{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:09:52Z","timestamp":1766128192807,"version":"3.48.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3641691","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:50Z","timestamp":1765219310000},"page":"211715-211734","source":"Crossref","is-referenced-by-count":0,"title":["HiTAGU-Net: Introducing Hierarchical Temporal-Aware Gated Units for Enhanced Motion Disentanglement in Action Recognition"],"prefix":"10.1109","volume":"13","author":[{"given":"Arash","family":"Asefnejad","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, SR.C., Islamic Azad University, Tehran, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1889-0294","authenticated-orcid":false,"given":"Javad","family":"Mohammadzadeh","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Ka.C., Islamic Azad University, Karaj, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mitra","family":"Mirzarezaee","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, SR.C., Islamic Azad University, Tehran, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v2i5.1292"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7839840"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-019-00212-x"},{"key":"ref4","article-title":"Human\u2013robot interaction for collaborative tasks: A deep learning perspective","volume":"168","author":"Wang","year":"2023","journal-title":"Robot. Auton. Syst."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s23094258"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107861"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s21062051"},{"key":"ref8","first-page":"38","article-title":"Optical-flow-free video action recognition using residual motion encoding","volume":"534","author":"Wu","year":"2023","journal-title":"Neurocomputing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-14075-5"},{"key":"ref10","article-title":"Vision transformers for human action recognition: A survey","volume":"100","author":"Fang","year":"2024","journal-title":"Inf. Fusion"},{"issue":"3","key":"ref11","first-page":"1221","article-title":"Resource-efficient video transformers for real-time action recognition","volume":"46","author":"Sun","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref12","first-page":"54","article-title":"Fine-grained action recognition using motion-aware representation","volume":"174","author":"Yang","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3514654"},{"issue":"1","key":"ref14","first-page":"1","article-title":"Efficient deep learning on edge devices: Challenges and opportunities","volume":"57","author":"Rahman","year":"2025","journal-title":"ACM Comput. Surv."},{"issue":"4","key":"ref15","first-page":"1031","article-title":"A review of deep learning-based human activity recognition","volume":"25","author":"Sharma","year":"2022","journal-title":"Int. J. Speech Technol."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128731"},{"key":"ref17","first-page":"275:1","article-title":"A spatio-temporal descriptor based on 3D gradients","volume-title":"Proc. BMVC","author":"Klaser"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref19","article-title":"Metaheuristic optimization for image seam selection: Genetic and swarm intelligence approaches","volume":"133","author":"Li","year":"2023","journal-title":"Pattern Recogn."},{"key":"ref20","first-page":"103","article-title":"Human action analysis using optical-flow-free hybrid descriptors","volume":"620","author":"Zhu","year":"2022","journal-title":"Inf. Sci."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-01898-z"},{"issue":"2","key":"ref22","first-page":"344","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"42","author":"Simonyan","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref23","first-page":"6039","article-title":"Deep 3D convolutional networks for human action recognition","volume":"29","author":"Ji","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref24","first-page":"160","article-title":"Spatio-temporal regularization in 3D CNNs for video understanding","volume":"151","author":"Cheng","year":"2021","journal-title":"Pattern Recogn. Lett."},{"key":"ref25","first-page":"68102","article-title":"Dynamic convolutional neural networks with channel gating for efficient HAR","volume":"10","author":"Zhao","year":"2022","journal-title":"IEEE Access"},{"key":"ref26","first-page":"73","article-title":"Optimized 3D CNN for real-time human action recognition","volume":"169","author":"Wu","year":"2024","journal-title":"Neural Netw."},{"issue":"6","key":"ref27","first-page":"2310","article-title":"Temporal segment networks: Towards good practices for deep action recognition","volume":"43","author":"Wang","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00320"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref35","first-page":"611","article-title":"Attention LSTM for action recognition in video","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) Workshops","author":"Yao"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00209"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref40","first-page":"2080","article-title":"Gated attention units for efficient video action recognition","volume-title":"Proc. AAAI Conf. Artif. Intell. (AAAI)","author":"Li"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref44","first-page":"6824","article-title":"Multiscale vision transformers","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Patrick"},{"key":"ref45","first-page":"1","article-title":"X-ViT: Cross-attention vision transformer for video recognition","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Buettner"},{"key":"ref46","first-page":"12456","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Patrick"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3294564"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref51","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Tan"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-98571-2"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref54","first-page":"4209","article-title":"Lite-VideoNet: Lightweight spatiotemporal network for efficient video recognition","volume":"23","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Multimedia"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref56","article-title":"Eco-Lite: Efficient and compact network for video action recognition","volume":"124","author":"Zhao","year":"2022","journal-title":"Pattern Recognit."},{"volume-title":"HiTAGU-Net: Reference Implementation","year":"2025","author":"Asefnejad","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/s25134028"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref61","first-page":"3665","article-title":"UniFormer V2: Unified transformer for efficient spatiotemporal representation learning","volume-title":"Proc. IEEE\/CVF CVPR","author":"Li"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref63","article-title":"Cross-modal self-attention for action recognition","volume":"101","author":"Zhang","year":"2023","journal-title":"Inf. Fusion"},{"issue":"4","key":"ref64","first-page":"5127","article-title":"Efficient hierarchical attention networks for video action recognition","volume":"35","author":"Hu","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref65","first-page":"146512","article-title":"Lightweight CNNs for real-time action recognition","volume":"9","author":"Tang","year":"2021","journal-title":"IEEE Access"},{"issue":"10","key":"ref66","first-page":"3817","article-title":"Efficient human activity recognition for edge devices using pruning and quantization","volume":"22","author":"Raza","year":"2022","journal-title":"Sensors"},{"issue":"7","key":"ref67","first-page":"6234","article-title":"Edge-friendly HAR via hierarchical lightweight networks","volume":"10","author":"Park","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref68","first-page":"1265","article-title":"Knowledge distillation-based quantized HAR networks","volume":"557","author":"Chen","year":"2024","journal-title":"Neurocomputing"},{"issue":"10","key":"ref69","first-page":"1","article-title":"How to improve video analytics with action recognition: A comprehensive survey","volume":"56","author":"Mahmood","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.06.014"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref75","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Simonyan"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11284850.pdf?arnumber=11284850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:05:52Z","timestamp":1766127952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11284850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3641691","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}