A Lightweight Graph Neural Network Algorithm for Action Recognition Based on Self-Distillation
Algorithms · 01.12.2023 · 16 (12) · 552
DOI: 10.3390/a16120552 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 01.12.2023. Verfasst von Miao Feng und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Scholarship Council (CSC), Natural Sciences and Engineering Research Council of Canada (NSERC).
Abstract (Originalsprache)
Recognizing human actions can help in numerous ways, such as health monitoring, intelligent surveillance, virtual reality and human–computer interaction. A quick and accurate detection algorithm is required for daily real-time detection. This paper first proposes to generate a lightweight graph neural network by self-distillation for human action recognition tasks. The lightweight graph neural network was evaluated on the NTU-RGB+D dataset. The results demonstrate that, with competitive accuracy, the heavyweight graph neural network can be compressed by up to 80%. Furthermore, the learned representations have denser clusters, estimated by the Davies–Bouldin index, the Dunn index and silhouette coefficients. The ideal input data and algorithm capacity are also discussed.
Förderung
- China Scholarship Council (CSC)
- Natural Sciences and Engineering Research Council of Canada (NSERC)
Zitieren
APA
Feng, M., & Meunier, J. (2023). A Lightweight Graph Neural Network Algorithm for Action Recognition Based on Self-Distillation. Algorithms, 16(12), 552. https://doi.org/10.3390/a16120552
Vancouver
Feng M, Meunier J. A Lightweight Graph Neural Network Algorithm for Action Recognition Based on Self-Distillation. Algorithms. 2023;16(12):552. doi:10.3390/a16120552
BibTeX
@article{Feng2023,
author = {Feng, Miao and Meunier, Jean},
title = {A Lightweight Graph Neural Network Algorithm for Action Recognition Based on Self-Distillation},
journal = {Algorithms},
year = {2023},
volume = {16},
number = {12},
pages = {552},
doi = {10.3390/a16120552}
}
EUVIMED