{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T08:19:35Z","timestamp":1783585175976,"version":"3.55.0"},"reference-count":84,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-58924-x","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:05:01Z","timestamp":1783577101000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimized multi-modal action recognition using multi-agent systems and adaptive temporal attention"],"prefix":"10.1038","volume":"16","author":[{"given":"Essam H.","family":"Houssein","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed A.","family":"Mahdy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed","family":"Kayed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nagwan Abdel","family":"Samee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Waleed M.","family":"Mohamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"issue":"3","key":"58924_CR1","first-page":"3200","volume":"45","author":"Z Sun","year":"2022","unstructured":"Sun, Z. et al. Human action recognition from various data modalities: A review. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3200\u20133225 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"58924_CR2","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/34.910878","volume":"23","author":"AF Bobick","year":"2001","unstructured":"Bobick, A. F. & Davis, J. W. The recognition of human movement using temporal templates. IEEE Trans. Pattern Anal. Mach. Intell. 23(3), 257\u2013267 (2001).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"58924_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 Mult. 19(2), 4\u201310 (2012).","journal-title":"IEEE Mult."},{"key":"58924_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, D. Q. & Koniusz, P. A comparative review of recent kinect-based action recognition algorithms. IEEE Trans. Image Process. 29, 15\u201328 (2019).","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"58924_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, P. P. & Majumdar, A. K. Characterizations of noise in kinect depth images: A review. IEEE Sens. J. 14(6), 1731\u20131740 (2014).","journal-title":"IEEE Sens. J."},{"key":"58924_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 8, 15280\u201315290 (2020).","journal-title":"IEEE Access"},{"issue":"3","key":"58924_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1922649.1922653","volume":"43","author":"JK Aggarwal","year":"2011","unstructured":"Aggarwal, J. K. & Ryoo, M. S. Human activity analysis: A review. ACM Comput. Surv. 43(3), 1\u201343 (2011).","journal-title":"ACM Comput. Surv."},{"key":"58924_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. Knowledge-Based Syst. 158, 43\u201353 (2018).","journal-title":"Knowledge-Based Syst."},{"issue":"5","key":"58924_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. 24(5), 624\u2013628 (2017).","journal-title":"IEEE Signal Process. Lett."},{"key":"58924_CR10","doi-asserted-by":"crossref","unstructured":"Yang, X. & Tian, Y. Super normal vector for activity recognition using depth sequences. Proceedings of the IEEE conference on computer vision and pattern recognition 804\u2013811 (2014).","DOI":"10.1109\/CVPR.2014.108"},{"issue":"10","key":"58924_CR11","doi-asserted-by":"publisher","first-page":"4648","DOI":"10.1109\/TIP.2017.2718189","volume":"26","author":"B Zhang","year":"2017","unstructured":"Zhang, B. et al. Action recognition using 3d histograms of texture and a multi-class boosting classifier. IEEE Trans. Image process. 26(10), 4648\u20134660 (2017).","journal-title":"IEEE Trans. Image process."},{"key":"58924_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.10.004","volume":"93","author":"Y Gu","year":"2020","unstructured":"Gu, Y., Ye, X., Sheng, W., Ou, Y. & Li, Y. Multiple stream deep learning model for human action recognition. Image Vis. Comput. 93, 103818 (2020).","journal-title":"Image Vis. Comput."},{"key":"58924_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. et al. Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015).","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"58924_CR14","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1186\/s40537-022-00664-6","volume":"9","author":"D Naik","year":"2022","unstructured":"Naik, D. & Jaidhar, C. A novel multi-layer attention framework for visual description prediction using bidirectional lstm. J. Big Data 9(1), 104 (2022).","journal-title":"J. Big Data"},{"key":"58924_CR15","unstructured":"Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30"},{"key":"58924_CR16","doi-asserted-by":"crossref","unstructured":"Karpathy, A. et al. Large-scale video classification with convolutional neural networks. