Video Retrieval On Ssv2 Template Retrieval
Metrics
text-to-video R@1
text-to-video R@10
text-to-video R@5
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | text-to-video R@1 | text-to-video R@10 | text-to-video R@5 |
|---|---|---|---|
| vid-tldr-training-free-token-merging-for | 90.2 | 100.0 | 100.0 |
| revealing-single-frame-bias-for-video-and | 77.6 | 98.9 | 96 |
| vindlu-a-recipe-for-effective-video-and | 83.3 | 100 | 100 |
| unmasked-teacher-towards-training-efficient | 90.8 | 100.0 | 100.0 |
| hitea-hierarchical-temporal-aware-video | 85.6 | 100 | 100 |