured":"Burchi M, Timofte R (2023) Audio-visual efficient conformer for robust speech recognition. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 2258\u20132267","DOI":"10.1109\/WACV56688.2023.00229"},{"key":"363_CR125","doi-asserted-by":"crossref","unstructured":"Li B, Wu Z, Wang Y (2022) Cross-modal mask fusion and modality-balanced audio-visual speech recognition. In: 2022 IEEE 4th international conference on power, intelligent computing and systems (ICPICS). IEEE, pp 371\u2013375","DOI":"10.1109\/ICPICS55264.2022.9873574"},{"key":"363_CR126","doi-asserted-by":"crossref","unstructured":"Sterpu G, Saam C, Harte N (2018) Attention-based audio-visual fusion for robust automatic speech recognition. In: Proceedings of the 20th ACM international conference on multimodal interaction, pp 111\u2013115","DOI":"10.1145\/3242969.3243014"},{"issue":"3","key":"363_CR127","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1109\/TMM.2016.2520091","volume":"18","author":"P Wu","year":"2016","unstructured":"Wu P, Liu H, Li X, Fan T, Zhang X (2016) A novel lip descriptor for audio-visual keyword spotting based on adaptive decision fusion. IEEE Trans Multimed 18(3):326\u2013338","journal-title":"IEEE Trans Multimed"},{"key":"363_CR128","doi-asserted-by":"crossref","unstructured":"Xu B, Wang J, Lu C, Guo Y (2020) Watch to listen clearly: Visual speech enhancement driven multi-modality speech recognition. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1637\u20131646","DOI":"10.1109\/WACV45572.2020.9093314"},{"key":"363_CR129","doi-asserted-by":"crossref","unstructured":"Xu B, Lu C, Guo Y, Wang J (2020) Discriminative multi-modality speech recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14433\u201314442","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"363_CR130","doi-asserted-by":"publisher","first-page":"2707","DOI":"10.1109\/TASLP.2023.3294705","volume":"31","author":"G Li","year":"2023","unstructured":"Li G, Deng J, Geng M, Jin Z, Wang T, Hu S, Cui M, Meng H, Liu X (2023) Audio-visual end-to-end multi-channel speech separation, dereverberation and recognition. IEEE\/ACM Trans Audio Speech Lang Process 31:2707\u20132723","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"363_CR131","first-page":"1","volume":"500","author":"C Benoit","year":"2000","unstructured":"Benoit C, Martin J-C, Pelachaud C, Schomaker L, Suhm B (2000) Audio-visual and multimodal speech systems. Handbook of standards and resources for spoken language systems-supplement 500:1\u201395","journal-title":"Handbook of standards and resources for spoken language systems-supplement"},{"key":"363_CR132","doi-asserted-by":"crossref","unstructured":"Mroueh Y, Marcheret E, Goel V (2015) Deep multimodal learning for audio-visual speech recognition. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 2130\u20132134","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"363_CR133","doi-asserted-by":"crossref","unstructured":"Huang J, Kingsbury B (2013) Audio-visual deep learning for noise robust speech recognition. In: 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, pp 7596\u20137599","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"363_CR134","doi-asserted-by":"crossref","unstructured":"Zhang S, Lei M, Ma B, Xie L (2019) Robust audio-visual speech recognition using bimodal DFSMN with multi-condition training and dropout regularization. In: ICASSP 2019-2019 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 6570\u20136574","DOI":"10.1109\/ICASSP.2019.8682566"},{"key":"363_CR135","doi-asserted-by":"publisher","first-page":"142606","DOI":"10.1109\/ACCESS.2024.3456436","volume":"12","author":"J Shin","year":"2024","unstructured":"Shin J, Miah ASM, Kabir MH, Rahim MA, Al Shiam A (2024) A methodological and structural review of hand gesture recognition across diverse data modalities. IEEE Access 12:142606\u2013142639","journal-title":"IEEE Access"},{"key":"363_CR136","doi-asserted-by":"publisher","first-page":"4410","DOI":"10.1109\/TCYB.2022.3178370","volume":"53","author":"Y