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition 1725\u20131732 (2014).","DOI":"10.1109\/CVPR.2014.223"},{"key":"58924_CR17","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A. & Zisserman, A. Convolutional two-stream network fusion for video action recognition. Proceedings of the IEEE conference on computer vision and pattern recognition 1933\u20131941 (2016).","DOI":"10.1109\/CVPR.2016.213"},{"issue":"11","key":"58924_CR18","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L. et al. Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2740\u20132755 (2018).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"58924_CR19","doi-asserted-by":"crossref","unstructured":"Zeng, M. et al. Convolutional neural networks for human activity recognition using mobile sensors, in 6th international conference on mobile computing, applications and services. IEEE , 197\u2013205 (2014).","DOI":"10.4108\/icst.mobicase.2014.257786"},{"issue":"1","key":"58924_CR20","doi-asserted-by":"publisher","first-page":"115","DOI":"10.3390\/s16010115","volume":"16","author":"FJ Ord\u00f3\u00f1ez","year":"2016","unstructured":"Ord\u00f3\u00f1ez, F. J. & Roggen, D. Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1), 115 (2016).","journal-title":"Sensors"},{"key":"58924_CR21","unstructured":"Dong, X. & Yang, Y. Nas-bench-201: Extending the scope of reproducible neural architecture searcharXiv:2001.00326 arXiv preprint."},{"issue":"2","key":"58924_CR22","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. 24(2), 1717\u20131729 (2023).","journal-title":"IEEE Sens. J."},{"key":"58924_CR23","unstructured":"D.\u00a0W. Romero, R.-J. Bruintjes, J.\u00a0M. Tomczak, E.\u00a0J. Bekkers, M.\u00a0Hoogendoorn, J.\u00a0C. van Gemert, Flexconv: Continuous kernel convolutions with differentiable kernel sizes, arXiv preprint arXiv:2110.08059."},{"issue":"5","key":"58924_CR24","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. 32(5), 829\u2013864 (2020).","journal-title":"Neural Comput."},{"key":"58924_CR25","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. & Hu, L. Deep learning for sensor-based activity recognition: A survey. Pattern Recognit. Lett. 119, 3\u201311 (2019).","journal-title":"Pattern Recognit. Lett."},{"issue":"21","key":"58924_CR26","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. 21(21), 24653\u201324664 (2021).","journal-title":"IEEE Sens. J."},{"issue":"4","key":"58924_CR27","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. & Hu, S. Skeleton-based fall detection with multiple inertial sensors using spatial-temporal graph convolutional networks. Sensors 23(4), 2153 (2023).","journal-title":"Sensors"},{"issue":"19","key":"58924_CR28","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. 80(19), 28919\u201328940 (2021).","journal-title":"Multimed. Tools Appl."},{"key":"58924_CR29","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. Pattern Recognit. Lett. 115, 107\u2013116 (2018).","journal-title":"Pattern Recognit. Lett."},{"key":"58924_CR30","doi-asserted-by":"crossref","unstructured":"Rehman, S.U., Yasin, A.U., Ul Haq E., 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 24, 4646 (2024).","DOI":"10.3390\/s24144646"},{"key":"58924_CR31","doi-asserted-by":"crossref","unstructured":"Tagmouni, A., Elmir, Y., & Kechadi M.\u00a0T. 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), IEEE, 12, pp. 1\u20136. (2024)","DOI":"10.1109\/ICSPIS63676.2024.10812599"},{"key":"58924_CR32","unstructured":"Batool, M., Alotaibi, M., Alotaibi, S.R., AlHammadi, D.A., Jamal, M.A., Jalal, A., & Lee, B. Multimodal human action recognition framework using an improved cnngru classifier. IEEE Access."},{"key":"58924_CR33","doi-asserted-by":"crossref","unstructured":"Haque, S.T., & Ngu, A.H. Poster: Multimodal convtransformer for human activity recognition, in: 2024 IEEE\/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), IEEE, pp. 206\u2013207. (2024)","DOI":"10.1109\/CHASE60773.2024.00041"},{"key":"58924_CR34","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., Gu, Y. & Chao, X. Depth sequential information entropy maps and multi-label subspace learning for human action recognition. IEEE Access 8, 135118\u2013135130 (2020).","journal-title":"IEEE Access"},{"key":"58924_CR35","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1105","volume":"8","author":"M Javeed","year":"2022","unstructured":"Javeed, M. et al. Physical human locomotion prediction using manifold regularization. PeerJ Comput. Sci. 8, e1105 (2022).","journal-title":"PeerJ Comput. Sci."