Temporal 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-IdentificationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Action Recognition | 20 | 4.32% |
Time Series Analysis | 14 | 3.02% |
Video Generation | 13 | 2.81% |
Decoder | 12 | 2.59% |
Temporal Action Localization | 9 | 1.94% |
Activity Recognition | 8 | 1.73% |
Graph Attention | 8 | 1.73% |
Video Understanding | 8 | 1.73% |
Denoising | 7 | 1.51% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |