{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:22:02Z","timestamp":1780726922843,"version":"3.54.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"34","license":[{"start":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T00:00:00Z","timestamp":1745193600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T00:00:00Z","timestamp":1745193600000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-025-20653-0","type":"journal-article","created":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T06:45:09Z","timestamp":1745217909000},"page":"42757-42776","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Hybrid attention-inflated 3D architecture for human action recognition"],"prefix":"10.1007","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1642-1838","authenticated-orcid":false,"given":"Khadija","family":"Lasri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamal","family":"Riffi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khalid","family":"El Fazazy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adnane","family":"Mohamed Mahraz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid","family":"Tairi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,21]]},"reference":[{"issue":"16","key":"20653_CR1","doi-asserted-by":"publisher","first-page":"20415","DOI":"10.1007\/s11042-017-5438-7","volume":"77","author":"Q Abbas","year":"2018","unstructured":"Abbas Q, Ibrahim MEA, Jaffar MA (2018) Video scene analysis: An overview and challenges on deep learning algorithms. Multimed Tools Appl 77(16):20415\u201320453. https:\/\/doi.org\/10.1007\/s11042-017-5438-7","journal-title":"Multimed Tools Appl"},{"key":"20653_CR2","doi-asserted-by":"publisher","unstructured":"Ali AA, El-Hafeez TA, Mohany YK (2019) An accurate system for face detection and recognition. J Adv Math Comput Sci 1\u201319. https:\/\/doi.org\/10.9734\/jamcs\/2019\/v33i330178","DOI":"10.9734\/jamcs\/2019\/v33i330178"},{"key":"20653_CR3","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? A new model and the kinetics dataset. 2017 IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI: IEEE, pp 4724\u20134733","DOI":"10.1109\/CVPR.2017.502"},{"key":"20653_CR4","unstructured":"Chen H, Yu Z, Liu X, Peng W, Lee Y, Zhao G (2020) 2nd place scheme on action recognition track of ECCV 2020 VIPriors challenges: An efficient optical flow stream guided framework. arXiv:2008.03996"},{"key":"20653_CR5","doi-asserted-by":"crossref","unstructured":"Dhiman C, Vishwakarma DK (2019) A review of state-of-the-art techniques for abnormal human activity recognition. Eng Appl Artif Intell, p 25","DOI":"10.1016\/j.engappai.2018.08.014"},{"issue":"7","key":"20653_CR6","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/JPROC.2002.801449","volume":"90","author":"Z Duric","year":"2002","unstructured":"Duric Z, Gray WD, Heishman R, Li F, Rosenfeld A, Schoelles MJ, Wechsler H (2002) Integrating perceptual and cognitive modeling for adaptive and intelligent human-computer interaction. Proc IEEE 90(7):18","journal-title":"Proc IEEE"},{"issue":"15","key":"20653_CR7","doi-asserted-by":"publisher","first-page":"6727","DOI":"10.3390\/s23156727","volume":"23","author":"M Eman","year":"2023","unstructured":"Eman M, Mahmoud TM, Ibrahim MM, Abd El-Hafeez T (2023) Innovative hybrid approach for masked face recognition using pretrained mask detection and segmentation, robust PCA, and KNN classifier. Sensors 23(15):6727. https:\/\/doi.org\/10.3390\/s23156727","journal-title":"Sensors"},{"key":"20653_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J, He K (2019) SlowFast networks for video recognition. 2019 IEEE\/CVF international conference on computer vision (ICCV), Seoul, Korea (South): IEEE, pp 6201\u20136210","DOI":"10.1109\/ICCV.2019.00630"},{"key":"20653_CR9","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes RP (2016a) Spatiotemporal residual networks for video action recognition. arXiv:1611.02155 [cs]","DOI":"10.1109\/CVPR.2017.787"},{"key":"20653_CR10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes RP (2017) Spatiotemporal multiplier networks for video action recognition. 2017 IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI: IEEE, pp 7445\u20137454","DOI":"10.1109\/CVPR.2017.787"},{"key":"20653_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016b) Convolutional two-stream network fusion for video action recognition. arXiv:1604.06573 [cs]","DOI":"10.1109\/CVPR.2016.213"},{"key":"20653_CR12","doi-asserted-by":"crossref","unstructured":"Hara K, Kataoka H, Satoh Y (2017) Learning spatio-temporal features with 3D residual networks for action recognition. 2017 IEEE international conference on computer vision workshops (ICCVW), Venice: IEEE, pp 3154\u20133160","DOI":"10.1109\/ICCVW.2017.373"},{"key":"20653_CR13","doi-asserted-by":"crossref","unstructured":"Hara K, Kataoka H, Satoh Y (2018) Can spatiotemporal 3D CNNs retrace the History of 2D CNNs and ImageNet? arXiv:1711.09577 [cs]","DOI":"10.1109\/CVPR.2018.00685"},{"key":"20653_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, pp 770\u2013778 USA: IEEE","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"20653_CR15","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3390\/bdcc7020087","volume":"7","author":"G Hnini","year":"2023","unstructured":"Hnini G, Riffi J, Mahraz MA, Yahyaouy A, Tairi H (2023) Attention mechanism and support vector machine for image-based e-mail spam filtering. Big Data Cognit Comput 7(2):87. https:\/\/doi.org\/10.3390\/bdcc7020087","journal-title":"Big Data Cognit Comput"},{"key":"20653_CR16","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Adam H (2017) MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861"},{"key":"20653_CR17","doi-asserted-by":"crossref","unstructured":"Karacsony T, Jeni LA, De\u00a0La Torre\u00a0Frade F, Cunha JPS (2023) Deep learning methods for single camera based clinical in-bed movement action recognition","DOI":"10.36227\/techrxiv.23796111.v1"},{"key":"20653_CR18","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, Zisserman A (2017) The kinetics human action video dataset. arXiv:1705.06950 [cs]"},{"key":"20653_CR19","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-2947413\/v1","volume-title":"Basketball action recognition based on the combination of YOLO and a deep fuzzy LSTM network","author":"SB Khobdeh","year":"2023","unstructured":"Khobdeh SB, Yamaghani MR, Sareshkeh SK (2023) Basketball action recognition based on the combination of YOLO and a deep fuzzy LSTM network. Preprint, In Review"},{"key":"20653_CR20","unstructured":"K\u00f6p\u00fckl\u00fc O, Kose N, Gunduz A, Rigoll G (2021) Resource efficient 3D convolutional neural networks. arXiv:1904.02422. arXiv"},{"key":"20653_CR21","doi-asserted-by":"crossref","unstructured":"Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) HMDB: A large video database for human motion recognition. 2011 International conference on computer vision, Barcelona, Spain: IEEE, pp 2556\u20132563","DOI":"10.1109\/ICCV.2011.6126543"},{"issue":"6","key":"20653_CR22","doi-asserted-by":"publisher","first-page":"2835","DOI":"10.1007\/s00521-023-09204-6","volume":"36","author":"A Omar","year":"2024","unstructured":"Omar A, Abd El-Hafeez T (2024) Optimizing epileptic seizure recognition performance with feature scaling and dropout layers. Neural Comput Appl 36(6):2835\u20132852. https:\/\/doi.org\/10.1007\/s00521-023-09204-6","journal-title":"Neural Comput Appl"},{"key":"20653_CR23","doi-asserted-by":"crossref","unstructured":"Qiu Z, Yao T, Mei T (2017) Learning spatio-temporal representation with pseudo-3D residual networks. arXiv:1711.10305 [cs]","DOI":"10.1109\/ICCV.2017.590"},{"key":"20653_CR24","doi-asserted-by":"crossref","unstructured":"Saabia AAB, El-Hafeez T, Zaki AM (2019) Face recognition based on grey wolf optimization for feature selection. Hassanien AE, Tolba MF, Shaalan K, Azar AT (Eds) Proceedings of the international conference on advanced intelligent systems and informatics 2018, vol 845. Cham: Springer International Publishing, pp 273\u2013283","DOI":"10.1007\/978-3-319-99010-1_25"},{"key":"20653_CR25","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. arXiv:1406.2199 [cs]"},{"key":"20653_CR26","unstructured":"Song X, Lan C, Zeng W, Xing J, Yang J, Sun X (2018) Temporal-spatial mapping for action recognition. arXiv:1809.03669"},{"key":"20653_CR27","unstructured":"Soomro K, Zamir AR, Shah M (2012) UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402"},{"key":"20653_CR28","doi-asserted-by":"crossref","unstructured":"Stroud JC, Ross DA, Sun C, Deng J, Sukthankar R (2020) D3D: Distilled 3D networks for video action recognition. 2020 IEEE winter conference on applications of computer vision (WACV), Snowmass Village, CO, USA: IEEE, pp 614\u2013623","DOI":"10.1109\/WACV45572.2020.9093274"},{"key":"20653_CR29","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Rabinovich A (2015) Going deeper with convolutions. 