{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T08:01:29Z","timestamp":1761984089997,"version":"build-2065373602"},"reference-count":101,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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":["J Intell Manuf"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s10845-024-02518-9","type":"journal-article","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T01:11:39Z","timestamp":1732151499000},"page":"5629-5672","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Proposing a cross-correlational-gated recurrent unit neural network for engine block assembly action recognition"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7288-8112","authenticated-orcid":false,"given":"Davar","family":"Giveki","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"2518_CR1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3249152","author":"T Ahmad","year":"2023","unstructured":"Ahmad, T., & Wu, J. (2023). SDIGRU: Spatial and deep features integration using multilayer gated recurrent unit for human activity recognition. IEEE Transactions on Computational Social Systems. https:\/\/doi.org\/10.1109\/TCSS.2023.3249152","journal-title":"IEEE Transactions on Computational Social Systems"},{"key":"2518_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01815-x","author":"M Al-Amin","year":"2023","unstructured":"Al-Amin, M., Qin, R., Moniruzzaman, M., Yin, Z., Tao, W., & Leu, M. C. (2023). An individualized system of skeletal data-based CNN classifiers for action recognition in manufacturing assembly. Journal of Intelligent Manufacturing. https:\/\/doi.org\/10.1007\/s10845-021-01815-x","journal-title":"Journal of Intelligent Manufacturing"},{"key":"2518_CR3","unstructured":"Aparat, Tutorial of complete engine repairing. Retrieved 4, 2023, from https:\/\/www.aparat.com\/v\/e1nzs, http:\/\/www.aparat.com\/Me.ziaee"},{"key":"2518_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3302353","author":"U Azmat","year":"2023","unstructured":"Azmat, U., Alotaibi, S. S., Abdelhaq, M., Alsufyani, N., Shorfuzzaman, M., Jalal, A., & Park, J. (2023). Aerial insights: Deep learning-based human action recognition in drone imagery. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2023.3302353","journal-title":"IEEE Access"},{"issue":"1479","key":"2518_CR5","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1098\/rstb.2006.1964","volume":"362","author":"A Borst","year":"2007","unstructured":"Borst, A. (2007). Correlation versus gradient type motion detectors: The pros and cons. Philosophical Transactions of the Royal Society B: Biological Sciences, 362(1479), 369\u2013374. https:\/\/doi.org\/10.1098\/rstb.2006.1964","journal-title":"Philosophical Transactions of the Royal Society B: Biological Sciences"},{"issue":"7","key":"2518_CR6","doi-asserted-by":"publisher","first-page":"3053","DOI":"10.1007\/s10845-022-01989-y","volume":"34","author":"J Cacace","year":"2023","unstructured":"Cacace, J., Caccavale, R., Finzi, A., & Grieco, R. (2023). Combining human guidance and structured task execution during physical human\u2013robot collaboration. Journal of Intelligent Manufacturing, 34(7), 3053\u20133067. https:\/\/doi.org\/10.1007\/s10845-022-01989-y","journal-title":"Journal of Intelligent Manufacturing"},{"issue":"4","key":"2518_CR7","doi-asserted-by":"publisher","first-page":"85","DOI":"10.3390\/jimaging10040085","volume":"10","author":"F Camarena","year":"2024","unstructured":"Camarena, F., Gonzalez-Mendoza, M., & Chang, L. (2024). Knowledge distillation in video-based human action recognition: An intuitive approach to efficient and flexible model training. Journal of Imaging, 10(4), 85. https:\/\/doi.org\/10.3390\/jimaging10040085","journal-title":"Journal of Imaging"},{"issue":"4","key":"2518_CR8","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1007\/s11760-022-02324-x","volume":"17","author":"H Cao","year":"2023","unstructured":"Cao, H., Wu, C., Lu, J., Wu, J., & Wang, L. (2023). Spatial\u2013temporal injection network: Exploiting auxiliary losses for action recognition with apparent difference and self-attention. Signal, Image and Video Processing, 17(4), 1173\u20131180. https:\/\/doi.org\/10.1007\/s11760-022-02324-x","journal-title":"Signal, Image and Video Processing"},{"key":"2518_CR9","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.neucom.2021.07.088","volume":"462","author":"J Chen","year":"2021","unstructured":"Chen, J., Li, Z., Jin, Y., Ren, D., & Ling, H. (2021). Video saliency prediction via spatio-temporal reasoning. Neurocomputing, 462, 59\u201368. https:\/\/doi.org\/10.1016\/j.neucom.2021.07.088","journal-title":"Neurocomputing"},{"key":"2518_CR10","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. Preprint at arXiv:1406.1078.","DOI":"10.3115\/v1\/D14-1179"},{"key":"2518_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122220","volume":"238","author":"AC Cob-Parro","year":"2024","unstructured":"Cob-Parro, A. C., Losada-Guti\u00e9rrez, C., Marr\u00f3n-Romera, M., Gardel-Vicente, A., & Bravo-Mu\u00f1oz, I. (2024). A new framework for deep learning video based human action recognition on the edge. Expert Systems with Applications, 238, 122220. https:\/\/doi.org\/10.1016\/j.eswa.2023.122220","journal-title":"Expert Systems with Applications"},{"key":"2518_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.105820","volume":"86","author":"C Dai","year":"2020","unstructured":"Dai, C., Liu, X., & Lai, J. (2020). Human action recognition using two-stream attention based LSTM networks. Applied Soft Computing, 86, 105820. https:\/\/doi.org\/10.1016\/j.asoc.2019.105820","journal-title":"Applied Soft Computing"},{"key":"2518_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.111166","volume":"151","author":"C Dai","year":"2024","unstructured":"Dai, C., Lu, S., Liu, C., & Guo, B. (2024). A light-weight skeleton human action recognition model with knowledge distillation for edge intelligent surveillance applications. Applied Soft Computing, 151, 111166. https:\/\/doi.org\/10.1016\/j.asoc.2023.111166","journal-title":"Applied Soft Computing"},{"key":"2518_CR14","doi-asserted-by":"publisher","DOI":"10.1155\/2024\/1052344","author":"E Dastbaravardeh","year":"2024","unstructured":"Dastbaravardeh, E., Askarpour, S., Saberi Anari, M., & Rezaee, K. (2024). Channel attention-based approach with autoencoder network for human action recognition in low-resolution frames. International Journal of Intelligent Systems. https:\/\/doi.org\/10.1155\/2024\/1052344","journal-title":"International Journal of Intelligent Systems"},{"key":"2518_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-024-02462-8","author":"P Ding","year":"2024","unstructured":"Ding, P., Zhang, J., Zheng, P., Zhang, P., Fei, B., & Xu, Z. (2024). Dynamic scenario-enhanced diverse human motion prediction network for proactive human\u2013robot collaboration in customized assembly tasks. Journal of Intelligent Manufacturing. https:\/\/doi.org\/10.1007\/s10845-024-02462-8","journal-title":"Journal of Intelligent Manufacturing"},{"key":"2518_CR16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316","author":"A Dosovitskiy","year":"2015","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., & Brox, T. (2015). Flownet: Learning optical flow with convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision. https:\/\/doi.org\/10.1109\/ICCV.2015.316","journal-title":"In Proceedings of the IEEE International Conference on Computer Vision"},{"key":"2518_CR17","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1007\/s00607-021-00928-8","volume":"103","author":"N Dua","year":"2021","unstructured":"Dua, N., Singh, S. N., & Semwal, V. B. (2021). Multi-input CNN-GRU based human activity recognition using wearable sensors. Computing, 103, 1461\u20131478. https:\/\/doi.org\/10.1007\/s00607-021-00928-8","journal-title":"Computing"},{"key":"2518_CR18","doi-asserted-by":"publisher","first-page":"22445","DOI":"10.1007\/s11042-017-4795-6","volume":"76","author":"IC Duta","year":"2017","unstructured":"Duta, I. C., Uijlings, R., Ionescu, J. R., Aizawa, B., & HauptmannSebe, K. G. A. N. (2017). Efficient human action recognition using histograms of motion gradients and VLAD with descriptor shape information. Multimedia Tools and Applications, 76, 22445\u201322472. https:\/\/doi.org\/10.1007\/s11042-017-4795-6","journal-title":"Multimedia Tools and Applications"},{"key":"2518_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-024-02362-x","author":"A Dzedzickis","year":"2024","unstructured":"Dzedzickis, A., Vai\u010di\u016bnas, G., Lapkauskait\u0117, K., Vir\u017eonis, D., & Bu\u010dinskas, V. (2024). Recent advances in human\u2013robot interaction: robophobia or synergy. Journal of Intelligent Manufacturing. https:\/\/doi.org\/10.1007\/s10845-024-02362-x","journal-title":"Journal of Intelligent Manufacturing"},{"key":"2518_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-023-02228-8","author":"C Gkournelos","year":"2023","unstructured":"Gkournelos, C., Konstantinou, C., Angelakis, P., Tzavara, E., & Makris, S. (2023). Praxis: A framework for AI-driven human action recognition in assembly. Journal of Intelligent Manufacturing. https:\/\/doi.org\/10.1007\/s10845-023-02228-8","journal-title":"Journal of Intelligent Manufacturing"},{"key":"2518_CR21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622","author":"R Goyal","year":"2017","unstructured":"Goyal, R., Ebrahimi Kahou, S., Michalski, V., Materzynska, J., Westphal, S., Kim, H., & Memisevic, R. (2017). The\" something something\" video database for learning and evaluating visual common sense. In Proceedings of the IEEE International Conference on Computer Vision. https:\/\/doi.org\/10.1109\/ICCV.2017.622","journal-title":"In Proceedings of the IEEE International Conference on Computer Vision"},{"key":"2518_CR22","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3265128","author":"C Han","year":"2023","unstructured":"Han, C., Zhang, L., Xu, S., Wang, X., Wu, H., & Song, A. (2023). An Efficient diverse-branch convolution scheme for sensor-based human activity recognition. IEEE Transactions on Instrumentation and Measurement. https:\/\/doi.org\/10.1109\/TIM.2023.3265128","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"2518_CR23","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.neucom.2020.05.118","volume":"444","author":"JY He","year":"2021","unstructured":"He, J. Y., Wu, X., Cheng, Z. Q., Yuan, Z., & Jiang, Y. G. (2021). DB-LSTM: Densely-connected Bi-directional LSTM for human action recognition. Neurocomputing, 444, 319\u2013331. https:\/\/doi.org\/10.1016\/j.neucom.2020.05.118","journal-title":"Neurocomputing"},{"issue":"3","key":"2518_CR24","doi-asserted-by":"publisher","first-page":"1833","DOI":"10.1007\/s10462-022-10210-8","volume":"56","author":"K Hu","year":"2023","unstructured":"Hu, K., Jin, J., Zheng, F., Weng, L., & Ding, Y. (2023). Overview