基于骨骼图神经网络的人体行为识别综述

doi:10.3778/j.issn.1002-8331.2407-0391

摘要/Abstract

摘要： 基于骨骼图神经网络的人体行为识别凭借其简洁性和鲁棒性引起了人们的广泛关注，图数据对于处理人体骨骼信息有天然的优势,逐渐成为行为识别领域的研究热点。从行为识别这个宽泛的基本概念入手，进一步引入用骨骼图神经网络进行的人体行为识别任务，分别从4个方面对近些年基于骨骼图神经网络的人体行为识别的研究成果进行了归纳总结；介绍了图结构构造拓扑图的不同方法分类、行为识别模型中的常用机制、目前常用的数据集及评价指标与目前主流方法的比较。最后,针对目前的研究状况对基于骨骼图神经网络的人体行为识别存在的问题进行详细的阐述，并立足于研究现状对该领域的未来发展进行了展望。

关键词: 行为识别, 深度学习, 图神经网络, 注意力机制

Abstract: Human action recognition based on skeletal graph neural network has attracted much attention by virtue of its simplicity and robustness, and graph data have a natural advantage in processing human skeletal information, which has gradually become a research hotspot in the field of action recognition. Starting from the broad basic concept of action recognition, this paper further introduces the task of human action recognition using skeletal graph neural networks, and summarizes the research results on human action recognition using skeletal graph neural networks in recent years from four aspects. The paper introduces different methods for constructing topological graphs with graph structures, the common mechanisms used in action recognition models, the comparison of commonly used datasets and evaluation indicators with mainstream methods. Finally, the problems of human action recognition based on skeletal graph neural networks are elaborated in detail with respect to the current state of research, and an outlook on the future development of the field is given based on the current state of research.

Key words: action recognition, deep learning, graph neural networks, attention mechanisms

蒋悦晗, 陈俊杰, 李洪均. 基于骨骼图神经网络的人体行为识别综述[J]. 计算机工程与应用, 2025, 61(3): 34-47.

JIANG Yuehan, CHEN Junjie, LI Hongjun. Review of Human Action Recognition Based on Skeletal Graph Neural Networks[J]. Computer Engineering and Applications, 2025, 61(3): 34-47.

