{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:59:23Z","timestamp":1776931163015,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,12]]},"DOI":"10.1145\/3756884.3765982","type":"proceedings-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T07:47:22Z","timestamp":1764920842000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Gated Temporal Shifts with Depth-Efficient Channel Attention for Real-Time Hand-Gesture Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5209-9893","authenticated-orcid":false,"given":"Salah eddine","family":"Laidoudi","sequence":"first","affiliation":[{"name":"IBISC, Universit\u00e9 Paris-Saclay, Univ Evry, Evry-courcouronnes, France and ESME Research Lab, ESME SUDRIA, Ivry-sur-seine, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7070-006X","authenticated-orcid":false,"given":"Madjid","family":"Maidi","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris 8 LIASD, Paris, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2221-4264","authenticated-orcid":false,"given":"Samir","family":"Otmane","sequence":"additional","affiliation":[{"name":"IBISC, Universit\u00e9 Paris-Saclay, Univ Evry, Evry-courcouronnes, France"}]}],"member":"320","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_3_1_3_2","first-page":"813","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is Space-Time Attention All You Need for Video Understanding?. In Proceedings of the International Conference on Machine Learning (ICML). 813\u2013824."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.153"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"ZhiYu Jiang Yi Zhang and Shu Hu. 2023. ESTI: an action recognition network with enhanced spatio-temporal information. International Journal of Machine Learning and Cybernetics 14 9 (2023) 3059\u20133070.","DOI":"10.1007\/s13042-023-01820-x"},{"key":"e_1_3_3_1_12_2","unstructured":"Colin Lea Michael\u00a0D. Flynn Rene Vidal Austin Reiter and Gregory\u00a0D. Hager. 2016. Temporal Convolutional Networks for Action Segmentation and Detection. arxiv:https:\/\/arXiv.org\/abs\/1611.05267\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1611.05267"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"TIAN\u00a0Ming LIU\u00a0Jie WANG\u00a0Yue. 2023. Dynamic Gesture Recognition Network Based on Multiscale Spatiotemporal Feature Fusion. Journal of Electronics & Information Technology 45 220758 (2023) 2614. 10.11999\/JEIT220758","DOI":"10.11999\/JEIT220758"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"e_1_3_3_1_16_2","first-page":"5761","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Min Yang","year":"2020","unstructured":"Yang Min, Liangli Zhang, Xiujuan He, and Hong Liu. 2020. PointLSTM: A Multi-Point LSTM Network for 3D Hand Gesture Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5761\u20135770."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.455"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"e_1_3_3_1_19_2","unstructured":"Lionel Pigou A\u00e4ron van\u00a0den Oord Sander Dieleman Mieke\u00a0Van Herreweghe and Joni Dambre. 2016. Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video. arxiv:https:\/\/arXiv.org\/abs\/1506.01911\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1506.01911"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"e_1_3_3_1_22_2","first-page":"568","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream Convolutional Networks for Action Recognition in Videos. In Advances in Neural Information Processing Systems (NeurIPS). 568\u2013576."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01080"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Liu Ting-Long. 2024. Short-Term Action Learning for Video Action Recognition. IEEE Access 12 (2024) 30867\u201330875.","DOI":"10.1109\/ACCESS.2024.3364810"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_3_1_26_2","unstructured":"Du Tran Jamie Ray Zheng Shou Shih-Fu Chang and Manohar Paluri. 2017. Convnet architecture search for spatiotemporal feature learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1708.05038 (2017)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.100"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Limin Wang Yuanjun Xiong Zhe Wang Yu Qiao Dahua Lin Xiaoou Tang and Luc Van\u00a0Gool. 2019. Temporal Segment Networks for Action Recognition in Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence 41 11 (2019) 2740\u20132755. 10.1109\/TPAMI.2018.2868668","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"e_1_3_3_1_31_2","unstructured":"Xiaolong Wang Ross Girshick Abhinav Gupta and Kaiming He. 2018. Non-local Neural Networks. arxiv:https:\/\/arXiv.org\/abs\/1711.07971\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1711.07971"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_3_1_34_2","unstructured":"Can Zhang Yuexian Zou Guang Chen and Lei Gan. 2020. Pan: Towards fast action recognition via learning persistence of appearance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2008.03462 (2020)."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00092"},{"key":"e_1_3_3_1_36_2","unstructured":"Xiangyu Zhang Xinyu Zhou Mengxiao Lin and Jian Sun. 2017. ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. arxiv:https:\/\/arXiv.org\/abs\/1707.01083\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1707.01083"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","unstructured":"Enmin Zhong Carlos\u00a0R. del Blanco Daniel Berj\u00f3n Fernando Jaureguizar and Narciso Garc\u00eda. 2023. Real-Time Monocular Skeleton-Based Hand Gesture Recognition Using 3D-Jointsformer. Sensors 23 16 (2023) 7066. 10.3390\/s23167066","DOI":"10.3390\/s23167066"}],"event":{"name":"VRST '25: 31st ACM Symposium on Virtual Reality Software and Technology","location":"Montreal QC Canada","acronym":"VRST '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 2025 31st ACM Symposium on Virtual Reality Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3756884.3765982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T09:11:34Z","timestamp":1764925894000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3756884.3765982"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":36,"alternative-id":["10.1145\/3756884.3765982","10.1145\/3756884"],"URL":"https:\/\/doi.org\/10.1145\/3756884.3765982","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]},"assertion":[{"value":"2025-12-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}