},{"key":"58924_CR36","doi-asserted-by":"crossref","unstructured":"Ni, J., Ngu, A.H., Yan, Y. (2022) Progressive cross-modal knowledge distillation for human action recognition, in: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5903\u20135912.","DOI":"10.1145\/3503161.3548238"},{"issue":"3","key":"58924_CR37","doi-asserted-by":"publisher","first-page":"768","DOI":"10.3390\/s21030768","volume":"21","author":"CM Ranieri","year":"2021","unstructured":"Ranieri, C. M., MacLeod, S., Dragone, M., Vargas, P. A. & Romero, R. A. F. Activity recognition for ambient assisted living with videos, inertial units and ambient sensors. Sensors 21(3), 768 (2021).","journal-title":"Sensors"},{"key":"58924_CR38","unstructured":"Wooldridge, M. An Introduction to Multiagent Systems (Wiley, 2009)."},{"key":"58924_CR39","unstructured":"Weiss, G. Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence (MIT press, 1999)."},{"key":"58924_CR40","unstructured":"Russell, S.J. & Norvig, P. Artificial Intelligence: A Modern Approach (Pearson, 2016)."},{"key":"58924_CR41","unstructured":"Ferber, J. Multi-agent systems: an introduction to distributed artificial intelligence(No Title)."},{"key":"58924_CR42","doi-asserted-by":"crossref","unstructured":"Esmaeili, A., Ghorrati, Z., & Matson, E.T. Distributed agent-based collaborative learning in cross-individual wearable sensor-based human activity recognition, in: 2023 Seventh IEEE International Conference on Robotic Computing (IRC), IEEE, pp. 381\u2013388 (2023)","DOI":"10.1109\/IRC59093.2023.00068"},{"key":"58924_CR43","doi-asserted-by":"crossref","unstructured":"Mocanu,I., & Florea, A.M. A multi-agent system for human activity recognition in smart environments, in: Intelligent Distributed Computing V: Proceedings of the 5th International Symposium on Intelligent Distributed Computing\u2013IDC 2011, Delft, The Netherlands\u2013October 2011, Springer, pp. 291\u2013301 ( 2011)","DOI":"10.1007\/978-3-642-24013-3_31"},{"issue":"7","key":"58924_CR44","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1016\/j.engappai.2011.06.007","volume":"24","author":"F Aiello","year":"2011","unstructured":"Aiello, F., Bellifemine, F. L., Fortino, G., Galzarano, S. & Gravina, R. An agent-based signal processing in-node environment for real-time human activity monitoring based on wireless body sensor networks. Engi. Appl. Artifi. Intell. 24(7), 1147\u20131161 (2011).","journal-title":"Engi. Appl. Artifi. Intell."},{"key":"58924_CR45","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, pp. 1135\u20131145 (2022).","DOI":"10.1145\/3511808.3557402"},{"issue":"17","key":"58924_CR46","doi-asserted-by":"publisher","first-page":"10835","DOI":"10.1007\/s00521-025-10978-0","volume":"37","author":"M Jayamohan","year":"2025","unstructured":"Jayamohan, M. & Yuvaraj, S. A novel human action recognition using grad-cam visualization with gated recurrent units. Neural Comput. Appl. 37(17), 10835\u201310850 (2025).","journal-title":"Neural Comput. Appl."},{"issue":"1","key":"58924_CR47","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/s44196-025-00848-x","volume":"18","author":"J Manoharan","year":"2025","unstructured":"Manoharan, J. & Sivagnanam, Y. A novel human action recognition model by grad-cam visualization with multi-level feature extraction using global average pooling with sequence modeling by bidirectional gated recurrent units. Int. J. Comput. Intell. Syst. 18(1), 118 (2025).","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"58924_CR48","doi-asserted-by":"crossref","unstructured":"M.\u00a0Jayamohan, & S.\u00a0Yuvaraj, Video-based action recognition of spatial and temporal deep learning models, in: International Conference on Advances in Data-driven Computing and Intelligent Systems, Springer, 2023, pp. 379\u2013391.","DOI":"10.1007\/978-981-99-9524-0_29"},{"issue":"2","key":"58924_CR49","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1007\/s11760-024-03726-9","volume":"19","author":"M Jayamohan","year":"2025","unstructured":"Jayamohan, M. & Yuvaraj, S. Iv3-mgrua: A novel human action recognition features extraction using inception v3 and video behaviour prediction using modified gated recurrent units with attention mechanism model, Signal. Image Video Process. 19(2), 134 (2025).","journal-title":"Image Video Process."},{"key":"58924_CR50","doi-asserted-by":"crossref","unstructured":"Manoharan, J., & Sivagnanam, Y. Enhanced hand gesture recognition using optimized preprocessing and vgg16-based deep learning model, in: 2024 10th International Conference on Communication and Signal Processing (ICCSP), IEEE, pp. 1101\u20131105 (2024)","DOI":"10.1109\/ICCSP60870.2024.10543590"},{"key":"58924_CR51","doi-asserted-by":"crossref","unstructured":"Tatarenkov, D., & Buchatsky, A. Feature extraction from a depth map for human detection, in: 2018Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO), IEEE, pp. 1\u20134 (2018)","DOI":"10.1109\/SYNCHROINFO.2018.8456984"},{"key":"58924_CR52","unstructured":"Tabussum, S., Al Amin, J.B., & Bulbul, M.F. Searching human action recognition accuracy from depth video sequences using hog and phog shape features."