TFC-GCN: Lightweight Temporal Feature Cross-Extraction Graph Convolutional Network for Skeleton-Based Action Recognition

被引:5
|
作者
Wang, Kaixuan [1 ]
Deng, Hongmin [1 ]
机构
[1] Sichuan Univ, Coll Elect & Informat Engn, 24,Sect 1,First Ring Rd, Chengdu 610041, Peoples R China
基金
中国国家自然科学基金;
关键词
deep learning; action recognition; graph convolutional networks; lightweight;
D O I
10.3390/s23125593
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
For skeleton-based action recognition, graph convolutional networks (GCN) have absolute advantages. Existing state-of-the-art (SOTA) methods tended to focus on extracting and identifying features from all bones and joints. However, they ignored many new input features which could be discovered. Moreover, many GCN-based action recognition models did not pay sufficient attention to the extraction of temporal features. In addition, most models had swollen structures due to too many parameters. In order to solve the problems mentioned above, a temporal feature cross-extraction graph convolutional network (TFC-GCN) is proposed, which has a small number of parameters. Firstly, we propose the feature extraction strategy of the relative displacements of joints, which is fitted for the relative displacement between its previous and subsequent frames. Then, TFC-GCN uses a temporal feature cross-extraction block with gated information filtering to excavate high-level representations for human actions. Finally, we propose a stitching spatial-temporal attention (SST-Att) block for different joints to be given different weights so as to obtain favorable results for classification. FLOPs and the number of parameters of TFC-GCN reach 1.90 G and 0.18 M, respectively. The superiority has been verified on three large-scale public datasets, namely NTU RGB + D60, NTU RGB + D120 and UAV-Human.
引用
收藏
页数:19
相关论文
共 50 条
  • [21] An improved spatial temporal graph convolutional network for robust skeleton-based action recognition
    Xing, Yuling
    Zhu, Jia
    Li, Yu
    Huang, Jin
    Song, Jinlong
    APPLIED INTELLIGENCE, 2023, 53 (04) : 4592 - 4608
  • [22] Enhanced Spatial and Extended Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
    Li, Fanjia
    Li, Juanjuan
    Zhu, Aichun
    Xu, Yonggang
    Yin, Hongsheng
    Hua, Gang
    SENSORS, 2020, 20 (18) : 1 - 19
  • [23] DD-GCN: Directed Diffusion Graph Convolutional Network for Skeleton-based Human Action Recognition
    Li, Chang
    Huang, Qian
    Mao, Yingchi
    2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 786 - 791
  • [24] Fast Temporal Graph Convolutional Model for Skeleton-Based Action Recognition
    Nan, Mihai
    Florea, Adina Magda
    SENSORS, 2022, 22 (19)
  • [25] Mini-TKAGCN: a lightweight Graph Convolutional Network via Temporal Kernel Attention for Skeleton-based Action Recognition
    Liu, Yanan
    Dong, Shiqi
    Zhang, Hao
    Xu, Dan
    Li, Haipeng
    THIRTEENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2021), 2022, 12083
  • [26] Lightweight Long and Short-Range Spatial-Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
    Chen, Hongbo
    Li, Menglei
    Jing, Lei
    Cheng, Zixue
    IEEE ACCESS, 2021, 9 : 161374 - 161382
  • [27] Temporal segment graph convolutional networks for skeleton-based action recognition
    Ding, Chongyang
    Wen, Shan
    Ding, Wenwen
    Liu, Kai
    Belyaev, Evgeny
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2022, 110
  • [28] Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
    Yan, Sijie
    Xiong, Yuanjun
    Lin, Dahua
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 7444 - 7452
  • [29] Lightweight channel-topology based adaptive graph convolutional network for skeleton-based action recognition
    Wang K.
    Deng H.
    Zhu Q.
    Neurocomputing, 2023, 560
  • [30] Spatial Temporal Variation Graph Convolutional Networks (STV-GCN) for Skeleton-Based Emotional Action Recognition
    Tsai, Ming-Fong
    Chen, Chiung-Hung
    IEEE ACCESS, 2021, 9 : 13870 - 13877