Tang","year":"2022","unstructured":"Tang Y, Chen D, Liu H, Cai C, Li X (2022) Deep EEG super resolution via correlating brain structural and functional connectivities. IEEE Trans Cybern 53:4410\u20134422","journal-title":"IEEE Trans Cybern"},{"issue":"2","key":"363_CR137","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1109\/TCYB.2019.2931142","volume":"51","author":"Y Fang","year":"2019","unstructured":"Fang Y, Zhou D, Li K, Ju Z, Liu H (2019) Attribute-driven granular model for EMG-based pinch and fingertip force grand recognition. IEEE Trans Cybern 51(2):789\u2013800","journal-title":"IEEE Trans Cybern"},{"key":"363_CR138","doi-asserted-by":"publisher","first-page":"7723","DOI":"10.1109\/TCYB.2022.3204343","volume":"53","author":"S Wei","year":"2022","unstructured":"Wei S, Zhang Y, Liu H (2022) A multimodal multilevel converged attention network for hand gesture recognition with hybrid SEMG and A-mode ultrasound sensing. IEEE Trans Cybern 53:7723\u20137734","journal-title":"IEEE Trans Cybern"},{"issue":"3","key":"363_CR139","doi-asserted-by":"publisher","first-page":"2773","DOI":"10.1109\/JSEN.2022.3231925","volume":"23","author":"S Duan","year":"2023","unstructured":"Duan S, Wu L, Xue B, Liu A, Qian R, Chen X (2023) A hybrid multimodal fusion framework for SEMG-ACC-based hand gesture recognition. IEEE Sens J 23(3):2773\u20132782","journal-title":"IEEE Sens J"},{"issue":"9","key":"363_CR140","doi-asserted-by":"publisher","first-page":"2434","DOI":"10.1109\/TBME.2019.2962499","volume":"67","author":"X Yang","year":"2019","unstructured":"Yang X, Yan J, Liu H (2019) Comparative analysis of wearable A-mode ultrasound and SEMG for muscle-computer interface. IEEE Trans Biomed Eng 67(9):2434\u20132442","journal-title":"IEEE Trans Biomed Eng"},{"key":"363_CR141","doi-asserted-by":"crossref","unstructured":"Boyd P, Liu H (2020) A-mode ultrasound driven sensor fusion for hand gesture recognition. In: 2020 International joint conference on neural networks (IJCNN). IEEE, pp 1\u20136","DOI":"10.1109\/IJCNN48605.2020.9207492"},{"key":"363_CR142","doi-asserted-by":"crossref","unstructured":"Zeng J, Zhou Y, Yang Y, Wang J, Liu H (2020) Feature fusion of SEMG and ultrasound signals in hand gesture recognition. In: 2020 IEEE international conference on systems, man, and cybernetics (SMC). IEEE, pp 3911\u20133916","DOI":"10.1109\/SMC42975.2020.9282818"},{"key":"363_CR143","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.neucom.2017.02.101","volume":"277","author":"B Fang","year":"2018","unstructured":"Fang B, Sun F, Liu H, Liu C (2018) 3d human gesture capturing and recognition by the IMMU-based data glove. Neurocomputing 277:198\u2013207","journal-title":"Neurocomputing"},{"issue":"3","key":"363_CR144","doi-asserted-by":"publisher","first-page":"1104","DOI":"10.1109\/TII.2016.2550528","volume":"12","author":"P P\u0142awiak","year":"2016","unstructured":"P\u0142awiak P, So\u015bnicki T, Nied\u017awiecki M, Tabor Z, Rzecki K (2016) Hand body language gesture recognition based on signals from specialized glove and machine learning algorithms. IEEE Trans Ind Inform 12(3):1104\u20131113","journal-title":"IEEE Trans Ind Inform"},{"issue":"1","key":"363_CR145","first-page":"539","volume":"21","author":"G Yuan","year":"2020","unstructured":"Yuan G, Liu X, Yan Q, Qiao S, Wang Z, Yuan L (2020) Hand gesture recognition using deep feature fusion network based on wearable sensors. IEEE Sens J 21(1):539\u2013547","journal-title":"IEEE Sens J"},{"issue":"5","key":"363_CR146","doi-asserted-by":"publisher","first-page":"3172","DOI":"10.1109\/TCYB.2020.3007173","volume":"52","author":"T-Y Pan","year":"2020","unstructured":"Pan T-Y, Tsai W-L, Chang C-Y, Yeh C-W, Hu M-C (2020) A hierarchical hand gesture recognition framework for sports referee training-based EMG and accelerometer sensors. IEEE Trans Cybern 52(5):3172\u20133183","journal-title":"IEEE Trans