G3D is a unified spatial-temporal graph convolutional operator that directly models cross-spacetime joint dependencies. It leverages dense cross-spacetime edges as skip connections for direct information propagation across the 3D spatial-temporal graph.
Source: Disentangling and Unifying Graph Convolutions for Skeleton-Based Action RecognitionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
3D Action Recognition | 1 | 25.00% |
Action Recognition | 1 | 25.00% |
Long-range modeling | 1 | 25.00% |
Skeleton Based Action Recognition | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |