Comparer des méthodes

	Réseaux de convolution sur graphes spatio-temporels	TimeGPT
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2018	2023
Auteur d'origine	Sijie Yan	Fabio Garza
Type	Neural network architecture	Neural network architecture
Source fondatrice	Yan, S., Xiong, Y., & Lin, D. (2018). Spatial temporal graph convolutional networks for skeleton-based action recognition. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 32).	Garza, F., & White, C. W. (2023). TimeGPT-1: A Time Series Foundation Model. In ICML 2024 Time Series Workshop.
Alias	ST-GCN, Spatial-Temporal Graph CNN	TimeGPT-1, Time series GPT
Apparentées	4	4
Résumé	Spatial-Temporal Graph Convolutional Networks (ST-GCN) is an architecture introduced by Yan et al. in 2018 for skeleton-based action recognition. By modeling human skeletons as graphs where joints are nodes and bones are edges, ST-GCN applies graph convolutions across space and time to recognize actions from skeleton sequences.	TimeGPT is a time series foundation model introduced by Garza and White in 2023 that unifies forecasting, anomaly detection, and classification in a single pre-trained model. Inspired by large language models, TimeGPT is pre-trained on diverse time series and transfers well to downstream tasks with minimal fine-tuning.