Temporally Consistent Spatial Augmentation is a video data augmentation technique used for contrastive learning in the Contrastive Video Representation Learning framework. It fixes the randomness of spatial augmentation across frames; this prevents spatial augmentation hurting learning if applied independently across frames, because in that case it breaks the natural motion. In contrast, having temporally consistent spatial augmentation does not break the natural motion in the frames.
Source: Spatiotemporal Contrastive Video Representation LearningPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Self-Supervised Learning | 2 | 40.00% |
Action Recognition | 1 | 20.00% |
Self-Supervised Action Recognition | 1 | 20.00% |
Unsupervised Pre-training | 1 | 20.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |