{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T01:06:04Z","timestamp":1772672764507,"version":"3.50.1"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University (IMSIU) (grant number IMSIU-DDRSP2501).","award":["IMSIU-DDRSP2501"],"award-info":[{"award-number":["IMSIU-DDRSP2501"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"DOI":"10.1186\/s40537-025-01293-5","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T09:49:32Z","timestamp":1758620972000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Optimizing action recognition: a residual convolution with hierarchical and gram matrix based attention mechanisms"],"prefix":"10.1186","volume":"12","author":[{"given":"Essam H.","family":"Houssein","sequence":"first","affiliation":[]},{"given":"Ibrahim A.","family":"Ibrahim","sequence":"additional","affiliation":[]},{"given":"Mohamed A.","family":"Mahdy","sequence":"additional","affiliation":[]},{"given":"Mohammed","family":"Kayed","sequence":"additional","affiliation":[]},{"given":"Abdullah M.","family":"Albarrak","sequence":"additional","affiliation":[]},{"given":"Waleed M.","family":"Mohamed","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,23]]},"reference":[{"issue":"3","key":"1293_CR1","first-page":"3200","volume":"45","author":"Z Sun","year":"2022","unstructured":"Sun Z, Ke Q, Rahmani H, Bennamoun M, Wang G, Liu J. Human action recognition from various data modalities: a review. IEEE Trans Pattern Anal Mach Intell. 2022;45(3):3200\u201325.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"1293_CR2","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/34.910878","volume":"23","author":"AF Bobick","year":"2001","unstructured":"Bobick AF, Davis JW. The recognition of human movement using temporal templates. IEEE Trans Pattern Anal Mach Intell. 2001;23(3):257\u201367.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"1293_CR3","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MMUL.2012.24","volume":"19","author":"Z Zhang","year":"2012","unstructured":"Zhang Z. Microsoft Kinect sensor and its effect. IEEE Multimed. 2012;19(2):4\u201310.","journal-title":"IEEE Multimed"},{"key":"1293_CR4","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/TIP.2019.2925285","volume":"29","author":"L Wang","year":"2019","unstructured":"Wang L, Huynh DQ, Koniusz P. A comparative review of recent kinect-based action recognition algorithms. IEEE Trans Image Process. 2019;29:15\u201328.","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"1293_CR5","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1109\/JSEN.2014.2309987","volume":"14","author":"T Mallick","year":"2014","unstructured":"Mallick T, Das PP, Majumdar AK. Characterizations of noise in kinect depth images: a review. IEEE Sens J. 2014;14(6):1731\u201340.","journal-title":"IEEE Sens J"},{"key":"1293_CR6","doi-asserted-by":"publisher","first-page":"15280","DOI":"10.1109\/ACCESS.2020.2968054","volume":"8","author":"Y Fan","year":"2020","unstructured":"Fan Y, Weng S, Zhang Y, Shi B, Zhang Y. Context-aware cross-attention for skeleton-based human action recognition. IEEE Access. 2020;8:15280\u201390.","journal-title":"IEEE Access"},{"issue":"3","key":"1293_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1922649.1922653","volume":"43","author":"JK Aggarwal","year":"2011","unstructured":"Aggarwal JK, Ryoo MS. Human activity analysis: a review. Acm Comput Surveys (Csur). 2011;43(3):1\u201343.","journal-title":"Acm Comput Surveys (Csur)"},{"key":"1293_CR8","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.knosys.2018.05.029","volume":"158","author":"P Wang","year":"2018","unstructured":"Wang P, Li W, Li C, Hou Y. Action recognition based on joint trajectory maps with convolutional neural networks. Knowl-Based Syst. 2018;158:43\u201353.","journal-title":"Knowl-Based Syst"},{"issue":"5","key":"1293_CR9","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1109\/LSP.2017.2678539","volume":"24","author":"C Li","year":"2017","unstructured":"Li C, Hou Y, Wang P, Li W. Joint distance maps based action recognition with convolutional neural networks. IEEE Signal Process Lett. 2017;24(5):624\u20138.","journal-title":"IEEE Signal Process Lett"},{"key":"1293_CR10","doi-asserted-by":"crossref","unstructured":"Yang X, Tian Y. Super normal vector for activity recognition using depth sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. p. 804\u2013811.","DOI":"10.1109\/CVPR.2014.108"},{"issue":"10","key":"1293_CR11","doi-asserted-by":"publisher","first-page":"4648","DOI":"10.1109\/TIP.2017.2718189","volume":"26","author":"B Zhang","year":"2017","unstructured":"Zhang B, Yang Y, Chen C, Yang L, Han J, Shao L. Action recognition using 3d histograms of texture and a multi-class boosting classifier. IEEE Trans Image Process. 2017;26(10):4648\u201360.","journal-title":"IEEE Trans Image Process"},{"key":"1293_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.10.004","volume":"93","author":"G Ye","year":"2020","unstructured":"Ye G, Ye X, Sheng W, Yongsheng O, Li Y. Multiple stream deep learning model for human action recognition. Image Vis Comput. 2020;93:103818.","journal-title":"Image Vis Comput"},{"key":"1293_CR13","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Hao S, Krause J, Satheesh S, Ma S, et al. Imagenet large scale visual recognition challenge. Int J Comput Vision. 2015;115:211\u201352.","journal-title":"Int J Comput Vision"},{"issue":"1","key":"1293_CR14","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00664-6","volume":"9","author":"D Naik","year":"2022","unstructured":"Naik D, Jaidhar CD. A novel multi-layer attention framework for visual description prediction using bidirectional lstm. J Big Data. 2022;9(1):104.","journal-title":"J Big Data"},{"key":"1293_CR15","first-page":"1","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. Adv Neural Inform Proc Syst. 2017;30:1.","journal-title":"Adv Neural Inform Proc Syst"},{"key":"1293_CR16","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L. Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2014. p. 1725\u20131732.","DOI":"10.1109\/CVPR.2014.223"},{"key":"1293_CR17","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A. Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 1933\u20131941.","DOI":"10.1109\/CVPR.2016.213"},{"issue":"11","key":"1293_CR18","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang L, Xiong Y, Zhe Wang Yu, Qiao DL, Tang X, Van Gool L. Temporal segment networks for action recognition in videos. IEEE Trans Pattern Anal Mach Intell. 2018;41(11):2740\u201355.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1293_CR19","doi-asserted-by":"crossref","unstructured":"Zeng M, Nguyen LT, Yu B, Mengshoel OJ, Zhu J, Wu P, Zhang J. Convolutional neural networks for human activity recognition using mobile sensors. In: 6th international conference on mobile computing, applications and services. 2014. p. 197\u2013205. IEEE.","DOI":"10.4108\/icst.mobicase.2014.257786"},{"issue":"1","key":"1293_CR20","doi-asserted-by":"publisher","DOI":"10.3390\/s16010115","volume":"16","author":"FJ Ord\u00f3\u00f1ez","year":"2016","unstructured":"Ord\u00f3\u00f1ez FJ, Roggen D. Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors. 2016;16(1):115.","journal-title":"Sensors"},{"key":"1293_CR21","unstructured":"Dong X, Yang Y. Nas-bench-201: extending the scope of reproducible neural architecture search. 2020. arXiv preprint arXiv:2001.00326."},{"issue":"1","key":"1293_CR22","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/s40815-024-01770-8","volume":"27","author":"\u015e \u00d6zl\u00fc","year":"2025","unstructured":"\u00d6zl\u00fc \u015e. Bipolar-valued complex hesitant fuzzy dombi aggregating operators based on multi-criteria decision-making problems. Int J Fuzzy Syst. 2025;27(1):162\u201389.","journal-title":"Int J Fuzzy Syst"},{"issue":"6","key":"1293_CR23","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1007\/s41066-023-00382-1","volume":"8","author":"\u015e \u00d6zl\u00fc","year":"2023","unstructured":"\u00d6zl\u00fc \u015e. Multi-criteria decision making based on vector similarity measures of picture type-2 hesitant fuzzy sets. Granul Comput. 