参考文献

[1] MAJUMDER S, KEHTARNAVAZ N. Vision and inertial sensing fusion for human action recognition: a review[J]. IEEE Sensors Journal, 2021, 21(3): 2454-2467.
[2] 申通, 王硕, 李孟, 等. 深度学习在动物行为分析中的应用研究进展[J]. 计算机科学与探索, 2024, 18(3): 612-626.
SHEN T, WANG S, LI M, et al. Research progress in application of deep learning in animal behavior analysis[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(3): 612-626.
[3] 李佳楠, 李锐宜, 赵至夫, 等. 基于多尺度特征图卷积网络的教学行为识别及分析[J]. 计算机科学, 2024, 51(10): 135-143.
LI J N, LI R Y, ZHAO Z F, et al. Recognition and analysis of teaching behavior based on multi-scale GCN[J]. Computer Science, 2024, 51(10): 135-143.
[4] 李嘎, 加云岗, 王志晓, 等. 基于YOLO-CARAFE的人员异常行为识别方法[J]. 计算机技术与发展, 2024, 34(6): 185-191.
LI G, JIA Y G, WANG Z X, et al. Human abnormal behavior recognition method based on YOLO-CARAFE[J]. Computer Technology and Development, 2024, 34(6): 185-191.
[5] 孔玮, 刘云, 李辉, 等. 基于图卷积网络的行为识别方法综述[J]. 控制与决策, 2021, 36(7): 1537-1546.
KONG W, LIU Y, LI H, et al. A survey of action recognition methods based on graph convolutional network[J]. Control and Decision, 2021, 36(7): 1537-1546.
[6] CAO Z, SIMON T, WEI S H, et al. Realtime multi-person 2D pose estimation using part affinity fields[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 1302-1310.
[7] FANG H S, XIE S Q, TAI Y W, et al. RMPE: regional multi-person pose estimation[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2353-2362.
[8] DONAHUE J, HENDRICKS L A, ROHRBACH M, et al. Long-term recurrent convolutional networks for visual recognition and description[C]//Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence. Piscataway: IEEE, 2017: 677-691.
[9] JI S W, YANG M, YU K. 3D convolutional neural networks for human action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 221-231.
[10] TRAN D, BOURDEV L, FERGUS R, et al. Learning spatiotemporal features with 3D convolutional networks[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 4489-4497.
[11] YAO L, TORABI A, CHO K, et al. Describing videos by exploiting temporal structure[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 4507-4515.
[12] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv:1409. 1556, 2014.
[13] LI S J, YI J H, ABU FARHA Y, et al. Pose refinement graph convolutional network for skeleton-based action recognition[J]. IEEE Robotics and Automation Letters, 2021, 6(2): 1028-1035.
[14] MOON G, KWON H, LEE K M, et al. IntegralAction: pose-driven feature integration for robust human action recognition in videos[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2021: 3334-3343.
[15] FENG M, MEUNIER J. Skeleton graph-neural-network-based human action recognition: a survey[J]. Sensors, 2022, 22(6): 2091.
[16] HU K, JIN J L, ZHENG F, et al. Overview of behavior recognition based on deep learning[J]. Artificial Intelligence Review, 2023, 56(3): 1833-1865.
[17] DU L L. Design of dance movement recognition algorithm based on 3D motion capture data[C]//Proceedings of the 2023 2nd International Conference on 3D Immersion, Interaction and Multi-Sensory Experiences. Piscataway: IEEE, 2023: 308-312.
[18] YANG X D, TIAN Y L. EigenJoints-based action recognition using Na?ve-Bayes-nearest-neighbor[C]//Proceedings of the 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2012: 14-19.
[19] ZHOU Y Z, SUN X Y, LUO C, et al. Spatiotemporal fusion in 3D CNNs: a probabilistic view[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 9826-9835.
[20] WU Z X, WANG X, JIANG Y G, et al. Modeling spatial-temporal clues in a hybrid deep learning framework for video classification[C]//Proceedings of the 23rd ACM International Conference on Multimedia. New York: ACM, 2015: 461-470.
[21] GORI M, MONFARDINI G, SCARSELLI F. A new model for learning in graph domains[C]//Proceedings of the 2005 IEEE International Joint Conference on Neural Networks. Piscataway: IEEE, 2005: 729-734.
[22] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv:1609.02907, 2016.
[23] DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[J]. arXiv:1606.09375, 2016.
[24] XU B B, SHEN H W, CAO Q, et al. Graph wavelet neural network[J]. arXiv:1904.07785, 2019.
[25] BROCKSCHMIDT M. GNN-FiLM: graph neural networks with feature-wise linear modulation[C]//Proceedings of the 37th International Conference on Machine Learning, ?2020: 1144-1152.
[26] JIANG J T, CUI Z, XU C Y, et al. Gaussian-induced convolution for graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019: 4007-4014.
[27] CHAMI I, YING R, Ré C, et al. Hyperbolic graph convolutional neural networks[C]//Advances in Neural Information Processing Systems, 2019: 4869-4880.
[28] YAN S J, XIONG Y J, LIN D H. Spatial temporal graph convolutional networks for skeleton-based action recognition[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018: 7444-7452.
[29] 张艳, 肖文琛, 张博. 基于双流骨架信息的人体动作识别方法[J]. 计算机技术与发展, 2024, 34(1): 158-163.
ZHANG Y, XIAO W C, ZHANG B. Human action recognition method based on two-flow skeleton information[J]. Computer Technology and Development, 2024, 34(1): 158-163.
[30] 李扬志, 袁家政, 刘宏哲. 基于时空注意力图卷积网络模型的人体骨架动作识别算法[J]. 计算机应用, 2021, 41(7): 1915-1921.
LI Y Z, YUAN J Z, LIU H Z. Human skeleton-based action recognition algorithm based on spatiotemporal attention graph convolutional network model[J]. Journal of Computer Applications, 2021, 41(7): 1915-1921.
[31] 毛国君, 王一锦. 融合内外依赖的人体骨架动作识别模型[J]. 计算机工程与应用, 2023, 59(21): 132-140.
MAO G J, WANG Y J. Human skeleton action recognition model integrated internal and external dependences[J]. Computer Engineering and Applications, 2023, 59(21): 132-140.
[32] LI M S, CHEN S H, CHEN X, et al. Actional-structural graph convolutional networks for skeleton-based action recognition[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 3590-3598.
[33] GAO J L, HE T, ZHOU X, et al. Focusing and diffusion: bidirectional attentive graph convolutional networks for skeleton-based action recognition[J]. arXiv:1912.11521, 2019.
[34] SHI L, ZHANG Y F, CHENG J, et al. Skeleton-based action recognition with directed graph neural networks[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 7904-7913.
[35] XIONG X, MIN W D, WANG Q, et al. Human skeleton feature optimizer and adaptive structure enhancement graph convolution network for action recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(1): 342-353.
[36] LIU R, XU C Y, ZHANG T, et al. Si-GCN: structure-induced graph convolution network for skeleton-based action recognition[C]//Proceedings of the 2019 International Joint Conference on Neural Networks. Piscataway: IEEE, 2019: 1-8.
[37] ZUO Q, ZOU L, FAN C E, et al. Whole and part adaptive fusion graph convolutional networks for skeleton-based action recognition[J]. Sensors, 2020, 20(24): 7149.
[38] WANG M S, NI B B, YANG X K. Learning multi-view interactional skeleton graph for action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(6): 6940-6954.
[39] ZHANG K, LING W J. Joint motion information extraction and human behavior recognition in video based on deep learning[J]. IEEE Sensors Journal, 2020, 20(20): 11919-11926.
[40] SI C Y, JING Y, WANG W, et al. Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network[J]. Pattern Recognition, 2020, 107: 107511.
[41] KANG M S, KANG D, KIM H. Efficient skeleton-based action recognition via joint-mapping strategies[C]//Proceedings of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2023: 3392-3401.
[42] TRIVEDI N, SARVADEVABHATLA R K. PSUMNet: unified modality part streams are all you need for efficient pose-based action recognition[C]//Proceedings of European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2023: 211-227.
[43] FAN Y Q, WANG X J, LV T Q, et al. Multi-scale adaptive graph convolutional network for skeleton-based action recognition[C]//Proceedings of the 2020 15th International Conference on Computer Science & Education. Piscataway: IEEE, 2020: 517-522.
[44] ZHU A Q, KE Q H, GONG M M, et al. Adaptive local-component-aware graph convolutional network for one-shot skeleton-based action recognition[C]//Proceedings of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2023: 6027-6036.
[45] XIANG W M, LI C, ZHOU Y X, et al. Generative action description prompts for skeleton-based action recognition[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2023: 10242-10251.
[46] LIU K, GAO L, KHAN N M, et al. A vertex-edge graph convolutional network for skeleton-based action recognition[C]//Proceedings of the 2020 IEEE International Symposium on Circuits and Systems. Piscataway: IEEE, 2020: 1-5.
[47] LEE J, LEE M, LEE D, et al. Hierarchically decomposed graph convolutional networks for skeleton-based action recognition[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2023: 10410-10419.
[48] TIAN H Y, MA X, LI X, et al. Skeleton-based action recognition with select-assemble-normalize graph convolutional networks[J]. IEEE Transactions on Multimedia, 2023, 25: 8527-8538.
[49] YIN X P, ZHONG J Q, LIAN D L, et al. Spatiotemporal progressive inward-outward aggregation network for skeleton-based action recognition[J]. Pattern Recognition, 2024, 150: 110262.
[50] CHENG K, ZHANG Y F, HE X Y, et al. Skeleton-based action recognition with shift graph convolutional network[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 180-189.
[51] LIU Z Y, ZHANG H W, CHEN Z H, et al. Disentangling and unifying graph convolutions for skeleton-based action recognition[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 140-149.
[52] FAN Y Q, WANG X J, LV T Q, et al. Multi-scale adaptive graph convolutional network for skeleton-based action recognition[C]//Proceedings of the 2020 15th International Conference on Computer Science & Education. Piscataway: IEEE, 2020: 517-522.
