{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:35:03Z","timestamp":1782988503713,"version":"3.54.5"},"reference-count":103,"publisher":"Wiley","license":[{"start":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T00:00:00Z","timestamp":1704326400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2024,1,4]]},"abstract":"<jats:p>Action recognition (AR) has many applications, including surveillance, health\/disabilities care, man-machine interactions, video-content-based monitoring, and activity recognition. Because human action videos contain a large number of frames, implemented models must minimize computation by reducing the number, size, and resolution of frames. We propose an improved method for detecting human actions in low-size and low-resolution videos by employing convolutional neural networks (CNNs) with channel attention mechanisms (CAMs) and autoencoders (AEs). By enhancing blocks with more representative features, convolutional layers extract discriminating features from various networks. Additionally, we use random sampling of frames before main processing to improve accuracy while employing less data. The goal is to increase performance while overcoming challenges such as overfitting, computational complexity, and uncertainty by utilizing CNN-CAM and AE. Identifying patterns and features associated with selective high-level performance is the next step. To validate the method, low-resolution and low-size video frames were used in the UCF50, UCF101, and HMDB51 datasets. Additionally, the algorithm has relatively minimal computational complexity. Consequently, the proposed method performs satisfactorily compared to other similar methods. It has accuracy estimates of 77.29, 98.87, and 97.16%, respectively, for HMDB51, UCF50, and UCF101 datasets. These results indicate that the method can effectively classify human actions. Furthermore, the proposed method can be used as a processing model for low-resolution and low-size video frames.<\/jats:p>","DOI":"10.1155\/2024\/1052344","type":"journal-article","created":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T22:35:05Z","timestamp":1704407705000},"page":"1-22","source":"Crossref","is-referenced-by-count":36,"title":["Channel Attention-Based Approach with Autoencoder Network for Human Action Recognition in Low-Resolution Frames"],"prefix":"10.1155","volume":"2024","author":[{"given":"Elaheh","family":"Dastbaravardeh","sequence":"first","affiliation":[{"name":"Department of Control Engineering, Islamic Azad University of Mashhad, Mashhad, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Somayeh","family":"Askarpour","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Technical and Vocational University (TVU), Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4125-4368","authenticated-orcid":true,"given":"Maryam","family":"Saberi Anari","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Technical and Vocational University (TVU), Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6763-6626","authenticated-orcid":true,"given":"Khosro","family":"Rezaee","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Meybod University, Meybod, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.044"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07937-4"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108220"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1145\/3447744"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.3390\/s23042182"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09406-3"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107102"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2022.10.003"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-021-01586-5"},{"key":"10","doi-asserted-by":"crossref","DOI":"10.1201\/9781351003827","volume-title":"Deep Learning in Computer Vision: Principles and Applications","author":"M. Hassaballah","year":"2020"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.01.029"},{"key":"12","first-page":"716","article-title":"Hon4d: histogram of oriented 4d normals for activity recognition from depth sequences","author":"O. Oreifej"},{"key":"13","first-page":"804","article-title":"Super normal vector for activity recognition using depth sequences","author":"X. Yang"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2017.2717439"},{"key":"15","first-page":"219","article-title":"Automatic features extraction using autoencoder in intrusion detection system","author":"Y. N. Kunang"},{"key":"16","first-page":"65","article-title":"Behavior recognition via sparse spatio-temporal features","author":"P. Doll\u00e1r"},{"key":"17","first-page":"3361","article-title":"Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis","author":"Q. V. Le"},{"key":"18","first-page":"1234","article-title":"Action bank: a high-level representation of activity in video","author":"S. Sadanand"},{"key":"19","first-page":"3551","article-title":"Action recognition with improved trajectories","author":"H. Wang"},{"key":"20","first-page":"793","article-title":"Multi-view descriptor mining via codeword net for action recognition","author":"J. Liu"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2015.10.035"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0846-5"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4795-6"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.03.013"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114829"},{"key":"26","first-page":"1767","article-title":"A compact pairwise trajectory representation for action recognition","author":"Q. Huang"},{"key":"27","first-page":"770","article-title":"Deep residual learning for image recognition","author":"K. He"},{"key":"28","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"A. Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"29","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K. Simonyan","year":"2014"},{"key":"30","first-page":"1","article-title":"Going deeper with convolutions","author":"C. Szegedy"},{"key":"31","first-page":"2210","article-title":"Boosting VLAD with double assignment using deep features for action recognition in videos","author":"I. C. Duta"},{"key":"32","first-page":"2147","article-title":"Lattice long short-term memory for human action recognition","author":"L. Sun"},{"key":"33","first-page":"1","article-title":"Odn: opening the deep network for open-set action recognition","author":"Y. Shu"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-018-9932-3"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.028"},{"key":"36","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.neucom.2020.06.032","article-title":"Human action recognition using convolutional LSTM and fully-connected LSTM with different attentions","volume":"410","author":"Z. Zhang","year":"2020","journal-title":"Neurocomputing"},{"key":"37","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/6608448"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"39","first-page":"2625","article-title":"Long-term recurrent convolutional networks for visual recognition and description","author":"J. Donahue"},{"key":"40","first-page":"20030","article-title":"Direcformer: a directed attention in transformer approach to robust action recognition","author":"T. D. Truong"},{"key":"41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2021.103121"},{"key":"42","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","volume":"2","author":"R. Christoph","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"43","first-page":"4768","article-title":"Spatiotemporal