2023;8(6):1505\u201331.","journal-title":"Granul Comput"},{"key":"1293_CR24","doi-asserted-by":"crossref","unstructured":"Horv\u00e1th R, T\u00f3th-Laufer E. Fuzzy model-based cutting parameter combination optimization. In: IEEE 18th International Conference on Intelligent Engineering Systems INES 2014. 2014. p. 151\u2013155. IEEE.","DOI":"10.1109\/INES.2014.6909359"},{"issue":"3","key":"1293_CR25","doi-asserted-by":"publisher","DOI":"10.1007\/s40314-024-02646-1","volume":"43","author":"\u015e \u00d6zl\u00fc","year":"2024","unstructured":"\u00d6zl\u00fc \u015e. New q-rung orthopair fuzzy Aczel-Alsina weighted geometric operators under group-based generalized parameters in multi-criteria decision-making problems. Comput Appl Math. 2024;43(3):122.","journal-title":"Comput Appl Math"},{"issue":"2","key":"1293_CR26","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1109\/JSEN.2023.3335213","volume":"24","author":"N Zhang","year":"2023","unstructured":"Zhang N, Song Y, Fang D, Gao Z, Yan Y. An improved deep convolutional lstm for human activity recognition using wearable sensors. IEEE Sens J. 2023;24(2):1717\u201329.","journal-title":"IEEE Sens J"},{"key":"1293_CR27","unstructured":"Romero DW, Bruintjes RJ, Tomczak JM, Bekkers EJ, Hoogendoorn M, Gemert JCv. Flexconv: Continuous kernel convolutions with differentiable kernel sizes. 2021. arXiv preprint arXiv:2110.08059."},{"issue":"5","key":"1293_CR28","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1162\/neco_a_01273","volume":"32","author":"J Gao","year":"2020","unstructured":"Gao J, Li P, Chen Z, Zhang J. A survey on deep learning for multimodal data fusion. Neural Comput. 2020;32(5):829\u201364.","journal-title":"Neural Comput"},{"key":"1293_CR29","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","volume":"119","author":"J Wang","year":"2019","unstructured":"Wang J, Chen Y, Hao S, Peng X, Lisha H. Deep learning for sensor-based activity recognition: a survey. Pattern Recogn Lett. 2019;119:3\u201311.","journal-title":"Pattern Recogn Lett"},{"issue":"21","key":"1293_CR30","doi-asserted-by":"publisher","first-page":"24653","DOI":"10.1109\/JSEN.2021.3102666","volume":"21","author":"X Wang","year":"2021","unstructured":"Wang X, Lv T, Gan Z, He M, Jin L. Fusion of skeleton and inertial data for human action recognition based on skeleton motion maps and dilated convolution. IEEE Sens J. 2021;21(21):24653\u201364.","journal-title":"IEEE Sens J"},{"issue":"4","key":"1293_CR31","doi-asserted-by":"publisher","first-page":"2153","DOI":"10.3390\/s23042153","volume":"23","author":"J Yan","year":"2023","unstructured":"Yan J, Wang X, Shi J, Shuai H. Skeleton-based fall detection with multiple inertial sensors using spatial-temporal graph convolutional networks. Sensors. 2023;23(4):2153.","journal-title":"Sensors"},{"issue":"19","key":"1293_CR32","doi-asserted-by":"publisher","first-page":"28919","DOI":"10.1007\/s11042-021-11058-w","volume":"80","author":"C Pham","year":"2021","unstructured":"Pham C, Nguyen L, Nguyen A, Nguyen N, Nguyen V-T. Combining skeleton and accelerometer data for human fine-grained activity recognition and abnormal behaviour detection with deep temporal convolutional networks. Multimed Tools Appl. 2021;80(19):28919\u201340.","journal-title":"Multimed Tools Appl"},{"key":"1293_CR33","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.patrec.2018.04.035","volume":"115","author":"P Khaire","year":"2018","unstructured":"Khaire P, Kumar P, Imran J. Combining CNN streams of RGB-D and skeletal data for human activity recognition. Patt Recogn Lett. 2018;115:107\u201316.","journal-title":"Patt Recogn Lett"},{"issue":"14","key":"1293_CR34","doi-asserted-by":"publisher","DOI":"10.3390\/s24144646","volume":"24","author":"SU Rehman","year":"2024","unstructured":"Rehman SU, Yasin AU, Haq EU, Ali M, Kim J, Mehmood A. Enhancing human activity recognition through integrated multimodal analysis: a focus on rgb imaging, skeletal tracking, and pose estimation. Sensors. 