Uporedite metode

	Konvolucione neuronske mreže zasnovane na prostorno-vremenskim grafovima	Vision Transformer
Oblast	Duboko učenje	Duboko učenje
Porodica	Machine learning	Machine learning
Godina nastanka	2018	2021
Tvorac	Sijie Yan	Dosovitskiy, A. et al.
Tip	Neural network architecture	Transformer architecture for images (self-attention over patches)
Temeljni izvor	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).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Drugi nazivi	ST-GCN, Spatial-Temporal Graph CNN	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Srodne	4	5
Sažetak	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.	The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).