Attention Mechanisms
Temporal attention
Introduced by Xu et al. in Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-IdentificationTemporal attention can be seen as a dynamic time selection mechanism determining when to pay attention, and is thus usually used for video processing.
Source: Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Action Recognition | 20 | 4.20% |
| Video Generation | 14 | 2.94% |
| Time Series Analysis | 14 | 2.94% |
| Decoder | 12 | 2.52% |
| Temporal Action Localization | 9 | 1.89% |
| Activity Recognition | 8 | 1.68% |
| Graph Attention | 8 | 1.68% |
| Video Understanding | 8 | 1.68% |
| Denoising | 7 | 1.47% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
