Improved Graph Convolutional Network with Enriched Graph Topology Representation for Skeleton-Based Action Recognition
Electronics · 09.02.2023 · 12 (4) · 879
DOI: 10.3390/electronics12040879 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 09.02.2023. Verfasst von Tamam Alsarhan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Lately, skeleton-based action recognition has drawn remarkable attention to graph convolutional networks (GCNs). Recent methods have focused on graph learning because graph topology is the key to GCNs. We propose to align graph learning on the channel level by introducing graph convolution with enriched topology based on careful channel-wise correlations, namely the attentive channel-wise correlation graph convolution (ACC-GC). For the model to learn channel-wise enriched topologies, ACC-GC learns a shared graph topology spanning many channels and enhances it with careful channel-wise correlations. Encoding the intra-correlation between various nodes within each channel, boosting informative channel-wise correlations, and suppressing trivial ones generates attentive channel-wise correlations. Our enhanced ACC-GCN is created by substituting our ACC-GC for the GC in a standard GCN. Extensive experiments on NTURGB60 and Northwestern-UCLA datasets demonstrate that our proposed ACC-GCN performs comparably to state-of-the-art methods while reducing the computational cost.
Zitieren
APA
Alsarhan, T., Harfoushi, O., Shdefat, A. Y., Mostafa, N., Alshinwan, M., & Ali, A. (2023). Improved Graph Convolutional Network with Enriched Graph Topology Representation for Skeleton-Based Action Recognition. Electronics, 12(4), 879. https://doi.org/10.3390/electronics12040879
Vancouver
Alsarhan T, Harfoushi O, Shdefat AY, Mostafa N, Alshinwan M, Ali A. Improved Graph Convolutional Network with Enriched Graph Topology Representation for Skeleton-Based Action Recognition. Electronics. 2023;12(4):879. doi:10.3390/electronics12040879
BibTeX
@article{Alsarhan2023,
author = {Alsarhan, Tamam and Harfoushi, Osama and Shdefat, Ahmed Younes and Mostafa, Nour and Alshinwan, Mohammad and Ali, Ahmad},
title = {Improved Graph Convolutional Network with Enriched Graph Topology Representation for Skeleton-Based Action Recognition},
journal = {Electronics},
year = {2023},
volume = {12},
number = {4},
pages = {879},
doi = {10.3390/electronics12040879}
}
EUVIMED