Skeleton-Based Action Segmentation With Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks
IEEE Transactions on Emerging Topics in Computing · 2024-01 · 12 (1) · 202-212
DOI: 10.1109/tetc.2022.3230912 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Emerging Topics in Computing, 2024-01. Verfasst von Benjamin Filtjens und 2 weiteren Autor:innen. Die Arbeit wurde bisher 83-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: KU Leuven.
Abstract (Originalsprache)
The ability to identify and temporally segment fine-grained actions in motion capture sequences is crucial for applications in human movement analysis. Motion capture is typically performed with optical or inertial measurement systems, which encode human movement as a time series of human joint locations and orientations or their higher-order representations. State-of-the-art action segmentation approaches use multiple stages of temporal convolutions. The main idea is to generate an initial prediction with several layers of temporal convolutions and refine these predictions over multiple stages, also with temporal convolutions. Although these approaches capture long-term temporal patterns, the initial predictions do not adequately consider the spatial hierarchy among the human joints. To address this limitation, we recently introduced multi-stage spatial-temporal graph convolutional neural networks (MS-GCN). Our framework replaces the initial stage of temporal convolutions with spatial graph convolutions and dilated temporal convolutions, which better exploit the spatial configuration of the joints and their long-term temporal dynamics. Our framework was compared to four strong baselines on five tasks. Experimental results demonstrate that our framework is a strong baseline for skeleton-based action segmentation.
Förderung
- KU Leuven
Zitieren
APA
Filtjens, B., Vanrumste, B., & Slaets, P. (2024). Skeleton-Based Action Segmentation With Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks. IEEE Transactions on Emerging Topics in Computing, 12(1), 202-212. https://doi.org/10.1109/tetc.2022.3230912
Vancouver
Filtjens B, Vanrumste B, Slaets P. Skeleton-Based Action Segmentation With Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks. IEEE Transactions on Emerging Topics in Computing. 2024;12(1):202-212. doi:10.1109/tetc.2022.3230912
BibTeX
@article{Filtjens2024,
author = {Filtjens, Benjamin and Vanrumste, Bart and Slaets, Peter},
title = {Skeleton-Based Action Segmentation With Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks},
journal = {IEEE Transactions on Emerging Topics in Computing},
year = {2024},
volume = {12},
number = {1},
pages = {202--212},
doi = {10.1109/tetc.2022.3230912}
}
EUVIMED