Action Recognition Models
Approximating Spatiotemporal Representations Using a 2DCNN
Introduced by Parmar et al. in HalluciNet-ing Spatiotemporal Representations Using a 2D-CNNApproximating Spatiotemporal Representations Using a 2DCNN
Source: HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Action Anticipation | 1 | 12.50% |
| Action Classification | 1 | 12.50% |
| Action Quality Assessment | 1 | 12.50% |
| Action Recognition | 1 | 12.50% |
| Action Recognition In Still Images | 1 | 12.50% |
| Fine-grained Action Recognition | 1 | 12.50% |
| Multi-Task Learning | 1 | 12.50% |
| Scene Recognition | 1 | 12.50% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
