Action Recognition Models
Self-Supervised Motion Disentanglement
Introduced by Parmar et al. in Domain Knowledge-Informed Self-Supervised Representations for Workout Form AssessmentA self-supervised learning method to disentangle irregular (anomalous) motion from regular motion in unlabeled videos.
Source: Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Disentanglement | 5 | 11.63% |
| Motion Disentanglement | 5 | 11.63% |
| Depth Estimation | 2 | 4.65% |
| Self-Supervised Learning | 2 | 4.65% |
| Motion Estimation | 1 | 2.33% |
| Optical Flow Estimation | 1 | 2.33% |
| Text-to-Video Generation | 1 | 2.33% |
| Video Editing | 1 | 2.33% |
| Video Generation | 1 | 2.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
