Video on Condensed Movies
Metric: text-to-video R@10 (higher is better)
LeaderboardDataset
Loading chart...
Results
Submit a result| # | Model↕ | text-to-video R@10▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | TESTA (ViT-B/16) | 55.1 | Yes | TESTA: Temporal-Spatial Token Aggregation for Lo... | 2023-10-29 | Code |
| 2 | VINDLU | 44.3 | Yes | VindLU: A Recipe for Effective Video-and-Languag... | 2022-12-09 | Code |
| 3 | LF-VILA | 41.8 | Yes | Long-Form Video-Language Pre-Training with Multi... | 2022-10-12 | Code |