[53] XIN W T, LIN H K, LIU R Y, et al. Is really correlation information represented well in self-attention for skeleton-based action recognition?[C]//Proceedings of the 2023 IEEE International Conference on Multimedia and Expo. Piscataway: IEEE, 2023: 780-785.
[54] HUANG Q, XIE M T, LI X, et al. Skeleton action recognition based on spatio-temporal features[C]//Proceedings of the 2023 IEEE International Conference on Image Processing. Piscataway: IEEE, 2023: 3284-3288.
[55] WU L Y, ZHANG C, ZOU Y X. SpatioTemporal focus for skeleton-based action recognition[J]. Pattern Recognition, 2023, 136: 109231.
[56] DAI M, SUN Z H, WANG T Y, et al. Global spatio-temporal synergistic topology learning for skeleton-based action recognition[J]. Pattern Recognition, 2023, 140: 109540.
[57] HUANG J H, WANG Z M, PENG J, et al. Feature reconstruction graph convolutional network for skeleton-based action recognition[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 106855.
[58] CHENG Q, CHENG J, REN Z L, et al. Multi-scale spatial-temporal convolutional neural network for skeleton-based action recognition[J]. Pattern Analysis and Applications, 2023, 26(3): 1303-1315.
[59] 费树岷, 赵宏涛, 杨艺, 等. 基于时序拓扑非共享图卷积和多尺度时间卷积的骨架行为识别[J]. 信息与控制, 2023, 52(6): 758-772.
FEI S M, ZHAO H T, YANG Y, et al. Temporal topology unshared graph convolution and multiscale temporal convolution for skeleton-based action recognition[J]. Information and Control, 2023, 52(6): 758-772.
[60] 赵登阁, 智敏. 用于人体动作识别的多尺度时空图卷积算法[J]. 计算机科学与探索, 2023, 17(3): 719-732.
ZHAO D G, ZHI M. Spatial multiple-temporal graph convolutional neural network for human action recognition[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(3): 719-732.
[61] PENG Z H, LIU H, JIA Y H, et al. Attention-driven graph clustering network[C]//Proceedings of the 29th ACM International Conference on Multimedia. New York: ACM, 2021: 935-943.
[62] SHI L, ZHANG Y F, CHENG J, et al. Skeleton-based action recognition with multi-stream adaptive graph convolutional networks[J]. IEEE Transactions on Image Processing, 2020, 29: 9532-9545.
[63] DONG J Q, GAO Y B, LEE H J, et al. Action recognition based on the fusion of graph convolutional networks with high order features[J]. Applied Sciences, 2020, 10(4): 1482.
[64] KONG J, DENG H Y, JIANG M. Symmetrical enhanced fusion network for skeleton-based action recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(11): 4394-4408.
[65] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. arXiv:1710.10903, 2017.
[66] KHALIL M I, ABBAS M A. Attention based graph neural networks[C]//Proceedings of the 2023 IEEE 3rd International Conference on Software Engineering and Artificial Intelligence. Piscataway: IEEE, 2023: 86-90.
[67] ZHANG B M, XU M, CHEN M C, et al. CopGAT: co-propagation self-supervised graph attention network[C]//Proceedings of the 2022 IEEE International Conference on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking. Piscataway: IEEE, 2022: 18-25.
[68] RAHEVAR M, GANATRA A, SABA T, et al. Spatial-temporal dynamic graph attention network for skeleton-based action recognition[J]. IEEE Access, 2023, 11: 21546-21553.
[69] HU K, JIN J L, SHEN C W, et al. Attentional weighting strategy-based dynamic GCN for skeleton-based action recognition[J]. Multimedia Systems, 2023, 29(4): 1941-1954.
[70] HU L Y, LIU S L, FENG W. Skeleton-based action recognition with local dynamic spatial-temporal aggregation[J]. Expert Systems with Applications, 2023, 232: 120683.
[71] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141.
[72] SI C Y, CHEN W T, WANG W, et al. An attention enhanced graph convolutional LSTM network for skeleton-based action recognition[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 1227-1236.
[73] SONG Y F, ZHANG Z, SHAN C F, et al. Stronger, faster and more explainable: a graph convolutional baseline for skeleton-based action recognition[C]//Proceedings of the 28th ACM International Conference on Multimedia. New York: ACM, 2020: 1625-1633.
[74] QIU H Y, WU Y, DUAN M M, et al. GLTA-GCN: global-local temporal attention graph convolutional network for unsupervised skeleton-based action recognition[C]//Proceedings of the 2022 IEEE International Conference on Multimedia and Expo. Piscataway: IEEE, 2022: 1-6.
[75] ZHANG M Y, QUAN Z Z, WANG W, et al. ASMGCN: attention-based semantic-guided multistream graph convolution network for skeleton action recognition[J]. IEEE Sensors Journal, 2024, 24(12): 20064-20075.
[76] YANG H Y, GU Y Z, ZHU J C, et al. PGCN-TCA: pseudo graph convolutional network with temporal and channel-wise attention for skeleton-based action recognition[J]. IEEE Access, 2020, 8: 10040-10047.
[77] ZHONG Q B, ZHENG C M, ZHANG H X. Research on discriminative skeleton-based action recognition in spatiotemporal fusion and human-robot interaction[J]. Complexity, 2020, 2020: 8717942.
[78] SONG Y F, ZHANG Z, SHAN C F, et al. Constructing stronger and faster baselines for skeleton-based action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(2): 1474-1488.
[79] LIU X Y, ZHOU S P, WANG L, et al. Parallel attention interaction network for few-shot skeleton-based action recognition[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2023: 1379-1388.
[80] SHI L, ZHANG Y F, CHENG J, et al. Two-stream adaptive graph convolutional networks for skeleton-based action recognition[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 12018-12027.
[81] YE F F, PU S L, ZHONG Q Y, et al. Dynamic GCN: context-enriched topology learning for skeleton-based action recognition[C]//Proceedings of the 28th ACM International Conference on Multimedia. New York: ACM, 2020: 55-63.
[82] HU Z S, PAN Z H, WANG Q, et al. Forward-reverse adaptive graph convolutional networks for skeleton-based action recognition[J]. Neurocomputing, 2022, 492: 624-636.
[83] CHENG K, ZHANG Y F, CAO C Q, et al. Decoupling GCN with DropGraph module for skeleton-based action recognition[C]//Proceedings of the 16th European Conference on Computer Vision. Cham: Springer, 2020: 536-553.
[84] CHEN Z, LI S C, YANG B, et al. Multi-scale spatial temporal graph convolutional network for skeleton-based action recognition[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2021: 1113-1122.
[85] CHEN Y X, ZHANG Z Q, YUAN C F, et al. Channel-wise topology refinement graph convolution for skeleton-based action recognition[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 13339-13348.
[86] CHI H G, HA M H, CHI S, et al. InfoGCN: representation learning for human skeleton-based action recognition[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 20154-20164.
[87] YUSSIF S B, XIE N, YANG Y, et al. Self-relational graph convolution network for skeleton-based action recognition[C]//Proceedings of the 31st ACM International Conference on Multimedia. New York: ACM, 2023: 27-36.
[88] LEE J, LEE M, CHO S, et al. Leveraging spatio-temporal dependency for skeleton-based action recognition[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2023: 10221-10230.
[89] JANG S, LEE H, KIM W J, et al. Multi-scale structural graph convolutional network for skeleton-based action recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(8): 7244-7258.
[90] SHAHROUDY A, LIU J, NG T T, et al. NTU RGB D: a large scale dataset for 3D human activity analysis[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 1010-1019.
[91] LIU J, SHAHROUDY A, PEREZ M, et al. NTU RGB D 120: a large-scale benchmark for 3D human activity understanding[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(10): 2684-2701.
[92] WANG J, NIE X H, XIA Y, et al. Cross-view action modeling, learning, and recognition[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 2649-2656.
[93] KAY W, CARREIRA J, SIMONYAN K, et al. The kinetics human action video dataset[J]. arXiv:1705.06950, 2017.
[94] LI T J, LIU J, ZHANG W, et al. UAV-human: a large benchmark for human behavior understanding with unmanned aerial vehicles[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 16261-16270.
[95] SHAO D, ZHAO Y, DAI B, et al. FineGym: a hierarchical video dataset for fine-grained action understanding[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 2613-2622.
[96] LI Y W, LI Y, VASCONCELOS N. RESOUND: towards action recognition without representation bias[C]//Proceedings of the 15th European Conference on Computer Vision. Cham: Springer, 2018: 520-535.
[97] DAI R, DAS S, SHARMA S, et al. Toyota smarthome untrimmed: real-world untrimmed videos for activity detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(2): 2533-2550.
[98] ZHOU Y X, YAN X D, CHENG Z Q, et al. BlockGCN: redefine topology awareness for skeleton-based action recognition[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 2049-2058.
[99] YUN X, XU C L, RIOU K, et al. Behavioral recognition of skeletal data based on targeted dual fusion strategy[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2024: 6917-6925.
[100] XIE J Y, MENG Y D, ZHAO Y T, et al. Dynamic semantic-based spatial graph convolution network for skeleton-based human action recognition[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2024: 6225-6233.
[101] QU H X, CAI Y J, LIU J. LLMs are good action recognizers[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 18395-18406.
[102] ABDELFATTAH M, HASSAN M, ALAHI A. MaskCLR: attention-guided contrastive learning for robust action representation learning[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 18678-18687.
[103] ZHOU H Y, LIU Q J, WANG Y H. Learning discriminative representations for skeleton based action recognition[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 10608-10617.
[104] CHANG H C, CHEN J, LI Y L, et al. Wavelet-decoupling contrastive enhancement network for fine-grained skeleton-based action recognition[C]//Proceedings of the 2024 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2024: 4060-4064.