2024;24(14):4646.","journal-title":"Sensors"},{"key":"1293_CR35","doi-asserted-by":"crossref","unstructured":"Tagmouni A, Elmir Y, Kechadi MT. Evaluating outputs fusion technique in multimodal human activity recognition: Impact of modality reduction on performance efficiency. In: 2024 7th International Conference on Signal Processing and Information Security (ICSPIS). 2024. p. 1\u20136. IEEE.","DOI":"10.1109\/ICSPIS63676.2024.10812599"},{"key":"1293_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3481631","volume":"12","author":"M Batool","year":"2024","unstructured":"Batool M, Alotaibi M, Alotaibi SR, AlHammadi DA, Jamal MA, Jalal A, et al. Multimodal human action recognition framework using an improved cnngru classifier. IEEE Access. 2024;12:2024:1.","journal-title":"IEEE Access"},{"key":"1293_CR37","doi-asserted-by":"crossref","unstructured":"Haque ST, Ngu AHH. Poster: multimodal convtransformer for human activity recognition. In: 2024 IEEE\/ACM Conference on Connected Health: applications, Systems and Engineering Technologies (CHASE). 2024. p. 206\u2013207. IEEE.","DOI":"10.1109\/CHASE60773.2024.00041"},{"key":"1293_CR38","doi-asserted-by":"publisher","first-page":"135118","DOI":"10.1109\/ACCESS.2020.3006067","volume":"8","author":"T Yang","year":"2020","unstructured":"Yang T, Hou Z, Liang J, Yuwan G, Chao X. Depth sequential information entropy maps and multi-label subspace learning for human action recognition. IEEE Access. 2020;8:135118\u201330.","journal-title":"IEEE Access"},{"key":"1293_CR39","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1105","volume":"8","author":"M Javeed","year":"2022","unstructured":"Javeed M, Shorfuzzaman M, Alsufyani N, Chelloug SA, Jalal A, Park J. Physical human locomotion prediction using manifold regularization. PeerJ Comput Sci. 2022;8:e1105.","journal-title":"PeerJ Comput Sci"},{"key":"1293_CR40","doi-asserted-by":"crossref","unstructured":"Ni J, Ngu AHH, Yan Y. Progressive cross-modal knowledge distillation for human action recognition. In: Proceedings of the 30th ACM International Conference on Multimedia. 2022. p. 5903\u20135912.","DOI":"10.1145\/3503161.3548238"},{"issue":"3","key":"1293_CR41","doi-asserted-by":"publisher","first-page":"768","DOI":"10.3390\/s21030768","volume":"21","author":"CM Ranieri","year":"2021","unstructured":"Ranieri CM, MacLeod S, Dragone M, Vargas PA, Romero RAF. Activity recognition for ambient assisted living with videos, inertial units and ambient sensors. Sensors (Basel). 2021;21(3):768.","journal-title":"Sensors (Basel)"},{"key":"1293_CR42","doi-asserted-by":"crossref","unstructured":"Zhang X, Wang Y, Gou M, Sznaier M, Camps O. Efficient temporal sequence comparison and classification using gram matrix embeddings on a riemannian manifold. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 4498\u20134507.","DOI":"10.1109\/CVPR.2016.487"},{"key":"1293_CR43","first-page":"1","volume":"30","author":"R Girdhar","year":"2017","unstructured":"Girdhar R, Ramanan D. Attentional pooling for action recognition. Adv Neural Inform Proc Syst. 2017;30:1.","journal-title":"Adv Neural Inform Proc Syst"},{"issue":"2","key":"1293_CR44","first-page":"26","volume":"4","author":"T Tieleman","year":"2012","unstructured":"Tieleman T. Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA Neural Netw Mach Learn. 2012;4(2):26.","journal-title":"COURSERA Neural Netw Mach Learn."},{"key":"1293_CR45","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning, vol. 1. Cambridge: MIT press Cambridge; 2016."},{"issue":"11","key":"1293_CR46","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86(11):2278\u2013324.","journal-title":"Proc IEEE"},{"key":"1293_CR47","unstructured":"Simonyan, K, Zisserman, A. Very deep convolutional networks for large-scale image recognition. 2014. arXiv preprint arXiv:1409.1556."},{"key":"1293_CR48","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1293_CR49","unstructured":"Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In International conference on machine learning. 