[ 1 ] Ben Mabrouk A, Zagrouba E. Abnormal behavior recognition for intelligent video surveillance systems [ J ] . Expert Systems with Applications: An International Journal, 2018, 91(C):480 - 491. [2]Wang L, Huynh D Q, Koniusz P. A comparative review of recent kinect-based action recognition algorithms[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2020, 29: 15-28. [3]卢修生,姚鸿勋. 视频中动作识别任务综述[J]. 智能计算机与应用, 2020, 10(3): 406-411.[4]Wang H, Klser A, Schmid C, et al. Action recognition by dense trajectories[C]∥CVPR. Colorado Springs, CO, USA. IEEE, 2011: 3169-3176. [5]Klaeser A, Marszaek M, Schmid C. A spatio-temporal descriptor based on 3D-gradients[C]∥BMVC 2008-19th British Machine Vision Conference. Leeds. British Machine Vision Association, 2008: 1-10. [6]Brox T, Malik J. Large displacement optical flow: descriptor matching in variational motion estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(3): 500-513. [7]许培振, 余志斌, 金炜东, 等. 基于提高的稠密轨迹人体行为识别[J]. 系统仿真学报, 2017, 29(9): 2053-2058. [8]Patel C I, Labana D, Pandya S, et al. Histogram of oriented gradient-based fusion of features for human action recognition in action video sequences[J]. Sensors, 2020, 20(24):7299. [9]Xia L M, Ma W T. Human action recognition using high-order feature of optical flows[J]. The Journal of Supercomputing, 2021, 77(12): 14230-14251. [10]Heslinga F G, Pluim J P W, Dashtbozorg B, et al. Approximation of a pipeline of unsupervised retina image analysis methods with a CNN[C]∥Medical Imaging 2019: Image Processing. San Diego, USA. SPIE, 2019, 10949: 416-422.