Adaptive Multi-Scale Difference Graph Convolution Network for Skeleton-Based Action Recognition

被引:2
|
作者
Wang, Xiaojuan [1 ]
Gan, Ziliang [1 ]
Jin, Lei [1 ]
Xiao, Yabo [1 ]
He, Mingshu [1 ]
机构
[1] Beijing Univ Posts & Telecommun, Sch Elect Engn, 10 Xitucheng Rd, Beijing 100876, Peoples R China
基金
中国国家自然科学基金;
关键词
skeleton-based action recognition; graph convolution networks; difference convolution;
D O I
10.3390/electronics12132852
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Graph convolutional networks (GCNs) have obtained remarkable performance in skeleton-based action recognition. However, previous approaches fail to capture the implicit correlations between joints and handle actions across varying time intervals. To address these problems, we propose an adaptive multi-scale difference graph convolution Network (AMD-GCN), which comprises an adaptive spatial graph convolution module (ASGC) and a multi-scale temporal difference convolution module (MTDC). The first module is capable of acquiring data-dependent and channel-wise graphs that are adaptable to both samples and channels. The second module employs the multi-scale approach to model temporal information across a range of time scales. Additionally, the MTDC incorporates an attention-enhanced module and difference convolution to accentuate significant channels and enhance temporal features, respectively. Finally, we propose a multi-stream framework for integrating diverse skeletal modalities to achieve superior performance. Our AMD-GCN approach was extensively tested and proven to outperform the current state-of-the-art methods on three widely recognized benchmarks: the NTU-RGB+D, NTU-RGB+D 120, and Kinetics Skeleton datasets.
引用
收藏
页数:19
相关论文
共 50 条
  • [21] Multi-scale Spatial and Temporal Feature Aggregation Graph Convolutional Network for Skeleton-Based Action Recognition
    Du, Yifei
    Zhang, Mingliang
    Li, Bin
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2024, PT VII, 2025, 15037 : 511 - 524
  • [22] Adaptive multi-level graph convolution with contrastive learning for skeleton-based action recognition
    Geng, Pei
    Li, Haowei
    Wang, Fuyun
    Lyu, Lei
    SIGNAL PROCESSING, 2022, 201
  • [23] Multi-scale skeleton adaptive weighted GCN for skeleton-based human action recognition in IoT
    Xu Weiyao
    Wu Muqing
    Zhu Jie
    Zhao Min
    APPLIED SOFT COMPUTING, 2021, 104
  • [24] Multi-scale sampling attention graph convolutional networks for skeleton-based action recognition
    Tian, Haoyu
    Zhang, Yipeng
    Wu, Hanbo
    Ma, Xin
    Li, Yibin
    NEUROCOMPUTING, 2024, 597
  • [25] Channel attention and multi-scale graph neural networks for skeleton-based action recognition
    Dang, Ronghao
    Liu, Chengju
    Liu, Ming
    Chen, Qijun
    AI COMMUNICATIONS, 2022, 35 (03) : 187 - 205
  • [26] Temporal channel reconfiguration multi-graph convolution network for skeleton-based action recognition
    Lei, Siyue
    Tang, Bin
    Chen, Yanhua
    Zhao, Mingfu
    Xu, Yifei
    Long, Zourong
    IET COMPUTER VISION, 2024, 18 (06) : 813 - 825
  • [27] Combining Adaptive Graph Convolution and Temporal Modeling for Skeleton-Based Action Recognition
    Zhen, Haoyu
    Zhang, De
    Computer Engineering and Applications, 2023, 59 (18) : 137 - 144
  • [28] Multi-stream adaptive 3D attention graph convolution network for skeleton-based action recognition
    Yu, Lubin
    Tian, Lianfang
    Du, Qiliang
    Bhutto, Jameel Ahmed
    APPLIED INTELLIGENCE, 2023, 53 (12) : 14838 - 14854
  • [29] Skeleton-based multi-stream adaptive-attentional sub-graph convolution network for action recognition
    Liu, Huan
    Wu, Jian
    Ma, Haokai
    Yan, Yuqi
    He, Rui
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (1) : 2935 - 2958
  • [30] Skeleton-based multi-stream adaptive-attentional sub-graph convolution network for action recognition
    Huan Liu
    Jian Wu
    Haokai Ma
    Yuqi Yan
    Rui He
    Multimedia Tools and Applications, 2024, 83 : 2935 - 2958