[1] C LIU, X LI, Q LI et al. Robot recognizing humans intention and interacting with humans based on a multi-task model combining ST-GCN-LSTM model and YOLO model. Neurocomputing, 430, 174-184(2021).

[2] X J HU, J Z DAI, M LI et al. Online human action detection and anticipation in videos： a survey. Neurocomputing, 491, 395-413(2022).

[3] [3] 3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

[4] Y LIU, F YANG, D GINHAC. ACDnet： an action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation. Pattern Recognition Letters, 145, 118-126(2021).

[5] Z H YUAN, J C STROUD, T LU et al. Temporal action localization by structured maximal sums, 3215-3223(2017).

[6] WEI， ZHANG, WEI， ZHANG. I2Net： Mining intra-video and inter-video attention for temporal action localization. Neurocomputing, 444, 16-29(2021).

[7] Y P HUANG, Q DAI, Y T LU. Decoupling localization and classification in single shot temporal action detection, 1288-1293(2019).

[8] Y ZHAO, Y J XIONG, L M WANG et al. Temporal action detection with structured segment networks. International Journal of Computer Vision, 128, 74-95(2020).

[9] T W LIN, X ZHAO, H S SU. Joint learning of local and global context for temporal action proposal generation. IEEE Transactions on Circuits and Systems for Video Technology, 30, 4899-4912(2020).

[10] H J XU, K SAENKO. R-C3D： region convolutional 3D network for temporal activity detection, 5794-5803(2017).

[11] G CHEN, C ZHANG, Y X ZOU. AFNet： temporal locality-aware network with dual structure for accurate and fast action detection. IEEE Transactions on Multimedia, 23, 2672-2682(2021).

[12] H J XU, K SAENKO. Two-stream region convolutional 3D network for temporal activity detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41, 2319-2332(2019).

[13] L YANG, H W PENG, D W ZHANG et al. Revisiting anchor mechanisms for temporal action localization. IEEE Transactions on Image Processing： a Publication of the IEEE Signal Processing Society(2020).

[14] [14] 14孟月波， 金丹， 刘光辉， 等. 共享核空洞卷积与注意力引导FPN文本检测［J］. 光学 精密工程， 2021， 29（8）： 1955-1967. doi: 10.37188/OPE.20212908.1955MENGY B， JIND， LIUG H， et al. Text detection with kernel-sharing dilated convolutions and attention-guided FPN［J］. Opt. Precision Eng.， 2021， 29（8）： 1955-1967.（in Chinese）. doi: 10.37188/OPE.20212908.1955

[15] [15] 15毛琳， 曹哲， 杨大伟， 等. 多阶段边界参考网络的动作分割［J］. 光学 精密工程， 2022， 30（3）： 340-349. doi: 10.37188/OPE.20223003.0340MAOL， CAOZH， YANGD W， et al. Multi-stage boundary reference network for action segmentation［J］. Opt. Precision Eng.， 2022， 30（3）： 340-349.（in Chinese）. doi: 10.37188/OPE.20223003.0340

[16] BAIRONG， LI, BAIRONG， LI. Learning frame-level affinity with video-level labels for weakly supervised temporal action detection. Neurocomputing, 463, 109-121(2021).

[17] W F YANG, T Z ZHANG, Z D MAO et al. Multi-scale structure-aware network for weakly supervised temporal action detection. IEEE Transactions on Image Processing： a Publication of the IEEE Signal Processing Society, 30, 5848-5861(2021).

[18] L YANG, J W HAN, T ZHAO et al. Background-click supervision for temporal action localization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 9814-9829(2022).

[19] M H ZHAO, S S ZHONG, X Y FU et al. Deep residual shrinkage networks for fault diagnosis. IEEE Transactions on Industrial Informatics, 16, 4681-4690(2020).

[20] L W LI, S Y QIN, Z LU et al. One-shot learning gesture recognition based on joint training of 3D ResNet and memory module. Multimedia Tools and Applications, 79, 6727-6757(2020).

[21] YIWEI， WANG, YIWEI， WANG. Temporal convolutional network with soft thresholding and attention mechanism for machinery prognostics. Journal of Manufacturing Systems, 60, 512-526(2021).

[22] W X CUI, S H LIU, F JIANG et al. Image compressed sensing using non-local neural network. IEEE Transactions on Multimedia(2021).

[23] Y JIANG, J LIU, A ZAMIR et al. THUMOS challenge： Action recognition with a large number of classes. http：//crcv.ucf.edu/THUMOS14/(2014).

[24] F C HEILBRON, V ESCORCIA, B GHANEM et al. ActivityNet： a large-scale video benchmark for human activity understanding, 961-970(2015).

[25] X Y ZHANG, H C SHI, C S LI et al. TwinNet： twin structured knowledge transfer network for weakly supervised action localization. Machine Intelligence Research, 19, 227-246(2022).

[26] G Z LI, J LI, N N WANG et al. Multi-hierarchical category supervision for weakly-supervised temporal action localization. IEEE Transactions on Image Processing： a Publication of the IEEE Signal Processing Society, 30, 9332-9344(2021).