Video-Text Retrieval on VATEX (HGR)
65.4R@1CLIP2TV-ViT16
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CLIP2TV-ViT16Backbone=ViT-B/162021.11 | 65.4 | 92.7 | 96.6 | 1 | 2.9 | |
| CLIP2TV+SDStochastic Distillation=true2021.11 | 61.5 | 90.9 | 95.6 | 1 | 3.7 | |
| CLIP2TV2021.11 | 61.4 | 90.6 | 95.2 | 1 | 3.7 | |
| CLIP2Video2021.11 | 61.2 | 90.9 | 95.6 | 1 | 3.4 | |
| CLIP4Clip-seqTransf*2021.11 | 60.3 | 89.1 | 94.4 | 1 | 4.5 | |
| SUPPORT-SET2021.11 | 44.9 | 82.1 | 89.7 | 1 | — | |
| CLIP-straight2021.11 | 39.7 | 72.3 | 82.2 | 2 | 12.8 |