},{"key":"58924_CR53","doi-asserted-by":"crossref","unstructured":"Ali, H.H., Youssif, A.A., & Moftah, H.M. Statistical hog on multi-temporal depth motion maps approach for human action recognition, in: Proceedings of the XX International Conference on Human Computer Interaction, 1\u20138 (2019)","DOI":"10.1145\/3335595.3335624"},{"key":"58924_CR54","doi-asserted-by":"crossref","unstructured":"Ganesh, D., Teja, R.R., Reddy, C.D., & Swathi, D. Human action recognition based on depth maps, skeleton and sensor images using deep learning, in, IEEE 3rd Global Conference for Advancement in Technology (GCAT). IEEE 2022, pp. 1\u20138 (2022).","DOI":"10.1109\/GCAT55367.2022.9971982"},{"key":"58924_CR55","doi-asserted-by":"crossref","unstructured":"Chen, C., Jafari, R., & Kehtarnavaz, N.  Fusion of depth, skeleton, and inertial data for human action recognition, in IEEE international conference on acoustics, speech and signal processing (ICASSP) 2016, pp. 2712\u20132716 (2016).","DOI":"10.1109\/ICASSP.2016.7472170"},{"key":"58924_CR56","unstructured":"Tieleman, T. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA 4, 26 (2012)."},{"key":"58924_CR57","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. Deep Learning (MIT press, 2016)."},{"key":"58924_CR58","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B.  Histograms of oriented gradients for human detection, in IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905), Vol. 1.  2005, 886\u2013893 (2005).","DOI":"10.1109\/CVPR.2005.177"},{"key":"58924_CR59","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhang, C., Tian, Y. Recognizing actions using depth motion maps-based histograms of oriented gradients, in Proceedings of the 20th ACM international conference on Multimedia, 1057\u20131060 (2012)","DOI":"10.1145\/2393347.2396382"},{"key":"58924_CR60","doi-asserted-by":"crossref","unstructured":"Rush, A., Wood, S.L. Focal plane processing for hog detection with bayer pattern sensors, in 2016 50th Asilomar Conference on Signals, Systems and Computers, IEEE, 1603\u20131607 (2016)","DOI":"10.1109\/ACSSC.2016.7869650"},{"issue":"3","key":"58924_CR61","doi-asserted-by":"publisher","first-page":"88","DOI":"10.3390\/robotics12030088","volume":"12","author":"NJB Dias","year":"2023","unstructured":"Dias, N. J. B., Laureano, G. T. & Da Costa, R. M. Keyframe selection for visual localization and mapping tasks: A systematic literature review. Robotics 12(3), 88 (2023).","journal-title":"Robotics"},{"key":"58924_CR62","doi-asserted-by":"crossref","unstructured":"Nikpour, B., & Armanfard, N. Joint selection using deep reinforcement learning for skeleton-based activity recognition, in 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), IEEE,1056\u20131061 (2021)","DOI":"10.1109\/SMC52423.2021.9659047"},{"issue":"4","key":"58924_CR63","doi-asserted-by":"publisher","first-page":"4659","DOI":"10.1007\/s40747-024-01403-5","volume":"10","author":"H Chen","year":"2024","unstructured":"Chen, H., Pan, Y. & Wang, C. An optimization method of human skeleton keyframes selection for action recognition. Compl. Intell. Syst. 10(4), 4659\u20134673 (2024).","journal-title":"Compl. Intell. Syst."},{"issue":"21","key":"58924_CR64","doi-asserted-by":"publisher","first-page":"9947","DOI":"10.3390\/app14219947","volume":"14","author":"J Hou","year":"2024","unstructured":"Hou, J., Su, L. & Zhao, Y. Key frame selection for temporal graph optimization of skeleton-based action recognition. Appl. Sci. 14(21), 9947 (2024).","journal-title":"Appl. Sci."},{"issue":"4","key":"58924_CR65","doi-asserted-by":"publisher","first-page":"3279","DOI":"10.1109\/TKDE.2021.3126456","volume":"35","author":"G Brauwers","year":"2021","unstructured":"Brauwers, G. & Frasincar, F. A general survey on attention mechanisms in deep learning. IEEE Trans. Knowl. Data Eng. 35(4), 3279\u20133298 (2021).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"58924_CR66","unstructured":"Ioffe, S. & Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. International conference on machine learning, pmlr 448\u2013456 (2015)."},{"issue":"1","key":"58924_CR67","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. 13(1), 281\u2013305 (2012).","journal-title":"J. Mach. Learn. Res."