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 |
|---|---|---|
| Video Generation | 32 | 4.62% |
| Action Recognition | 25 | 3.61% |
| Time Series Analysis | 15 | 2.17% |
| Prediction | 14 | 2.02% |
| Decoder | 14 | 2.02% |
| Denoising | 11 | 1.59% |
| Temporal Action Localization | 10 | 1.45% |
| Activity Recognition | 9 | 1.30% |
| Graph Attention | 9 | 1.30% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
