EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Kaixuan Wang, Hongmin Deng

Sensors · 15.06.2023 · 23 (12) · 5593

DOI: 10.3390/s23125593 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.06.2023. Verfasst von Kaixuan Wang und 1 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronics and Information Engineering, Sichuan University, No. 24, Section 1, First Ring Road, Wuhou District, Chengdu 610041, China. Hauptthemen laut MEDLINE: Skeleton, Musculoskeletal System. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Sichuan Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SkeletonMusculoskeletal SystemHumansRecognition, PsychologyRecordsSeizures

Stichwörter der Autor:innen

action recognitiondeep learninggraph convolutional networkslightweight

Autor:innen und Institutionen

  • College of Electronics and Information Engineering, Sichuan University, No. 24, Section 1, First Ring Road, Wuhou District, Chengdu 610041, China.

Förderung

  • Natural Science Foundation of Sichuan Province
  • National Natural Science Foundation of China

Zitieren

APA

Wang, K., & Deng, H. (2023). TFC-GCN: Lightweight Temporal Feature Cross-Extraction Graph Convolutional Network for Skeleton-Based Action Recognition. Sensors, 23(12), 5593. https://doi.org/10.3390/s23125593

Vancouver

Wang K, Deng H. TFC-GCN: Lightweight Temporal Feature Cross-Extraction Graph Convolutional Network for Skeleton-Based Action Recognition. Sensors. 2023;23(12):5593. doi:10.3390/s23125593

BibTeX
@article{Wang2023,
  author = {Wang, Kaixuan and Deng, Hongmin},
  title = {TFC-GCN: Lightweight Temporal Feature Cross-Extraction Graph Convolutional Network for Skeleton-Based Action Recognition},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {12},
  pages = {5593},
  doi = {10.3390/s23125593}
}
Kostenlos starten →