Action Recognition on UCF-101 Few-shot
94.6Top-1 AccuracyTC-CLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| TC-CLIPShots (K)=16, Text Augmentation=None2024.04 | 94.6 | |
| TC-CLIPShots (K)=16, Text Augmentation=LLM-based2024.04 | 94.3 | |
| OSTShots (K)=16, Text Augmentation=LLM-based2024.04 | 93.9 | |
| ViFi-CLIPShots (K)=16, Text Augmentation=None2024.04 | 92.7 | |
| TC-CLIPShots (K)=8, Text Augmentation=None2024.04 | 92.5 | |
| TC-CLIPShots (K)=8, Text Augmentation=LLM-based2024.04 | 92 | |
| OSTShots (K)=8, Text Augmentation=LLM-based2024.04 | 91.7 | |
| X-CLIPShots (K)=16, Text Augmentation=None2024.04 | 91.4 | |
| TC-CLIPShots (K)=4, Text Augmentation=LLM-based2024.04 | 90.1 | |
| ViFi-CLIPShots (K)=8, Text Augmentation=None2024.04 | 90 | |
| A5Shots (K)=16, Text Augmentation=None2024.04 | 89.9 | |
| TC-CLIPShots (K)=4, Text Augmentation=None2024.04 | 89.9 | |
| X-CLIPShots (K)=8, Text Augmentation=None2024.04 | 88.3 | |
| OSTShots (K)=4, Text Augmentation=LLM-based2024.04 | 87.5 | |
| TC-CLIPShots (K)=2, Text Augmentation=LLM-based2024.04 | 86.8 | |
| TC-CLIPShots (K)=2, Text Augmentation=None2024.04 | 85.9 | |
| A5Shots (K)=8, Text Augmentation=None2024.04 | 85.7 | |
| ViFi-CLIPShots (K)=4, Text Augmentation=None2024.04 | 85.1 | |
| X-CLIPShots (K)=4, Text Augmentation=None2024.04 | 83.4 | |
| OSTShots (K)=2, Text Augmentation=LLM-based2024.04 | 82.5 | |
| ActionCLIPShots (K)=16, Text Augmentation=None2024.04 | 81.4 | |
| ViFi-CLIPShots (K)=2, Text Augmentation=None2024.04 | 80.7 | |
| A5Shots (K)=4, Text Augmentation=None2024.04 | 79.9 | |
| X-CLIPShots (K)=2, Text Augmentation=None2024.04 | 76.4 | |
| ActionCLIPShots (K)=8, Text Augmentation=None2024.04 | 73 | |
| ActionCLIPShots (K)=4, Text Augmentation=None2024.04 | 71.5 | |
| A5Shots (K)=2, Text Augmentation=None2024.04 | 71.4 | |
| ActionCLIPShots (K)=2, Text Augmentation=None2024.04 | 70.6 | |
| Vanilla CLIPShots (K)=2, Text Augmentation=None2024.04 | 63.6 | |
| Vanilla CLIPShots (K)=16, Text Augmentation=None2024.04 | 63.6 |