Rendered synthetically using a library of standard 3D objects, and tests the ability to recognize compositions of object movements that require long-term reasoning.
Source: CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning
Image Source: CATER
Variants: CATER
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Atomic action recognition | SCI3D | Deep set conditioned latent representations … | 2022-12-21 |
| Atomic action recognition | R3D-NL | Deep set conditioned latent representations … | 2022-12-21 |
| Atomic action recognition | Single stream SCI3D | Deep set conditioned latent representations … | 2022-12-21 |
| Atomic action recognition | FasterRCNN | Deep set conditioned latent representations … | 2022-12-21 |
Recent papers with results on this dataset: