Video-Text Retrieval on ActivityNet (val)
46.3R@1UCOFIA
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| UCOFIA2023.09 | 46.3 | 76.5 | 86.3 | 2 | 6.7 | — | — | |
| UCOFIA2023.09 | 45.7 | 76.6 | 86.6 | 2 | 6.4 | — | — | |
| Ours_wtivariant=wti2023.09 | 44.9 | 76.1 | 86.5 | 2 | — | 6.6 | 207.5 | |
| Ours_tivariant=ti2023.09 | 44.8 | 74.4 | 85.1 | 2 | — | 7.4 | 204.3 | |
| X-CLIP2023.09 | 44.3 | 74.1 | — | — | 7.9 | — | — | |
| DRLre-training=true2023.09 | 44.2 | 74.5 | 86.1 | 2 | — | — | 204.8 | |
| X-CLIP2023.09 | 43.9 | 73.9 | — | — | 7.6 | — | — | |
| CenterCLIP2023.09 | 43.9 | 75.3 | 85.2 | 2 | — | 7 | 204.4 | |
| CLIP4Clip2023.09 | 42.5 | 74.1 | 85.8 | 2 | 6.6 | — | — | |
| Baseline2023.09 | 41.1 | 72.3 | 84.1 | 2 | — | 8.2 | 197.5 | |
| TS2-Net2023.09 | 41 | 73.6 | 84.5 | 2 | 8.4 | — | — | |
| CLIP4Clip2023.09 | 40.5 | 72.4 | 98.2 | 2 | 7.5 | — | — | |
| CLIP4Clip2023.09 | 40.5 | 72.4 | — | 2 | — | 7.5 | — | |
| TS2-Netre-training=true2023.09 | 39.9 | 72.3 | 84.3 | 2 | — | 8.5 | 196.5 | |
| Support set2023.09 | 29.2 | 61.6 | 94.7 | 3 | — | — | — | |
| MMT2023.09 | 28.9 | 61.1 | — | 4 | 17.1 | — | — | |
| MMT2023.09 | 28.7 | 61.4 | 94.5 | 3.3 | 16 | — | — | |
| Support set2023.09 | 28.7 | 60.8 | — | 2 | — | — | — | |
| TT-CE2023.09 | 23.5 | 57.2 | 96.1 | 4 | — | — | — | |
| TT-CE2023.09 | 23 | 56.1 | — | 4 | — | — | — | |
| CE2023.09 | 18.2 | 47.7 | 91.4 | 6 | 23.1 | — | — | |
| CE2023.09 | 17.7 | 46.6 | — | 6 | 24.4 | — | — |