2015. p. 448\u2013456. pmlr."},{"issue":"1","key":"1293_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning. J Big Data. 2019;6(1):1\u201348.","journal-title":"J Big Data"},{"issue":"1","key":"1293_CR51","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra J, Bengio Y. Random search for hyper-parameter optimization. J Mach Learn Res. 2012;13(1):281\u2013305.","journal-title":"J Mach Learn Res"},{"key":"1293_CR52","doi-asserted-by":"crossref","unstructured":"Akiba T, Sano S, Yanase T, Ohta T, Koyama M. Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 2019. p. 2623\u20132631.","DOI":"10.1145\/3292500.3330701"},{"issue":"2","key":"1293_CR53","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1484","volume":"13","author":"B Bischl","year":"2023","unstructured":"Bischl B, Binder M, Lang M, Pielok T, Richter J, Coors S, et al. Hyperparameter optimization: foundations, algorithms, best practices, and open challenges. WIREs Data Min Knowl Discov. 2023;13(2):e1484.","journal-title":"WIREs Data Min Knowl Discov"},{"issue":"1","key":"1293_CR54","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15(1):1929\u201358.","journal-title":"J Mach Learn Res"},{"key":"1293_CR55","doi-asserted-by":"crossref","unstructured":"Prechelt L. Early stopping-but when? In Neural Networks: Tricks of the trade. Springer; 2002 p. 55\u201369.","DOI":"10.1007\/3-540-49430-8_3"},{"key":"1293_CR56","unstructured":"Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics. 2020. p. 249\u2013256. JMLR Workshop and Conference Proceedings."},{"key":"1293_CR57","doi-asserted-by":"crossref","unstructured":"Chen C, Jafari R, Kehtarnavaz N. Utd-mhad: a multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor. In: 2015 IEEE International conference on image processing (ICIP). 2025. p. 168\u2013172. IEEE.","DOI":"10.1109\/ICIP.2015.7350781"},{"issue":"7","key":"1293_CR58","doi-asserted-by":"publisher","first-page":"7034","DOI":"10.1109\/JSEN.2022.3150225","volume":"22","author":"X Chao","year":"2022","unstructured":"Chao X, Hou Z, Mo Y. Czu-mhad: a multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors. IEEE Sens J. 2022;22(7):7034\u201342.","journal-title":"IEEE Sens J"},{"key":"1293_CR59","unstructured":"Powers DMW. Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation. 2020. arXiv preprint arXiv:2010.16061."},{"issue":"8","key":"1293_CR60","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T. An introduction to roc analysis. Pattern Recogn Lett. 2006;27(8):861\u201374.","journal-title":"Pattern Recogn Lett"},{"issue":"11","key":"1293_CR61","first-page":"2579","volume":"9","author":"LVD Maaten","year":"2008","unstructured":"Maaten LVD, Hinton G. Visualizing data using t-sne. J Mach Learn Res. 2008;9(11):2579\u2013605.","journal-title":"J Mach Learn Res"},{"key":"1293_CR62","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis. 2020;128:336\u201359.","journal-title":"Int J Comput Vis"},{"key":"1293_CR63","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42452-021-04528-1","volume":"3","author":"MF Bulbul","year":"2021","unstructured":"Bulbul MF, Ali H. Gradient local auto-correlation features for depth human action recognition. SN Appl Sci. 2021;3:1\u201313.","journal-title":"SN Appl Sci"},{"issue":"21","key":"1293_CR64","doi-asserted-by":"publisher","first-page":"14551","DOI":"10.1007\/s00521-021-06097-1","volume":"33","author":"J Trelinski","year":"2021","unstructured":"Trelinski J, Kwolek B. Cnn-based and dtw features for human activity recognition on depth maps. Neural Comput Appl. 2021;33(21):14551\u201363.","journal-title":"Neural Comput Appl"},{"issue":"6","key":"1293_CR65","doi-asserted-by":"publisher","first-page":"1615","DOI":"10.1007\/s11760-021-02116-9","volume":"16","author":"M Sima","year":"2022","unstructured":"Sima M, Hou M, Zhang X, Ding J, Feng Z. Action recognition algorithm based on skeletal joint data and adaptive time pyramid. SIViP. 2022;16(6):1615\u201322.","journal-title":"SIViP"},{"issue":"9","key":"1293_CR66","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TSMC.2018.2850149","volume":"49","author":"A Kamel","year":"2018","unstructured":"Kamel A, Sheng B, Yang P, Li P, Shen R, Feng DD. Deep convolutional neural networks for human action recognition using depth maps and postures. IEEE Trans Syst Man Cybern Syst. 2018;49(9):1806\u201319.","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"3","key":"1293_CR67","first-page":"1250","volume":"32","author":"W Hanbo","year":"2021","unstructured":"Hanbo W, Ma X, Li Y. Spatiotemporal multimodal learning with 3D cnns for video action recognition. IEEE Trans Circuits Syst Video Technol. 2021;32(3):1250\u201361.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"18","key":"1293_CR68","doi-asserted-by":"publisher","first-page":"10681","DOI":"10.1007\/s00521-024-09630-0","volume":"36","author":"RMR Guddeti","year":"2024","unstructured":"Guddeti RMR. Human action recognition using multi-stream attention-based deep networks with heterogeneous data from overlapping sub-actions. Neural Comput Appl. 2024;36(18):10681\u201397.","journal-title":"Neural Comput Appl"},{"key":"1293_CR69","doi-asserted-by":"crossref","unstructured":"Haque ST, Ni J, Li J, Yan Y, Ngu AHH. Lighthart: lightweight human activity recognition transformer. In: International Conference on Pattern Recognition. Springer; 2024. p. 425\u2013441.","DOI":"10.1007\/978-3-031-78354-8_27"},{"key":"1293_CR70","doi-asserted-by":"crossref","unstructured":"Li J, Yao L, Li B, Wang X, Sammut C. Multi-agent transformer networks for multimodal human activity recognition. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2022. p. 1135\u20131145.","DOI":"10.1145\/3511808.3557402"},{"issue":"5","key":"1293_CR71","doi-asserted-by":"publisher","first-page":"1862","DOI":"10.1109\/JSEN.2018.2884443","volume":"19","author":"T Liu","year":"2018","unstructured":"Liu T, Kong J, Jiang M. Rgb-d action recognition using multimodal correlative representation learning model. IEEE Sens J. 2018;19(5):1862\u201372.","journal-title":"IEEE Sens J"},{"key":"1293_CR72","unstructured":"Zhuokun Z, Zhenjie H, Jiuzhen L, En L, Haiyong S. Multimodal cooperative self-attention network for action. IET Image Processing. 2023."},{"key":"1293_CR73","unstructured":"Li J, Yao L, Li B, Sammut C. Distilled mid-fusion transformer networks for multi-modal human activity recognition. 2023. arXiv preprint arXiv:2305.03810."},{"issue":"20","key":"1293_CR74","doi-asserted-by":"publisher","first-page":"10133","DOI":"10.1007\/s10489-024-05719-0","volume":"54","author":"H Wang","year":"2024","unstructured":"Wang H, Bai B, Li J, Ke H, Xiang W. Action recognition method based on multi-stream attention-enhanced recursive graph convolution. Appl Intell. 2024;54(20):10133\u201347.","journal-title":"Appl Intell"},{"issue":"1","key":"1293_CR75","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1109\/JSEN.2022.3225031","volume":"23","author":"H Shi","year":"2022","unstructured":"Shi H, Hou Z, Liang J, Lin E, Zhong Z. Dsfnet: a distributed sensors fusion network for action recognition. IEEE Sens J. 2022;23(1):839\u201348.","journal-title":"IEEE Sens J"},{"key":"1293_CR76","unstructured":"Kamboj A, Nguyen AD, Do M. C3t: cross-modal transfer through time for human action recognition. 2024. arXiv preprint arXiv:2407.16803."}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01293-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-025-01293-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01293-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:10:10Z","timestamp":1758625810000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-025-01293-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,23]]},"references-count":76,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1293"],"URL":"https:\/\/doi.org\/10.1186\/s40537-025-01293-5","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,23]]},"assertion":[{"value":"8 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals carried out by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"217"}}