Action Recognition Models
Temporaral Difference Network
Introduced by Wang et al. in TDN: Temporal Difference Networks for Efficient Action RecognitionTDN, or Temporaral Difference Network, is an action recognition model that aims to capture multi-scale temporal information. To fully capture temporal information over the entire video, the TDN is established with a two-level difference modeling paradigm. Specifically, for local motion modeling, temporal difference over consecutive frames is used to supply 2D CNNs with finer motion pattern, while for global motion modeling, temporal difference across segments is incorporated to capture long-range structure for motion feature excitation.
Source: TDN: Temporal Difference Networks for Efficient Action Recognition
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Denoising | 2 | 10.53% |
| Action Recognition | 2 | 10.53% |
| Action Recognition In Videos | 2 | 10.53% |
| Topological Data Analysis | 1 | 5.26% |
| Chemical Process | 1 | 5.26% |
| Fault Detection | 1 | 5.26% |
| Fault Diagnosis | 1 | 5.26% |
| Fault localization | 1 | 5.26% |
| Human Detection | 1 | 5.26% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