},{"key":"58924_CR68","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, 2623\u20132631(2019)","DOI":"10.1145\/3292500.3330701"},{"key":"58924_CR69","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 IEEE International conference on image processing (ICIP) 2015, 168\u2013172 (2015).","DOI":"10.1109\/ICIP.2015.7350781"},{"issue":"7","key":"58924_CR70","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. 22(7), 7034\u20137042 (2022).","journal-title":"IEEE Sens. J."},{"key":"58924_CR71","unstructured":"Powers, D. M. Evaluation: From precision, recall and f-measure to roc, informedness, markedness and correlationarXiv:2010.16061 arXiv preprint."},{"issue":"8","key":"58924_CR72","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. Patt. Recogn. Lett. 27(8), 861\u2013874 (2006).","journal-title":"Patt. Recogn. Lett."},{"key":"58924_CR73","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42452-021-04528-1","volume":"3","author":"MF Bulbul","year":"2021","unstructured":"Bulbul, M. F. & Ali, H. Gradient local auto-correlation features for depth human action recognition. SN Appl. Sci. 3, 1\u201313 (2021).","journal-title":"SN Appl. Sci."},{"key":"58924_CR74","doi-asserted-by":"crossref","unstructured":"Liu, M. & Yuan, J. Recognizing human actions as the evolution of pose estimation maps. in Proceedings of the IEEE conference on computer vision and pattern recognition 1159\u20131168 (2018).","DOI":"10.1109\/CVPR.2018.00127"},{"issue":"21","key":"58924_CR75","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. 33(21), 14551\u201314563 (2021).","journal-title":"Neural Comput. Appl."},{"issue":"6","key":"58924_CR76","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. Signal Image Video Process. 16(6), 1615\u20131622 (2022).","journal-title":"Signal Image Video Process."},{"issue":"9","key":"58924_CR77","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TSMC.2018.2850149","volume":"49","author":"A Kamel","year":"2018","unstructured":"Kamel, A. et al. Deep convolutional neural networks for human action recognition using depth maps and postures. IEEE Trans. Syst. Man Cybern. Syst. 49(9), 1806\u20131819 (2018).","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"3","key":"58924_CR78","doi-asserted-by":"publisher","first-page":"1250","DOI":"10.1109\/TCSVT.2021.3077512","volume":"32","author":"H Wu","year":"2021","unstructured":"Wu, H., Ma, X. & Li, Y. Spatiotemporal multimodal learning with 3D cnns for video action recognition. IEEE Trans. Circ. Syst. Video Technol. 32(3), 1250\u20131261 (2021).","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"issue":"18","key":"58924_CR79","doi-asserted-by":"publisher","first-page":"10681","DOI":"10.1007\/s00521-024-09630-0","volume":"36","author":"RMR Guddeti","year":"2024","unstructured":"Guddeti, R. M. R. Human action recognition using multi-stream attention-based deep networks with heterogeneous data from overlapping sub-actions. Neural Comput. Appl. 36(18), 10681\u201310697 (2024).","journal-title":"Neural Comput. Appl."},{"key":"58924_CR80","unstructured":"Abro, I. A. et al. Advanced biosignal-rgb fusion with adaptive neurofuzzy classification for high-precision action recognition (IEEE Access, )."},{"issue":"1","key":"58924_CR81","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. 23(1), 839\u2013848 (2022).","journal-title":"IEEE Sens. J."},{"issue":"20","key":"58924_CR82","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. 54(20), 10133\u201310147 (2024).","journal-title":"Appl. Intell."},{"key":"58924_CR83","unstructured":"Kamboj, A., Nguyen, A. D. & Do, M. C3t: Cross-modal transfer through time for human action recognitionarXiv:2407.16803 arXiv preprint."},{"issue":"1","key":"58924_CR84","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1186\/s40537-025-01293-5","volume":"12","author":"EH Houssein","year":"2025","unstructured":"Houssein, E. H. et al. Optimizing action recognition: A residual convolution with hierarchical and gram matrix based attention mechanisms. J. Big Data 12(1), 217 (2025).","journal-title":"J. Big Data"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58924-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58924-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58924-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T08:02:36Z","timestamp":1783584156000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58924-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":84,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["58924"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-58924-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]},"assertion":[{"value":"23 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"The authors declare no competing interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interest"}}],"article-number":"21396"}}