Uporedite metode

	Konvolucione neuronske mreže zasnovane na prostorno-vremenskim grafovima	Swin Transformer
Oblast	Duboko učenje	Duboko učenje
Porodica	Machine learning	Machine learning
Godina nastanka	2018	2021
Tvorac	Sijie Yan	Ze Liu
Tip	Neural network architecture	Neural network architecture
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).	Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 10012-10022).
Drugi nazivi	ST-GCN, Spatial-Temporal Graph CNN	Swin, Hierarchical Vision Transformer
Srodne	4	4
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 Swin Transformer is a hierarchical vision transformer introduced by Liu et al. in 2021 that uses shifted window attention to achieve computational efficiency while maintaining strong performance on computer vision tasks. Unlike the original Vision Transformer which applies global self-attention, Swin uses local window-based attention with periodic shifting to balance expressiveness and efficiency.