of behavior recognition based on deep learning. Artificial Intelligence Review, 56(3), 1833\u20131865. https:\/\/doi.org\/10.1007\/s10462-022-10210-8","journal-title":"Artificial Intelligence Review"},{"key":"2518_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122314","volume":"239","author":"Z Hu","year":"2024","unstructured":"Hu, Z., Xiao, J., Li, L., Liu, C., & Ji, G. (2024). Human-centric multimodal fusion network for robust action recognition. Expert Systems with Applications, 239, 122314. https:\/\/doi.org\/10.1016\/j.eswa.2023.122314","journal-title":"Expert Systems with Applications"},{"key":"2518_CR26","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3454167","author":"A Hussain","year":"2022","unstructured":"Hussain, A., Hussain, T., Ullah, W., & Baik, S. W. (2022). Vision Transformer and deep sequence learning for human activity recognition in surveillance videos. Computational Intelligence and Neuroscience. https:\/\/doi.org\/10.1155\/2022\/3454167","journal-title":"Computational Intelligence and Neuroscience"},{"key":"2518_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106060","author":"MM Islam","year":"2022","unstructured":"Islam, M. M., Nooruddin, S., Karray, F., & Muhammad, G. (2022). Human activity recognition using tools of convolutional neural networks: A state of the art review, data sets, challenges, and future prospects. Computers in Biology and Medicine. https:\/\/doi.org\/10.1016\/j.compbiomed.2022.106060","journal-title":"Computers in Biology and Medicine"},{"issue":"2","key":"2518_CR28","doi-asserted-by":"publisher","first-page":"842","DOI":"10.3390\/make6020040","volume":"6","author":"M Kaseris","year":"2024","unstructured":"Kaseris, M., Kostavelis, I., & Malassiotis, S. (2024). A comprehensive survey on deep learning methods in human activity recognition. Machine Learning and Knowledge Extraction, 6(2), 842\u2013876. https:\/\/doi.org\/10.3390\/make6020040","journal-title":"Machine Learning and Knowledge Extraction"},{"issue":"5","key":"2518_CR29","doi-asserted-by":"publisher","first-page":"14885","DOI":"10.1007\/s11042-020-08806-9","volume":"83","author":"MA Khan","year":"2024","unstructured":"Khan, M. A., Javed, K., Khan, S. A., Saba, T., Habib, U., Khan, J. A., & Abbasi, A. A. (2024). Human action recognition using fusion of multiview and deep features: An application to video surveillance. Multimedia Tools and Applications, 83(5), 14885\u201314911. https:\/\/doi.org\/10.1007\/s11042-020-08806-9","journal-title":"Multimedia Tools and Applications"},{"key":"2518_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105702","volume":"118","author":"G Khodabandelou","year":"2023","unstructured":"Khodabandelou, G., Moon, H., Amirat, Y., & Mohammed, S. (2023). A fuzzy convolutional attention-based GRU network for human activity recognition. Engineering Applications of Artificial Intelligence, 118, 105702. https:\/\/doi.org\/10.1016\/j.engappai.2022.105702","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"2518_CR31","doi-asserted-by":"crossref","unstructured":"Kim, M., Seo, P. H., Schmid, C., & Cho, M. (2024). Learning correlation structures for vision transformers. Preprint at arXiv:2404.03924.","DOI":"10.1109\/CVPR52733.2024.01792"},{"key":"2518_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2021.101399","volume":"50","author":"S Kim","year":"2021","unstructured":"Kim, S., Hwang, S., & Hong, S. H. (2021). Identifying shoplifting behaviors and inferring behavior intention based on human action detection and sequence analysis. Advanced Engineering Informatics, 50, 101399. https:\/\/doi.org\/10.1016\/j.aei.2021.101399","journal-title":"Advanced Engineering Informatics"},{"key":"2518_CR33","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-023-02150-z","author":"H Kou","year":"2023","unstructured":"Kou, H., Shi, H., & Zhao, H. (2023). Subspace and second-order statistical distribution alignment for cross-domain recognition of human hand motions. Journal of Intelligent Manufacturing. https:\/\/doi.org\/10.1007\/s10845-023-02150-z","journal-title":"Journal of Intelligent Manufacturing"},{"issue":"1","key":"2518_CR34","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1162\/08989290051137594","volume":"12","author":"Z Kourtzi","year":"2000","unstructured":"Kourtzi, Z., & Kanwisher, N. (2000). Activation in human MT\/MST by static images with implied motion. Journal of Cognitive Neuroscience, 12(1), 48\u201355. https:\/\/doi.org\/10.1162\/08989290051137594","journal-title":"Journal of Cognitive Neuroscience"},{"key":"2518_CR35","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.procir.2018.03.130","volume":"72","author":"N Kousi","year":"2018","unstructured":"Kousi, N., Michalos, G., Aivaliotis, S., & Makris, S. (2018). An outlook on future assembly systems introducing robotic mobile dual arm workers. Procedia CIRP, 72, 33\u201338. https:\/\/doi.org\/10.1016\/j.procir.2018.03.130","journal-title":"Procedia CIRP"},{"key":"2518_CR36","doi-asserted-by":"publisher","DOI":"10.1145\/3065386","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems. https:\/\/doi.org\/10.1145\/3065386","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2518_CR37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543","author":"H Kuehne","year":"2011","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011). HMDB: A large video database for human motion recognition. In 2011 International Conference on Computer