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
  • [41] Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognition
    Qin Cheng
    Jun Cheng
    Ziliang Ren
    Qieshi Zhang
    Jianming Liu
    Pattern Analysis and Applications, 2023, 26 (3) : 1303 - 1315
  • [42] Adaptive Channel-Enhanced Graph Convolution for Skeleton-Based Human Action Recognition
    Han, Xiao-Wei
    Chen, Xing-Yu
    Cui, Ying
    Guo, Qiu-Yang
    Hu, Wen
    APPLIED SCIENCES-BASEL, 2024, 14 (18):
  • [43] MTT: Multi-Scale Temporal Transformer for Skeleton-Based Action Recognition
    Kong, Jun
    Bian, Yuhang
    Jiang, Min
    IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 528 - 532
  • [44] PART AWARE GRAPH CONVOLUTION NETWORK WITH TEMPORAL ENHANCEMENT FOR SKELETON-BASED ACTION RECOGNITION
    Huang, Qian
    Nie, Yunqing
    Li, Xing
    Yang, Tianjin
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 3255 - 3259
  • [45] SelfGCN: Graph Convolution Network With Self-Attention for Skeleton-Based Action Recognition
    Wu, Zhize
    Sun, Pengpeng
    Chen, Xin
    Tang, Keke
    Xu, Tong
    Zou, Le
    Wang, Xiaofeng
    Tan, Ming
    Cheng, Fan
    Weise, Thomas
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 4391 - 4403
  • [46] Auxiliary Task Graph Convolution Network: A Skeleton-Based Action Recognition for Practical Use
    Cho, Junsu
    Kim, Seungwon
    Oh, Chi-Min
    Park, Jeong-Min
    APPLIED SCIENCES-BASEL, 2025, 15 (01):
  • [47] Dual-Stream Structured Graph Convolution Network for Skeleton-Based Action Recognition
    Xu, Chunyan
    Liu, Rong
    Zhang, Tong
    Cui, Zhen
    Yang, Jian
    Hu, Chunlong
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2021, 17 (04)
  • [48] Dual-Excitation SpatialTemporal Graph Convolution Network for Skeleton-Based Action Recognition
    Lu, Jian
    Huang, Tingting
    Zhao, Bo
    Chen, Xiaogai
    Zhou, Jian
    Zhang, Kaibing
    IEEE SENSORS JOURNAL, 2024, 24 (06) : 8184 - 8196
  • [49] Semantics-Assisted Training Graph Convolution Network for Skeleton-Based Action Recognition
    Hu, Huangshui
    Cao, Yu
    Fang, Yue
    Meng, Zhiqiang
    Sensors, 2025, 25 (06)
  • [50] Skeleton-based Action Recognition with Graph Involution Network
    Tang, Zhihao
    Xia, Hailun
    Gao, Xinkai
    Gao, Feng
    Feng, Chunyan
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 3348 - 3354