Action Segmentation On Coin
Metrics
Frame accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Frame accuracy |
|---|---|
| multi-granularity-correspondence-learning-1 | 69.8 |
| vlm-task-agnostic-video-language-model-pre | 68.4 |
| end-to-end-learning-of-visual-representations | 53.9 |
| end-to-end-learning-of-visual-representations | 61.0 |
| videoclip-contrastive-pre-training-for-zero | 68.7 |
| unloc-a-unified-framework-for-video | 72.8 |
| taco-token-aware-cascade-contrastive-learning | 68.4 |
| actbert-learning-global-local-video-text-1 | 57.0 |
| univilm-a-unified-video-and-language-pre | 70.0 |