Vision. https:\/\/doi.org\/10.1109\/ICCV.2011.6126543","journal-title":"In 2011 International Conference on Computer Vision"},{"issue":"1","key":"2518_CR38","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/s11831-023-09986-x","volume":"31","author":"P Kumar","year":"2024","unstructured":"Kumar, P., Chauhan, S., & Awasthi, L. K. (2024). Human activity recognition (HAR) using deep learning: review, methodologies, progress and future research directions. Archives of Computational Methods in Engineering, 31(1), 179\u2013219. https:\/\/doi.org\/10.1007\/s11831-023-09986-x","journal-title":"Archives of Computational Methods in Engineering"},{"key":"2518_CR39","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/8323962","author":"VT Le","year":"2022","unstructured":"Le, V. T., Tran-Trung, K., & Hoang, V. T. (2022). A comprehensive review of recent deep learning techniques for human activity recognition. Computational Intelligence and Neuroscience. https:\/\/doi.org\/10.1155\/2022\/8323962","journal-title":"Computational Intelligence and Neuroscience"},{"key":"2518_CR40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3282631","author":"K Li","year":"2023","unstructured":"Li, K., Wang, Y., Zhang, J., Gao, P., Song, G., Liu, Y., & Qiao, Y. (2023). Uniformer: Unifying convolution and self-attention for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2023.3282631","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2518_CR41","doi-asserted-by":"publisher","first-page":"44211","DOI":"10.1109\/ACCESS.2018.2863943","volume":"6","author":"W Li","year":"2018","unstructured":"Li, W., Nie, W., & Su, Y. (2018a). Human action recognition based on selected spatio-temporal features via bidirectional LSTM. IEEE Access, 6, 44211\u201344220. https:\/\/doi.org\/10.1109\/ACCESS.2018.2863943","journal-title":"IEEE Access"},{"key":"2518_CR42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099","author":"Y Li","year":"2020","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., & Wang, L. (2020). Tea: Temporal excitation and aggregation for action recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00099","journal-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"2518_CR43","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2018","unstructured":"Li, Z., Gavrilyuk, K., Gavves, E., Jain, M., & Snoek, C. G. (2018b). Videolstm convolves, attends and flows for action recognition. Computer Vision and Image Understanding, 166, 41\u201350. https:\/\/doi.org\/10.1016\/j.cviu.2017.10.011","journal-title":"Computer Vision and Image Understanding"},{"key":"2518_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103740","volume":"90","author":"J Lin","year":"2023","unstructured":"Lin, J., Mu, Z., Zhao, T., Zhang, H., Yang, X., & Zhao, P. (2023). Action density based frame sampling for human action recognition in videos. Journal of Visual Communication and Image Representation, 90, 103740. https:\/\/doi.org\/10.1016\/j.jvcir.2022.103740","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"2518_CR45","doi-asserted-by":"publisher","first-page":"1327","DOI":"10.1007\/s00371-020-01868-8","volume":"37","author":"C Liu","year":"2021","unstructured":"Liu, C., Ying, J., Yang, H., Hu, X., & Liu, J. (2021). Improved human action recognition approach based on two-stream convolutional neural network model. The Visual Computer, 37, 1327\u20131341. https:\/\/doi.org\/10.1007\/s00371-020-01868-8","journal-title":"The Visual Computer"},{"key":"2518_CR46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350908","author":"J Liu","year":"2015","unstructured":"Liu, J., Huang, Y., Peng, X., & Wang, L. (2015). Multi-view descriptor mining via codeword net for action recognition. In 2015 IEEE International Conference on Image Processing (ICIP). https:\/\/doi.org\/10.1109\/ICIP.2015.7350908","journal-title":"In 2015 IEEE International Conference on Image Processing (ICIP)"},{"key":"2518_CR47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206744","author":"J Liu","year":"2009","unstructured":"Liu, J., Luo, J., & Shah, M. (2009). Recognizing realistic actions from videos \u201cin the wild.\u201d In 2009IEEE Conference on Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.1109\/CVPR.2009.5206744","journal-title":"In 2009IEEE Conference on Computer Vision and Pattern Recognition"},{"issue":"07","key":"2518_CR48","doi-asserted-by":"publisher","first-page":"11669","DOI":"10.1609\/aaai.v34i07.6836","volume":"34","author":"Z Liu","year":"2020","unstructured":"Liu, Z., Luo, D., Wang, Y., Wang, L., Tai, Y., Wang, C., & Lu, T. (2020). Teinet: Towards an efficient architecture for video recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11669\u201311676. https:\/\/doi.org\/10.1609\/aaai.v34i07.6836","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2518_CR49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557","author":"M Marszalek","year":"2009","unstructured":"Marszalek, M., Laptev, I., & Schmid, C. (2009). Actions in context. In 2009IEEE Conference on Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.1109\/CVPR.2009.5206557","journal-title":"In 2009IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"2518_CR50","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.procs.2019.08.147","volume":"157","author":"A Michele","year":"2019","unstructured":"Michele, A., Colin, V., & Santika, D. D. (2019). Mobilenet convolutional neural networks and support vector machines for palmprint recognition. Procedia Computer Science, 157, 110\u2013117. https:\/\/doi.org\/10.1016\/j.procs.2019.08.147","journal-title":"Procedia Computer Science"},{"key":"2518_CR51","doi-asserted-by":"publisher","first-page":"119419","DOI":"10.1016\/j.eswa.2022.119419","volume":"216","author":"TR Mim","year":"2023","unstructured":"Mim, T. R., Amatullah, M., Afreen, S., Yousuf, M. A., Uddin, S., Alyami, S. A., & Moni, M. A. (2023). GRU-INC: An inception-attention based approach using GRU for human activity recognition. Expert Systems with Applications, 216, 119419. https:\/\/doi.org\/10.1016\/j.eswa.2022.119419","journal-title":"Expert Systems with Applications"},{"key":"2518_CR52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110051","volume":"146","author":"Y Mitsuzumi","year":"2024","unstructured":"Mitsuzumi, Y., Irie, G., Kimura, A., & Nakazawa, A. (2024). Phase Randomization: A data augmentation for domain adaptation in human action recognition. Pattern Recognition, 146, 110051. https:\/\/doi.org\/10.1016\/j.patcog.2023.110051","journal-title":"Pattern Recognition"},{"key":"2518_CR53","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1016\/j.future.2021.06.045","volume":"125","author":"K Muhammad","year":"2021","unstructured":"Muhammad, K., Ullah, A., Imran, A. S., Sajjad, M., Kiran, M. S., Sannino, G., & de Albuquerque, V. H. C. (2021). Human action recognition using attention based LSTM network with dilated CNN features. Future Generation Computer Systems, 125, 820\u2013830. https:\/\/doi.org\/10.1016\/j.future.2021.06.045","journal-title":"Future Generation Computer Systems"},{"key":"2518_CR54","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2023.035214","author":"IM Nasir","year":"2023","unstructured":"Nasir, I. M., Raza, M., Shah, J. H., Khan, M. A., Nam, Y. C., & Nam, Y. (2023). Improved shark smell optimization algorithm for human action recognition. Computers, Materials & Continua. https:\/\/doi.org\/10.32604\/cmc.2023.035214","journal-title":"Computers, Materials & Continua"},{"key":"2518_CR55","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00179","author":"JYH Ng","year":"2018","unstructured":"Ng, J. Y. H., Choi, J., Neumann, J., & Davis, L. S. (2018). Actionflownet: Learning motion representation for action recognition. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). https:\/\/doi.org\/10.1109\/WACV.2018.00179","journal-title":"In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)"},{"issue":"1","key":"2518_CR56","doi-asserted-by":"publisher","first-page":"14624","DOI":"10.1038\/s41598-023-39744-9","volume":"13","author":"HP Nguyen","year":"2023","unstructured":"Nguyen, H. P., & Bernardete, R. (2023). Video action recognition collaborative learning with dynamics via PSO-ConvNet transformer. Scientific Reports, 13(1), 14624. https:\/\/doi.org\/10.1038\/s41598-023-39744-9","journal-title":"Scientific Reports"},{"key":"2518_CR57","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101953","volume":"100","author":"S Nooruddin","year":"2023","unstructured":"Nooruddin, S., Islam, M. M., Karray, F., & Muhammad, G. (2023). A multi-resolution fusion approach for human activity recognition from video data in tiny edge devices. Information Fusion, 100, 101953. https:\/\/doi.org\/10.1016\/j.inffus.2023.101953","journal-title":"Information Fusion"},{"key":"2518_CR58","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106995","volume":"222","author":"T \u00d6zyer","year":"2021","unstructured":"\u00d6zyer, T., Ak, D. S., & Alhajj, R. (2021). Human action recognition approaches with video datasets\u2014a survey. Knowledge-Based Systems, 222, 106995. https:\/\/doi.org\/10.1016\/j.knosys.2021.106995","journal-title":"Knowledge-Based Systems"},{"key":"2518_CR59","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.cviu.2016.03.013","volume":"150","author":"X Peng","year":"2016","unstructured":"Peng, X., Wang, L., Wang, X., & Qiao, Y. (2016). Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice. Computer Vision and Image Understanding, 150, 109\u2013125. https:\/\/doi.org\/10.1016\/j.cviu.2016.03.013","journal-title":"Computer Vision and Image Understanding"},{"issue":"4","key":"2518_CR60","doi-asserted-by":"publisher","first-page":"82","DOI":"10.3390\/drones3040082","volume":"3","author":"AG Perera","year":"2019","unstructured":"Perera, A. G., Law, Y. W., & Chahl, J. (2019). Drone-action: An outdoor recorded drone video dataset for action recognition. Drones, 3(4), 82.","journal-title":"Drones"},{"key":"2518_CR61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00289","author":"K Ranasinghe","year":"2022","unstructured":"Ranasinghe, K., Naseer, M., Khan, S., Khan, F. S., & Ryoo, M. S. (2022). Self-supervised video transformer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00289","journal-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"issue":"5","key":"2518_CR62","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1007\/s00138-012-0450-4","volume":"24","author":"KK Reddy","year":"2013","unstructured":"Reddy, K. K., & Shah, M. (2013). Recognizing 50 human action categories of web videos. Machine Vision and Applications, 24(5), 971\u2013981. https:\/\/doi.org\/10.1007\/s00138-012-0450-4","journal-title":"Machine Vision and Applications"},{"key":"2518_CR63","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3296252","author":"T Shanableh","year":"2023","unstructured":"Shanableh, T. (2023). ViCo-MoCo-DL: Video coding and motion compensation solutions for human activity recognition using deep learning. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2023.3296252","journal-title":"IEEE Access"},{"key":"2518_CR64","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., & Woo, W. C. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems, 28."},{"key":"2518_CR65","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486601","author":"Y Shu","year":"2018","unstructured":"Shu, Y., Shi, Y., Wang, Y., Zou, Y., Yuan, Q., & Tian, Y. (2018). Odn: Opening the deep network for open-set action recognition. In IEEE 2018 International Conference on Multimedia and Expo (ICME). https:\/\/doi.org\/10.1109\/ICME.2018.8486601","journal-title":"In IEEE 2018 International Conference on Multimedia and Expo (ICME)"},{"key":"2518_CR66","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition, In: Proceedings of the International Conference on Learning Representations, 2015."},{"issue":"11","key":"2518_CR67","first-page":"1","volume":"2","author":"K Soomro","year":"2012","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). A dataset of 101 human action classes from videos in the wild. Center for Research in Computer Vision, 2(11), 1\u20137.","journal-title":"Center for Research in Computer Vision"},{"key":"2518_CR68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.236","author":"L Sun","year":"2017","unstructured":"Sun, L., Jia, K., Chen, K., Yeung, D. Y., Shi, B. E., & Savarese, S. (2017). Lattice long short-term memory for human action recognition. In Proceedings of the IEEE International Conference on Computer Vision. https:\/\/doi.org\/10.1109\/ICCV.2017.236","journal-title":"In Proceedings of the IEEE International Conference on Computer Vision"},{"key":"2518_CR69","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118484","volume":"210","author":"KS Tan","year":"2022","unstructured":"Tan, K. S., Lim, K. M., Lee, C. P., & Kwek, L. C. (2022). Bidirectional long short-term memory with temporal dense sampling for human action recognition. Expert Systems with Applications, 210, 118484. https:\/\/doi.org\/10.1016\/j.eswa.2022.118484","journal-title":"Expert Systems with Applications"},{"key":"2518_CR70","unstructured":"Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105\u20136114). PMLR."},{"key":"2518_CR71","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107102","volume":"103","author":"A Ullah","year":"2021","unstructured":"Ullah, A., Muhammad, K., Ding, W., Palade, V., Haq, I. U., & Baik, S. W. (2021a). Efficient activity recognition using lightweight CNN and DS-GRU network for surveillance applications. Applied Soft Computing, 103, 107102. https:\/\/doi.org\/10.1016\/j.asoc.2021.107102","journal-title":"Applied Soft Computing"},{"key":"2518_CR72","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.neucom.2019.12.151","volume":"435","author":"A Ullah","year":"2021","unstructured":"Ullah, A., Muhammad, K., Hussain, T., & Baik, S. W. (2021b). Conflux LSTMs network: A novel approach for multi-view action recognition. Neurocomputing, 435, 321\u2013329. https:\/\/doi.org\/10.1016\/j.neucom.2019.12.151","journal-title":"Neurocomputing"},{"issue":"12","key":"2518_CR73","doi-asserted-by":"publisher","first-page":"9692","DOI":"10.1109\/TIE.2018.2881943","volume":"66","author":"A Ullah","year":"2018","unstructured":"Ullah, A., Muhammad, K., Del Ser, J., Baik, S. W., & de Albuquerque, V. H. C. (2018). Activity recognition using temporal optical flow convolutional features and multilayer LSTM. IEEE Transactions on Industrial Electronics, 66(12), 9692\u20139702. https:\/\/doi.org\/10.1109\/TIE.2018.2881943","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"2518_CR74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11710","author":"C Wang","year":"2018","unstructured":"Wang, C., Zhang, L., Xie, L., & Yuan, J. (2018). Kernel cross-correlator. In Proceedings of the AAAI Conference on Artificial Intelligence. https:\/\/doi.org\/10.1609\/aaai.v32i1.11710","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2518_CR75","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11263-015-0846-5","volume":"119","author":"H Wang","year":"2016","unstructured":"Wang, H., Oneata, D., Verbeek, J., & Schmid, C. (2016). A robust and efficient video representation for action recognition. International Journal of Computer Vision, 119, 219\u2013238. https:\/\/doi.org\/10.1007\/s11263-015-0846-5","journal-title":"International Journal of Computer Vision"},{"key":"2518_CR76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441","author":"H Wang","year":"2013","unstructured":"Wang, H., & Schmid, C. (2013). Action recognition with improved trajectories. In Proceedings of the IEEE International Conference on Computer Vision. https:\/\/doi.org\/10.1109\/ICCV.2013.441","journal-title":"In Proceedings of the IEEE International Conference on Computer Vision"},{"key":"2518_CR77","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2020.10.037","volume":"423","author":"H Wang","year":"2021","unstructured":"Wang, H., Yu, B., Xia, K., Li, J., & Zuo, X. (2021a). Skeleton edge motion networks for human action recognition. Neurocomputing, 423, 1\u201312. https:\/\/doi.org\/10.1016\/j.neucom.2020.10.037","journal-title":"Neurocomputing"},{"key":"2518_CR78","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/j.neucom.2021.04.071","volume":"451","author":"J Wang","year":"2021","unstructured":"Wang, J., Shao, Z., Huang, X., Lu, T., Zhang, R., & Lv, X. (2021b). Spatial\u2013temporal