Video-to-Text Retrieval on MSR-VTT 7K
46.9Recall@1CenterCLIP
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CenterCLIPBackbone=ViT-B/16, Algorithm=k-medoids++, Setting=B6 - 4, 160, MeM. (GB)=17.6, Speed (ms)=86.52022.05 | 46.9 | 73.4 | 83.2 | 2 | 9.3 | |
| CLIP4clip (meanP)Backbone=ViT-B/16, MeM. (GB)=25.7, Speed (ms)=59.62022.05 | 46.5 | 73.4 | 82.3 | 2 | 11 | |
| CenterCLIPBackbone=ViT-B/32, Algorithm=spectral, Setting=B6 - 3, 49, MeM. (GB)=14.2, Speed (ms)=43.62022.05 | 43.2 | 71 | 80.4 | 2 | 12.3 | |
| CLIP4clip (meanP)Backbone=ViT-B/32, MeM. (GB)=20.8, Speed (ms)=24.42022.05 | 42.2 | 68.8 | 78.8 | 2 | 12.5 | |
| CenterCLIPBackbone=ViT-B/32, Algorithm=spectral, Setting=B6 - 4, 49, MeM. (GB)=14.9, Speed (ms)=40.82022.05 | 42.1 | 70.5 | 80.6 | 2 | 11.7 | |
| CenterCLIPBackbone=ViT-B/32, Algorithm=k-medoids++, Setting=B6 - 4, 49, MeM. (GB)=15, Speed (ms)=22.92022.05 | 41.8 | 68.9 | 77.9 | 2 | 13.3 | |
| CenterCLIPBackbone=ViT-B/32, Algorithm=k-medoids++, Setting=B6 - 3, 49, MeM. (GB)=14.2, Speed (ms)=22.92022.05 | 40.9 | 68.4 | 78.3 | 2 | 13.4 |