[1] [1] 1张红颖， 安征. 基于改进双流时空网络的人体行为识别［J］. 光学 精密工程， 2021， 29（2）： 420-429. doi: 10.37188/OPE.20212902.0420ZHANGH Y， ANZH. Human action recognition based on improved two-stream spatiotemporal network［J］. Opt. Precision Eng.， 2021， 29（2）： 420-429. （in Chinese）. doi: 10.37188/OPE.20212902.0420

[2] [2] 2马世伟， 刘丽娜， 傅琪， 等. 采用PHOG融合特征和多类别Adaboost分类器的行为识别［J］. 光学 精密工程， 2018， 26（11）： 2827-2837. doi: 10.3788/ope.20182611.2827MASH W， LIUL N， FUQ， et al. Using PHOG fusion features and multi-class Adaboost classifier for human behavior recognition［J］. Opt. Precision Eng.， 2018， 26（11）： 2827-2837. （in Chinese）. doi: 10.3788/ope.20182611.2827

[3] OORD AVAN DEN, DIELEMAN S et al. WaveNet： a generative model for raw audio[J]. CoRR(2016).

[4] LEA C, FLYNN M D, VIDAL R et al. Temporal convolutional networks for action segmentation and detection[C], 1003-1012(2017).

[5] KUEHNE H, RICHARD A, GALL J. A hybrid RNN-HMM approach for weakly supervised temporal action segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 765-779(2018).

[6] [6] 6李庆辉， 李艾华， 郑勇， 等. 利用几何特征和时序注意递归网络的动作识别［J］. 光学 精密工程， 2018， 26（10）： 2584-2591. doi: 10.3788/ope.20182610.2584LIQ H， LIA H， ZHENGY， et al. Action recognition using geometric features and recurrent temporal attention network［J］. Opt. Precision Eng.， 2018， 26（10）： 2584-2591. （in Chinese）. doi: 10.3788/ope.20182610.2584

[7] SINGH B, MARKS T K, JONES M et al. A multi- stream Bi-directional recurrent neural network for fine-grained action detection[C], 1961-1970(2016).

[8] FARHA Y A, GALL J. MS-TCN： multi-stage temporal convolutional network for action segmentation[C], 3570-3579(2019).

[9] LI S J, ABUFARHA Y, LIU Y et al. MS-TCN： multi-stage temporal convolutional network for action segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 99, 1(1756).

[10] WANG Z Z, GAO Z T, WANG L M et al. Boundary-aware cascade networks for temporal action segmentation[J]. Computer Vision-ECCV, 2020, 34-51(2020).

[11] LIN T W, ZHAO X, SU H S et al. BSN： boundary sensitive network for temporal action proposal generation[J]. Computer Vision-ECCV, 2018, 3-21(2018).

[12] CARREIRA J, ZISSERMAN A. Quo vadis， action recognition？[C], 4724-4733(2017).

[13] LEI P, TODOROVIC S. Temporal deformable residual networks for action segmentation in videos[C], 6742-6751(2018).

[14] LEA C, REITER A, VIDAL R et al. Segmental spatiotemporal CNNs for fine-grained action segmentation[J]. Computer Vision-ECCV, 2016, 36-52(2016).

[15] KUEHNE H, GALL J, SERRE T. An end-to-end generative framework for video segmentation and recognition[C], 1-8(2016).

[16] RICHARD A, KUEHNE H, GALL J. Weakly supervised action learning with RNN based fine-to- coarse modeling[C], 1273-1282(2017).