Cybern"},{"issue":"8","key":"363_CR147","doi-asserted-by":"publisher","first-page":"3376","DOI":"10.1109\/TII.2017.2779814","volume":"14","author":"S Jiang","year":"2017","unstructured":"Jiang S, Lv B, Guo W, Zhang C, Wang H, Sheng X, Shull PB (2017) Feasibility of wrist-worn, real-time hand, and surface gesture recognition via SEMG and IMU sensing. IEEE Trans Ind Inform 14(8):3376\u20133385","journal-title":"IEEE Trans Ind Inform"},{"key":"363_CR148","doi-asserted-by":"publisher","first-page":"43","DOI":"10.3389\/fnbot.2019.00043","volume":"13","author":"W Shahzad","year":"2019","unstructured":"Shahzad W, Ayaz Y, Khan MJ, Naseer N, Khan M (2019) Enhanced performance for multi-forearm movement decoding using hybrid IMU-SEMG interface. Front Neurorobot 13:43","journal-title":"Front Neurorobot"},{"issue":"10","key":"363_CR149","doi-asserted-by":"publisher","first-page":"2964","DOI":"10.1109\/TBME.2019.2899222","volume":"66","author":"W Wei","year":"2019","unstructured":"Wei W, Dai Q, Wong Y, Hu Y, Kankanhalli M, Geng W (2019) Surface-electromyography-based gesture recognition by multi-view deep learning. IEEE Trans Biomed Eng 66(10):2964\u20132973","journal-title":"IEEE Trans Biomed Eng"},{"key":"363_CR150","doi-asserted-by":"crossref","unstructured":"Fougner A, Scheme E, Chan A.D, Englehart K, Stavdahl \u00d8 (2011) A multi-modal approach for hand motion classification using surface emg and accelerometers. In: 2011 Annual international conference of the IEEE engineering in medicine and biology society. IEEE, pp 4247\u20134250","DOI":"10.1109\/IEMBS.2011.6091054"},{"key":"363_CR151","doi-asserted-by":"publisher","first-page":"15283","DOI":"10.1109\/JSEN.2024.3376606","volume":"24","author":"S Heinrich","year":"2024","unstructured":"Heinrich S, Michaelis J, Reiher I, Coppers B, Lohmayer M, Fleischmann E, Kleyer A, Schett G, De Craemer A-S, Elewaut D et al (2024) Comparison and improvement of cyberglove III calibration methods. IEEE Sens J 24:15283\u201315291","journal-title":"IEEE Sens J"},{"issue":"5","key":"363_CR152","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.3390\/s21051576","volume":"21","author":"J Henderson","year":"2021","unstructured":"Henderson J, Condell J, Connolly J, Kelly D, Curran K (2021) Review of wearable sensor-based health monitoring glove devices for rheumatoid arthritis. Sensors 21(5):1576","journal-title":"Sensors"},{"issue":"1","key":"363_CR153","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji S, Xu W, Yang M, Yu K (2012) 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35(1):221\u2013231","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"363_CR154","doi-asserted-by":"publisher","first-page":"1692","DOI":"10.1109\/TPAMI.2015.2461544","volume":"38","author":"N Neverova","year":"2015","unstructured":"Neverova N, Wolf C, Taylor G, Nebout F (2015) Moddrop: adaptive multi-modal gesture recognition. IEEE Trans Pattern Anal Mach Intell 38(8):1692\u20131706","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"363_CR155","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1109\/TII.2011.2172450","volume":"8","author":"C Tran","year":"2011","unstructured":"Tran C, Trivedi MM (2011) 3-d posture and gesture recognition for interactivity in smart spaces. IEEE Trans Ind Inform 8(1):178\u2013187","journal-title":"IEEE Trans Ind Inform"},{"issue":"14","key":"363_CR156","doi-asserted-by":"publisher","first-page":"14610","DOI":"10.1109\/JSEN.2022.3181518","volume":"22","author":"DG Leon","year":"2022","unstructured":"Leon DG, Groli J, Yeduri SR, Rossier D, Mosqueron R, Pandey OJ, Cenkeramaddi LR (2022) Video hand gestures recognition using depth camera and lightweight CNN. IEEE Sens J 22(14):14610\u201314619","journal-title":"IEEE Sens J"},{"issue":"1","key":"363_CR157","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1007\/s40747-023-01173-6","volume":"10","author":"J Qi","year":"2024","unstructured":"Qi J, Ma L, Cui Z, Yu Y (2024) Computer vision-based hand gesture recognition for