2015 IEEE conference on computer vision and pattern recognition (CVPR), Boston, MA, USA: IEEE, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"20653_CR30","doi-asserted-by":"publisher","unstructured":"Taha M, Mostafa T, Abd El-Rahman T (2023) A novel hybrid approach to masked face recognition using robust PCA and GOA optimizer. Sci J Damietta Fac Sci 0(0):0\u20130. https:\/\/doi.org\/10.21608\/sjdfs.2023.222524.1117","DOI":"10.21608\/sjdfs.2023.222524.1117"},{"key":"20653_CR31","unstructured":"Tran D, Ray J, Shou Z, Chang SF, Paluri M (2017) ConvNet architecture search for spatiotemporal feature learning. arXiv:1708.05038 [cs]"},{"key":"20653_CR32","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Feiszli M, Torresani L (2019) Video classification with channel-separated convolutional networks. 2019 IEEE\/CVF international conference on computer vision (ICCV), Seoul, Korea (South): IEEE, pp 5551\u20135560","DOI":"10.1109\/ICCV.2019.00565"},{"key":"20653_CR33","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (2018) A closer look at spatiotemporal convolutions for action recognition. arXiv:1711.11248 [cs]","DOI":"10.1109\/CVPR.2018.00675"},{"key":"20653_CR34","doi-asserted-by":"crossref","unstructured":"Wang H, Tran D, Torresani L, Feiszli M (2020) Video modeling with correlation networks. 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), Seattle, WA, USA: IEEE, pp 349\u2013358","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"20653_CR35","unstructured":"Wang L, Tong Z, Ji B, Wu G (2024) TDN: Temporal difference networks for efficient action recognition., 13"},{"key":"20653_CR36","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van\u00a0Gool L (2016) Temporal segment networks: Towards good practices for deep action recognition. arXiv:1608.00859 [cs]","DOI":"10.1007\/978-3-319-46484-8_2"},{"issue":"11","key":"20653_CR37","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2019","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2019) Temporal segment networks for action recognition in videos. IEEE Trans Pattern Anal Mach Intell 41(11):2740\u20132755. https:\/\/doi.org\/10.1109\/TPAMI.2018.2868668","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20653_CR38","unstructured":"Wang Y, Long M, Wang J, Yu PS (2019) Spatiotemporal pyramid network for video action recognition. arXiv:1903.01038 [cs]"},{"key":"20653_CR39","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Dollar P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. 2017 IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI: IEEE, pp 5987\u20135995","DOI":"10.1109\/CVPR.2017.634"},{"key":"20653_CR40","doi-asserted-by":"crossref","unstructured":"Xie S, Sun C, Huang J, Tu Z, Murphy K (2018) Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. arXiv:1712.04851 [cs]","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"20653_CR41","doi-asserted-by":"publisher","unstructured":"Xu Y, Feng Y, Xie Z, Xie M, Luo W (2020) Action Recognition Using High Temporal Resolution 3D Neural Network Based on Dilated Convolution. IEEE Access, vol. 8, pp. 165365\u2013165372. https:\/\/doi.org\/10.1109\/ACCESS.2020.3022407","DOI":"10.1109\/ACCESS.2020.3022407"},{"key":"20653_CR42","doi-asserted-by":"crossref","unstructured":"Zhang C, Zou Y, Chen G, Gan L (2020) PAN: Towards fast action recognition via learning persistence of appearance. arXiv:2008.03462","DOI":"10.1145\/3343031.3350876"},{"key":"20653_CR43","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2017) ShuffleNet: An extremely efficient convolutional neural network for mobile devices. arXiv:1707.01083","DOI":"10.1109\/CVPR.2018.00716"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-20653-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-025-20653-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-20653-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T23:08:13Z","timestamp":1759446493000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-025-20653-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,21]]},"references-count":43,"journal-issue":{"issue":"34","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["20653"],"URL":"https:\/\/doi.org\/10.1007\/s11042-025-20653-0","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,21]]},"assertion":[{"value":"25 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 December 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2025","order":4,"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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}]}}