{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T06:02:42Z","timestamp":1763445762641,"version":"3.45.0"},"reference-count":34,"publisher":"Tech Science Press","issue":"1","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":88,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.061376","type":"journal-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T03:04:46Z","timestamp":1740020686000},"page":"1101-1116","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Lightweight Classroom Student Action Recognition Method Based on Spatiotemporal Multimodal Feature Fusion"],"prefix":"10.32604","volume":"83","author":[{"given":"Shaodong","family":"Zou","sequence":"first","affiliation":[]},{"given":"Di","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jianhou","family":"Gan","sequence":"additional","affiliation":[]},{"given":"Juxiang","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Jiatian","family":"Mei","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","series-title":"2015 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"4489","article-title":"Learning spatiotemporal features with 3D convolutional networks","author":"Tran","year":"2015"},{"key":"ref2","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7794","article-title":"Non-local neural networks","author":"Wang","year":"2018"},{"key":"ref3","first-page":"2217","article-title":"Real-time violent action recognition using key frames extraction and deep learning","volume":"59","author":"Ahmed","year":"2021","journal-title":"Comput Mater Contin"},{"key":"ref4","first-page":"5593","article-title":"Smart deep learning based human behaviour classification for video surveillance","volume":"72","author":"AlQaralleh","year":"2022","journal-title":"Comput Mater Contin"},{"key":"ref5","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12026","article-title":"Two-stream adaptive graph convolutional networks for skeleton-based action recognition","author":"Shi","year":"2019"},{"key":"ref6","first-page":"4489","article-title":"BCCLR: a skeleton-based action recognition with graph convolutional network combining behavior dependence and context clues","volume":"79","author":"Wang","year":"2024","journal-title":"Comput Mater Contin"},{"key":"ref7","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"13359","article-title":"Channel-wise topology refinement graph convolution for skeleton-based action recognition","author":"Chen","year":"2021"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1007\/s00138-024-01608-1","article-title":"Intercity rail platform abnormal action recognition based on a skeleton tracking and recognition framework","volume":"35","author":"Dong","year":"2024","journal-title":"Mach Vis Appl"},{"key":"ref9","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13289","article-title":"MMTM: multimodal transfer module for Cnn fusion","author":"Vaezi Joze","year":"2020"},{"key":"ref10","series-title":"2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"3381","article-title":"Multi-view action recognition using contrastive learning","author":"Shah","year":"2023"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"104068","DOI":"10.1016\/j.cviu.2024.104068","article-title":"Classroom teacher action recognition based on spatio-temporal dual-branch feature fusion","volume":"247","author":"Wu","year":"2024","journal-title":"Comput Vis Image Understanding"},{"key":"ref12","first-page":"1089","article-title":"HgaNets: fusion of visual data and skeletal heatmap for human gesture action recognition","volume":"79","author":"Liang","year":"2024","journal-title":"Comput Mater Contin"},{"key":"ref13","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"7083","article-title":"TSM: temporal shift module for efficient video understanding","author":"Lin","year":"2019"},{"key":"ref14","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"203","article-title":"X3D: expanding architectures for efficient video recognition","author":"Feichtenhofer","year":"2020"},{"key":"ref15","unstructured":"Li K, Wang Y, Gao P, Song G, Liu Y, Li H, et al. Uniformer: unified transformer for efficient spatiotemporal representation learning. arXiv:2201.04676. 2022."},{"key":"ref16","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","volume":"32","author":"Yan","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1016\/j.neucom.2022.06.070","article-title":"PB-GCN: progressive binary graph convolutional networks for skeleton-based action recognition","volume":"501","author":"Zhao","year":"2022","journal-title":"Neurocomputing"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/TIP.2023.3308750","article-title":"B2C-AFM: bi-directional co-temporal and cross-spatial attention fusion model for human action recognition","author":"Guo","year":"2023","journal-title":"IEEE Trans Image Process"},{"key":"ref19","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2969","article-title":"Revisiting skeleton-based action recognition","author":"Duan","year":"2022"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"3007","DOI":"10.1109\/TPAMI.2017.2771306","article-title":"Skeleton-based action recognition using spatio-temporal lstm network with trust gates","volume":"40","author":"Liu","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.patcog.2017.02.030","article-title":"Enhanced skeleton visualization for view invariant human action recognition","volume":"68","author":"Liu","year":"2017","journal-title":"Pattern Recognit"},{"key":"ref22","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7912","article-title":"Skeleton-based action recognition with directed graph neural networks","author":"Shi","year":"2019"},{"key":"ref23","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"143","article-title":"Disentangling and unifying graph convolutions for skeleton-based action recognition","author":"Liu","year":"2020"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"3305","DOI":"10.3390\/s20113305","article-title":"A hybrid network for large-scale action recognition from rgb and depth modalities","volume":"20","author":"Wang","year":"2020","journal-title":"Sensors"},{"key":"ref25","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"469","article-title":"Glimpse clouds: human activity recognition from unstructured feature points","author":"Baradel","year":"2018"},{"key":"ref26","series-title":"2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"3330","article-title":"Star-transformer: a spatio-temporal cross attention transformer for human action recognition","author":"Ahn","year":"2023"},{"key":"ref27","first-page":"3199","article-title":"Multimodal fusion via teacher-student network for indoor action recognition","volume":"35","author":"Yu","year":"2021","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.1109\/TIP.2017.2785279","article-title":"Skeleton-based human action recognition with global context-aware attention LSTM networks","volume":"27","author":"Liu","year":"2017","journal-title":"IEEE Trans Image Process"},{"key":"ref29","first-page":"4873","article-title":"DVANet: disentangling view and action features for multi-view action recognition","volume":"38","author":"Siddiqui","year":"2024","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11042-023-17788-3","article-title":"VT-BPAN: vision transformer-based bilinear pooling and attention network fusion of rgb and skeleton features for human action recognition","volume":"83","author":"Sun","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"9703","DOI":"10.1109\/TPAMI.2021.3127885","article-title":"VPN++: rethinking video-pose embeddings for understanding activities of daily living","volume":"44","author":"Das","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref32","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6450","article-title":"A closer look at spatiotemporal convolutions for action recognition","author":"Tran","year":"2018"},{"key":"ref33","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6202","article-title":"Slowfast networks for video recognition","author":"Feichtenhofer","year":"2019"},{"key":"ref34","unstructured":"Bertasius G, Wang H, Torresani L. Is space-time attention all you need for video understanding? arXiv:2102.05095. 2021."}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-83-1\/TSP_CMC_61376\/TSP_CMC_61376.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T06:39:43Z","timestamp":1763102383000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v83n1\/60114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.061376","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2024-11-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-13","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-26","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}