human\u2013robot interaction: a review. Complex Intell Syst 10(1):1581\u20131606","journal-title":"Complex Intell Syst"},{"key":"363_CR158","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123349","volume":"247","author":"R Rastgoo","year":"2024","unstructured":"Rastgoo R, Kiani K, Escalera S, Sabokrou M (2024) Multi-modal zero-shot dynamic hand gesture recognition. Expert Syst Appl 247:123349","journal-title":"Expert Syst Appl"},{"issue":"20","key":"363_CR159","doi-asserted-by":"publisher","first-page":"15396","DOI":"10.1109\/JIOT.2021.3072169","volume":"8","author":"R Min","year":"2021","unstructured":"Min R, Wang X, Zou J, Gao J, Wang L, Cao Z (2021) Early gesture recognition with reliable accuracy based on high-resolution IoT radar sensors. IEEE Internet Things J 8(20):15396\u201315406","journal-title":"IEEE Internet Things J"},{"key":"363_CR160","first-page":"1","volume":"19","author":"Z Liu","year":"2022","unstructured":"Liu Z, Liu H, Ma C (2022) A robust hand gesture sensing and recognition based on dual-flow fusion with FMCW radar. IEEE Geosci Remote Sens Lett 19:1\u20135","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"363_CR161","doi-asserted-by":"crossref","unstructured":"Zhang H, Liu K, Zhang Y, Lin J (2024) Trans-CNN-based gesture recognition for mmwave radar. Sensors 24(6):1800","DOI":"10.3390\/s24061800"},{"key":"363_CR162","doi-asserted-by":"publisher","first-page":"1745","DOI":"10.1109\/LSP.2020.3026942","volume":"27","author":"Z Liu","year":"2020","unstructured":"Liu Z, Kong Y, Zhang X, Wu J, Lu W (2020) Vital sign extraction in the presence of radar mutual interference. IEEE Signal Process Lett 27:1745\u20131749","journal-title":"IEEE Signal Process Lett"},{"key":"363_CR163","volume-title":"Millimeter-wave radar targets and clutter","author":"GP Kulemin","year":"2003","unstructured":"Kulemin GP (2003) Millimeter-wave radar targets and clutter. Artech House, London"},{"key":"363_CR164","doi-asserted-by":"publisher","first-page":"22295","DOI":"10.1109\/ACCESS.2021.3056878","volume":"9","author":"M Altmann","year":"2021","unstructured":"Altmann M, Ott P, Stache NC, Waldschmidt C (2021) Multi-modal cross learning for an FMCW radar assisted by thermal and RGB cameras to monitor gestures and cooking processes. IEEE Access 9:22295\u201322303","journal-title":"IEEE Access"},{"key":"363_CR165","doi-asserted-by":"crossref","unstructured":"Molchanov P, Gupta S, Kim K, Pulli K (2015) Multi-sensor system for driver\u2019s hand-gesture recognition. In: 2015 11th IEEE international conference and workshops on automatic face and gesture recognition (FG), vol 1. IEEE, pp 1\u20138","DOI":"10.1109\/FG.2015.7163132"},{"key":"363_CR166","doi-asserted-by":"crossref","unstructured":"Liu H, Liu Z (2023) A multimodal dynamic hand gesture recognition based on radar-vision fusion. IEEE Trans Instrum Meas 72:1\u201315","DOI":"10.1109\/TIM.2023.3253906"},{"key":"363_CR167","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108976","volume":"250","author":"Y Ma","year":"2022","unstructured":"Ma Y, Zhao S, Wang W, Li Y, King I (2022) Multimodality in meta-learning: a comprehensive survey. Knowl Based Syst 250:108976","journal-title":"Knowl Based Syst"},{"key":"363_CR168","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105253","volume":"144","author":"MA Azam","year":"2022","unstructured":"Azam MA, Khan KB, Salahuddin S, Rehman E, Khan SA, Khan MA, Kadry S, Gandomi AH (2022) A review on multimodal medical image fusion: compendious analysis of medical modalities, multimodal databases, fusion techniques and quality metrics. Comput Biol Med 144:105253","journal-title":"Comput Biol Med"},{"key":"363_CR169","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102040","volume":"102","author":"T Shaik","year":"2024","unstructured":"Shaik T, Tao X, Li L, Xie H, Vel\u00e1squez JD (2024) A survey of multimodal information fusion for smart healthcare: mapping the journey from data to wisdom. Inf Fusion 