A 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 AssessmentPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Disentanglement | 6 | 12.77% |
Motion Disentanglement | 6 | 12.77% |
Text-to-Video Generation | 2 | 4.26% |
Video Generation | 2 | 4.26% |
Depth Estimation | 2 | 4.26% |
Self-Supervised Learning | 2 | 4.26% |
Motion Estimation | 1 | 2.13% |
Optical Flow Estimation | 1 | 2.13% |
Video Editing | 1 | 2.13% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |