Machine learningDeep Learning, Graph Neural Networks, Action Recognition

Konvolucione neuronske mreže zasnovane na prostorno-vremenskim grafovima

Konvolucione neuronske mreže zasnovane na prostorno-vremenskim grafovima (ST-GCN) su arhitektura koju su uveli Yan i saradnici 2018. godine za prepoznavanje akcija na osnovu skeleta. Modeliranjem ljudskih skeleta kao grafova gde su zglobovi čvorovi, a kosti grane, ST-GCN primenjuje grafičke konvolucije kroz prostor i vreme radi prepoznavanja akcija iz sekvenci skeleta.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Konvolucione neuronske mreže zasnovane na prostorno-vremenskim grafovima
Mamba (model prostora st…Swin TransformerVision MambaVision TransformerGraphRAGN-BEATSx

Izvori

  1. 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). link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Spatial-Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. ScholarGate. https://scholargate.app/sr/deep-learning/spatial-temporal-gcn

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateSpatial-Temporal GCN (Spatial-Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/spatial-temporal-gcn · Skup podataka: https://doi.org/10.5281/zenodo.20539026