Text-to-Video Retrieval on Charades
15.9R@5TrajViT-2
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| TrajViT-2mode=Zero-shot2026.02 | 15.9 | — | — | |
| TrajViTEvaluation Protocol=Zero-shot, Training Samples=4M2025.05 | 14.9 | — | — | |
| TrajViTmode=Zero-shot2026.02 | 14.7 | — | — | |
| ViT3Dmode=Zero-shot2026.02 | 13.8 | — | — | |
| RLTEvaluation Protocol=Zero-shot, Training Samples=4M2025.05 | 13.4 | — | — | |
| ViT3DEvaluation Protocol=Zero-shot, Training Samples=4M2025.05 | 12.9 | — | — | |
| ViViTmode=Zero-shot2026.02 | 12.3 | — | — | |
| RLTmode=Zero-shot2026.02 | 12.2 | — | — | |
| ViViTEvaluation Protocol=Zero-shot, Training Samples=4M2025.05 | 12 | — | — | |
| TokenLearnermode=Zero-shot2026.02 | 12 | — | — | |
| TokenLearnerEvaluation Protocol=Zero-shot, Training Samples=4M2025.05 | 11.7 | — | — | |
| AutoMergeEvaluation Protocol=Zero-shot, Training Samples=4M2025.05 | 10.3 | — | — | |
| ToMeEvaluation Protocol=Zero-shot, Training Samples=4M2025.05 | 10.2 | — | — | |
| Clip4clip2026.01 | — | 9.9 | 36.8 | |
| HVD2026.01 | — | 18.8 | 54.6 | |
| T-Mass2026.01 | — | 14.2 | 48.3 |