multiplier networks for video action recognition","author":"C. Feichtenhofer"},{"key":"44","first-page":"1933","article-title":"Convolutional two-stream network fusion for video action recognition","author":"C. Feichtenhofer"},{"key":"45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.071"},{"key":"46","first-page":"20","article-title":"Temporal segment networks: towards good practices for deep action recognition","author":"L. Wang"},{"key":"47","first-page":"4489","article-title":"Learning spatiotemporal features with 3d convolutional networks","author":"D. Tran"},{"key":"48","first-page":"6299","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"J. Carreira"},{"key":"49","first-page":"5533","article-title":"Learning spatio-temporal representation with pseudo-3d residual networks","author":"Z. Qiu"},{"key":"50","first-page":"6450","article-title":"A closer look at spatiotemporal convolutions for action recognition","author":"D. Tran"},{"key":"51","first-page":"305","article-title":"Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification","author":"S. Xie"},{"key":"52","first-page":"803","article-title":"Temporal relational reasoning in videos","author":"B. Zhou"},{"key":"53","first-page":"7083","article-title":"Tsm: temporal shift module for efficient video understanding","author":"J. Lin"},{"key":"54","first-page":"7794","article-title":"Non-local neural networks","author":"X. Wang"},{"key":"55","first-page":"6202","article-title":"Slowfast networks for video recognition","author":"C. Feichtenhofer"},{"key":"56","first-page":"6165","article-title":"Deep analysis of cnn-based spatio-temporal representations for action recognition","author":"C. F. R. Chen"},{"key":"57","first-page":"13719","article-title":"Efficient action recognition via dynamic knowledge propagation","author":"H. Kim"},{"key":"58","first-page":"13434","article-title":"Else-net: elastic semantic network for continual action recognition from skeleton data","author":"T. Li"},{"key":"59","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3061115"},{"key":"60","first-page":"7939","article-title":"Contrast and order representations for video self-supervised learning","author":"K. Hu"},{"key":"61","first-page":"527","article-title":"Shuffle and learn: unsupervised learning using temporal order verification","author":"I. Misra"},{"key":"62","first-page":"10334","article-title":"Self-supervised spatiotemporal learning via video clip order prediction","author":"D. Xu"},{"key":"63","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3152247"},{"key":"64","article-title":"Is space-time attention all you need for video understanding?","author":"G. Bertasius"},{"key":"65","first-page":"694","article-title":"Spatial temporal transformer network for skeleton-based action recognition","author":"C. Plizzari"},{"key":"66","first-page":"3229","article-title":"STST: spatial-temporal specialized transformer for skeleton-based action recognition","author":"Y. Zhang"},{"key":"67","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2020.3048883"},{"key":"68","first-page":"203","article-title":"X3d: expanding architectures for efficient video recognition","author":"C. Feichtenhofer"},{"key":"69","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103598"},{"key":"70","first-page":"2598","article-title":"Learning a distance function with a Siamese network to localize anomalies in videos","author":"B. Ramachandra"},{"key":"71","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13496-6"},{"key":"72","first-page":"1071","article-title":"Foreground detection of moving object using Gaussian mixture model","author":"N. Aslam"},{"key":"73","first-page":"1","article-title":"Action recognition from extremely low-resolution thermal image sequence","author":"T. Kawashima"},{"key":"74","first-page":"6546","article-title":"Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet?","author":"K. Hara"},{"key":"75","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-012-0450-4"},{"key":"76","article-title":"UCF101: a dataset of 101 human actions classes from videos in the wild","author":"K. Soomro","year":"2012"},{"key":"77","article-title":"Privacy-preserving human activity recognition from extreme low resolution","author":"M. S. Ryoo"},{"key":"78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12299"},{"key":"79","first-page":"139","article-title":"Semi-coupled two-stream fusion convnets for action recognition at extremely low resolutions","author":"J. Chen"},{"key":"80","first-page":"1607","article-title":"Fully-coupled two-stream spatiotemporal networks for extremely low resolution action recognition","author":"M. Xu"},{"key":"81","first-page":"8799","article-title":"Two-stream action recognition-oriented video super-resolution","author":"H. Zhang"},{"key":"82","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2901464"},{"key":"83","first-page":"6047","article-title":"Ava: a video dataset of spatio-temporally localized atomic visual actions","author":"C. Gu"},{"key":"84","article-title":"Youtube-8m: a large-scale video classification benchmark","author":"S. Abu-El-Haija","year":"2016"},{"key":"85","first-page":"624","article-title":"Deep laplacian pyramid networks for fast and accurate super-resolution","author":"W. S. Lai"},{"key":"86","first-page":"7387","article-title":"Tinyvirat: low-resolution video action recognition","author":"U. Demir"},{"key":"87","doi-asserted-by":"publisher","DOI":"10.3390\/mi12060670"},{"key":"88","first-page":"2556","article-title":"HMDB: a large video database for human motion recognition","author":"H. Kuehne"},{"key":"89","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-020-00501-x"},{"key":"90","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2017.2749159"},{"key":"91","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2016.2611485"},{"key":"92","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.02.028"},{"key":"93","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-018-1347-3"},{"key":"94","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2020.2984569"},{"key":"95","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-05698-0"},{"key":"96","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"97","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2912357"},{"key":"98","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112927"},{"key":"99","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.148"},{"key":"100","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2019.2951680"},{"key":"101","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.015"},{"key":"102","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3235300"},{"key":"103","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110143"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2024\/1052344.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2024\/1052344.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2024\/1052344.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T22:35:10Z","timestamp":1704407710000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/ijis\/2024\/1052344\/"}},"subtitle":[],"editor":[{"given":"Alexander","family":"Ho\u0161ovsk\u00fd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,1,4]]},"references-count":103,"alternative-id":["1052344","1052344"],"URL":"https:\/\/doi.org\/10.1155\/2024\/1052344","relation":{},"ISSN":["1098-111X","0884-8173"],"issn-type":[{"value":"1098-111X","type":"electronic"},{"value":"0884-8173","type":"print"}],"subject":[],"published":{"date-parts":[[2024,1,4]]}}}