102:102040","journal-title":"Inf Fusion"},{"issue":"8","key":"363_CR170","doi-asserted-by":"publisher","first-page":"2939","DOI":"10.1007\/s00371-021-02166-7","volume":"38","author":"K Bayoudh","year":"2022","unstructured":"Bayoudh K, Knani R, Hamdaoui F, Mtibaa A (2022) A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Vis Comput 38(8):2939\u20132970","journal-title":"Vis Comput"},{"issue":"4","key":"363_CR171","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1109\/JBHI.2021.3117575","volume":"26","author":"K Panetta","year":"2021","unstructured":"Panetta K, Rajendran R, Ramesh A, Rao SP, Agaian S (2021) Tufts dental database: a multimodal panoramic X-ray dataset for benchmarking diagnostic systems. IEEE J Biomed Health Inform 26(4):1650\u20131659","journal-title":"IEEE J Biomed Health Inform"},{"issue":"3","key":"363_CR172","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/s10389-022-01795-z","volume":"32","author":"R Tertulino","year":"2024","unstructured":"Tertulino R, Antunes N, Morais H (2024) Privacy in electronic health records: a systematic mapping study. J Public Health 32(3):435\u2013454","journal-title":"J Public Health"},{"key":"363_CR173","doi-asserted-by":"publisher","first-page":"2030","DOI":"10.1109\/TIFS.2022.3175599","volume":"17","author":"H Ren","year":"2022","unstructured":"Ren H, Sun L, Guo J, Han C (2022) A dataset and benchmark for multimodal biometric recognition based on fingerprint and finger vein. IEEE Trans Inf Forensics Secur 17:2030\u20132043","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"10","key":"363_CR174","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3663364","volume":"56","author":"PP Liang","year":"2024","unstructured":"Liang PP, Zadeh A, Morency L-P (2024) Foundations and trends in multimodal machine learning: principles, challenges, and open questions. ACM Comput Surv 56(10):1\u201342","journal-title":"ACM Comput Surv"},{"key":"363_CR175","doi-asserted-by":"crossref","unstructured":"Wang J, Zhang H, Zhong Y, Liang Y, Ji R, Cang Y (2024) Advanced multimodal deep learning architecture for image-text matching. In: 2024 IEEE 4th international conference on electronic technology, communication and information (ICETCI). IEEE, pp 1185\u20131191","DOI":"10.1109\/ICETCI61221.2024.10594167"},{"key":"363_CR176","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3368112","author":"M Zhou","year":"2024","unstructured":"Zhou M, Huang J, Yan K, Hong D, Jia X, Chanussot J, Li C (2024) A general spatial-frequency learning framework for multimodal image fusion. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2024.3368112","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"10","key":"363_CR177","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/bdcc8100125","volume":"8","author":"S Kumar","year":"2024","unstructured":"Kumar S, Sharma S (2024) An improved deep learning framework for multimodal medical data analysis. Big Data Cogn Comput 8(10):125","journal-title":"Big Data Cogn Comput"},{"key":"363_CR178","unstructured":"Zhang Y, Gong K, Zhang K, Li H, Qiao Y, Ouyang W, Yue X (2023) Meta-transformer: a unified framework for multimodal learning. arXiv preprint arXiv:2307.10802"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-025-00363-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13735-025-00363-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-025-00363-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T15:03:45Z","timestamp":1749567825000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13735-025-00363-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,15]]},"references-count":178,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["363"],"URL":"https:\/\/doi.org\/10.1007\/s13735-025-00363-x","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,15]]},"assertion":[{"value":"9 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"The authors state that there are no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"15"}}