pooling for action recognition in videos. Neurocomputing, 451, 265\u2013278. https:\/\/doi.org\/10.1016\/j.neucom.2021.04.071","journal-title":"Neurocomputing"},{"key":"2518_CR79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193","author":"L Wang","year":"2021","unstructured":"Wang, L., Tong, Z., Ji, B., & Wu, G. (2021c). Tdn: Temporal difference networks for efficient action recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00193","journal-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"issue":"7","key":"2518_CR80","doi-asserted-by":"publisher","first-page":"7188","DOI":"10.1109\/JSEN.2023.3242603","volume":"23","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Xu, H., Liu, Y., Wang, M., Wang, Y., Yang, Y., & Li, J. (2023). A novel deep multifeature extraction framework based on attention mechanism using wearable sensor data for human activity recognition. IEEE Sensors Journal, 23(7), 7188\u20137198. https:\/\/doi.org\/10.1109\/JSEN.2023.3242603","journal-title":"IEEE Sensors Journal"},{"issue":"12","key":"2518_CR81","doi-asserted-by":"publisher","first-page":"5784","DOI":"10.3390\/app12125784","volume":"12","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Lu, H., Jin, J., & Hu, K. (2022). Human action recognition based on improved two-stream convolution network. Applied Sciences, 12(12), 5784. https:\/\/doi.org\/10.3390\/app12125784","journal-title":"Applied Sciences"},{"key":"2518_CR82","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3293813","author":"J Wensel","year":"2023","unstructured":"Wensel, J., Ullah, H., & Munir, A. (2023). Vit-ret: Vision and recurrent transformer neural networks for human activity recognition in videos. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2023.3293813","journal-title":"IEEE Access"},{"key":"2518_CR83","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.101939","volume":"56","author":"H Wu","year":"2023","unstructured":"Wu, H., Li, H., Chi, H. L., Peng, Z., Chang, S., & Wu, Y. (2023). Thermal image-based hand gesture recognition for worker-robot collaboration in the construction industry: A feasible study. Advanced Engineering Informatics, 56, 101939. https:\/\/doi.org\/10.1016\/j.aei.2023.101939","journal-title":"Advanced Engineering Informatics"},{"key":"2518_CR84","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.patcog.2019.01.006","volume":"90","author":"Z Wu","year":"2019","unstructured":"Wu, Z., Shen, C., & Van Den Hengel, A. (2019). Wider or deeper: Revisiting the resnet model for visual recognition. Pattern Recognition, 90, 119\u2013133. https:\/\/doi.org\/10.1016\/j.patcog.2019.01.006","journal-title":"Pattern Recognition"},{"key":"2518_CR85","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/978-3-031-20062-5_36","volume-title":"European Conference on Computer Vision","author":"W Xiang","year":"2022","unstructured":"Xiang, W., Li, C., Wang, B., Wei, X., Hua, X. S., & Zhang, L. (2022). Spatiotemporal self-attention modeling with temporal patch shift for action recognition. In S. Avidan, G. Brostow, M. Ciss\u00e9, G. M. Farinella, & T. Hassner (Eds.), European Conference on Computer Vision (pp. 627\u2013644). Cham: Springer. https:\/\/doi.org\/10.1007\/978-3-031-20062-5_36"},{"key":"2518_CR86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00325","author":"J Xiao","year":"2022","unstructured":"Xiao, J., Jing, L., Zhang, L., He, J., She, Q., Zhou, Z., & Li, Y. (2022). Learning from temporal gradient for semi-supervised action recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00325","journal-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"2518_CR87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01804","author":"Z Xing","year":"2023","unstructured":"Xing, Z., Dai, Q., Hu, H., Chen, J., Wu, Z., & Jiang, Y. G. (2023). Svformer: Semi-supervised video transformer for action recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01804","journal-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"2518_CR88","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1016\/j.jmsy.2020.04.007","volume":"56","author":"Q Xiong","year":"2020","unstructured":"Xiong, Q., Zhang, J., Wang, P., Liu, D., & Gao, R. X. (2020). Transferable two-stream convolutional neural network for human action recognition. Journal of Manufacturing Systems, 56, 605\u2013614. https:\/\/doi.org\/10.1016\/j.jmsy.2020.04.007","journal-title":"Journal of Manufacturing Systems"},{"key":"2518_CR89","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/6608448","author":"X Xiong","year":"2022","unstructured":"Xiong, X., Min, W., Han, Q., Wang, Q., & Zha, C. (2022). Action recognition using action sequences optimization and two-stream 3D dilated neural network. Computational Intelligence and Neuroscience. https:\/\/doi.org\/10.1155\/2022\/6608448","journal-title":"Computational Intelligence and Neuroscience"},{"key":"2518_CR90","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1016\/j.neucom.2020.04.150","volume":"441","author":"J Xu","year":"2021","unstructured":"Xu, J., Song, R., Wei, H., Guo, J., Zhou, Y., & Huang, X. (2021a). A fast human action recognition network based on spatio-temporal features. Neurocomputing, 441, 350\u2013358. https:\/\/doi.org\/10.1016\/j.neucom.2020.04.150","journal-title":"Neurocomputing"},{"key":"2518_CR91","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114829","volume":"178","author":"Y Xu","year":"2021","unstructured":"Xu, Y., Yang, J., Mao, K., Yin, J., & See, S. (2021b). Exploiting inter-frame regional correlation for efficient action recognition. Expert Systems with Applications, 178, 114829. https:\/\/doi.org\/10.1016\/j.eswa.2021.114829","journal-title":"Expert Systems with Applications"},{"key":"2518_CR92","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.neunet.2022.12.005","volume":"159","author":"SK Yadav","year":"2023","unstructured":"Yadav, S. K., Luthra, A., Pahwa, E., Tiwari, K., Rathore, H., Pandey, H. M., & Corcoran, P. (2023). DroneAttention: Sparse weighted temporal attention for drone-camera based activity recognition. Neural Networks, 159, 57\u201369. https:\/\/doi.org\/10.1016\/j.neunet.2022.12.005","journal-title":"Neural Networks"},{"key":"2518_CR93","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-024-02420-4","author":"CL Yang","year":"2024","unstructured":"Yang, C. L., Hsu, S. C., Kang, Y. C., Nian, J. F., & Cakravastia, A. (2024). Unsupervised exceptional human action detection from repetition of human assembling tasks using entropy signal clustering. Journal of Intelligent Manufacturing. https:\/\/doi.org\/10.1007\/s10845-024-02420-4","journal-title":"Journal of Intelligent Manufacturing"},{"key":"2518_CR94","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.sigpro.2015.10.035","volume":"124","author":"Y Yang","year":"2016","unstructured":"Yang, Y., Liu, R., Deng, C., & Gao, X. (2016). Multi-task human action recognition via exploring super-category. Signal Processing, 124, 36\u201344. https:\/\/doi.org\/10.1016\/j.sigpro.2015.10.035","journal-title":"Signal Processing"},{"key":"2518_CR95","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2024.102371","volume":"60","author":"S Yi","year":"2024","unstructured":"Yi, S., Liu, S., Yang, Y., Yan, S., Guo, D., Wang, X. V., & Wang, L. (2024). Safety-aware human-centric collaborative assembly. Advanced Engineering Informatics, 60, 102371. https:\/\/doi.org\/10.1016\/j.aei.2024.102371","journal-title":"Advanced Engineering Informatics"},{"key":"2518_CR96","doi-asserted-by":"publisher","DOI":"10.1109\/GECOST60902.2024.10474856","author":"AZS Yii","year":"2024","unstructured":"Yii, A. Z. S., Lim, K. H., & Chiong, C. W. R. (2024). Review of three dimensional human action recognition. In International Conference on Green Energy Computing and Sustainable Technology (GECOST). https:\/\/doi.org\/10.1109\/GECOST60902.2024.10474856","journal-title":"In International Conference on Green Energy Computing and Sustainable Technology (GECOST)."},{"key":"2518_CR97","unstructured":"YouTube, The restorator. Retrieved April, 2023, from https:\/\/www.youtube.com\/watch?v=2LwtApYRGD4&t=1154s and https:\/\/www.youtube.com\/watch?v=wH21p1GwyIY&t=4s ."},{"key":"2518_CR98","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109985","volume":"146","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Chen, Z., Xu, T., Zhao, J., Mi, S., Geng, X., & Zhang, M. L. (2024). Temporal segment dropout for human action video recognition. Pattern Recognition, 146, 109985. https:\/\/doi.org\/10.1016\/j.patcog.2023.109985","journal-title":"Pattern Recognition"},{"key":"2518_CR99","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2022.101792","volume":"54","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Ding, K., Hui, J., Lv, J., Zhou, X., & Zheng, P. (2022). Human-object integrated assembly intention recognition for context-aware human-robot collaborative assembly. Advanced Engineering Informatics, 54, 101792. https:\/\/doi.org\/10.1016\/j.aei.2022.101792","journal-title":"Advanced Engineering Informatics"},{"key":"2518_CR100","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.jmsy.2023.01.007","volume":"67","author":"H Zhou","year":"2023","unstructured":"Zhou, H., Yang, G., Wang, B., Li, X., Wang, R., Huang, X., & Wang, X. V. (2023a). An attention-based deep learning approach for inertial motion recognition and estimation in human-robot collaboration. Journal of Manufacturing Systems, 67, 97\u2013110. https:\/\/doi.org\/10.1016\/j.jmsy.2023.01.007","journal-title":"Journal of Manufacturing Systems"},{"key":"2518_CR101","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1016\/j.neunet.2023.09.031","volume":"168","author":"S Zhou","year":"2023","unstructured":"Zhou, S., Xu, H., Bai, Z., Du, Z., Zeng, J., Wang, Y., & Xu, J. (2023b). A multidimensional feature fusion network based on MGSE and TAAC for video-based human action recognition. Neural Networks, 168, 496\u2013507. https:\/\/doi.org\/10.1016\/j.neunet.2023.09.031","journal-title":"Neural Networks"}],"container-title":["Journal of Intelligent Manufacturing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10845-024-02518-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10845-024-02518-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10845-024-02518-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T07:57:05Z","timestamp":1761983825000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10845-024-02518-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"references-count":101,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2518"],"URL":"https:\/\/doi.org\/10.1007\/s10845-024-02518-9","relation":{},"ISSN":["0956-5515","1572-8145"],"issn-type":[{"type":"print","value":"0956-5515"},{"type":"electronic","value":"1572-8145"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"20 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}