Video-to-Text Retrieval on MSRVTT
50.1R@1MAMA
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| MAMABase Model=CLIP-ViP2026.01 | 50.1 | 76.8 | 84.8 | — | — | |
| DiscoVLABackbone=CLIP (ViT-B/16), # Params (M)=0.562025.06 | 49.2 | 76 | 84.7 | 209.9 | 8.6 | |
| Vid2SeqBase Model=CLIP-ViP2026.01 | 49.1 | 74.1 | 82.5 | — | — | |
| LaViLaBase Model=CLIP-ViP2026.01 | 49 | 74.5 | 83.4 | — | — | |
| CLIP-ViP2026.01 | 48 | 72.4 | 82.9 | — | — | |
| DiscoVLABackbone=CLIP (ViT-B/32), # Params (M)=0.562025.06 | 47.7 | 73.6 | 83.6 | 204.9 | 10 | |
| TempMeBackbone=CLIP (ViT-B/16), # Params (M)=0.502025.06 | 47.6 | 75.3 | 85.4 | 208.3 | 9 | |
| VindLU2026.01 | 46 | 71.8 | 80.2 | — | — | |
| DGLBackbone=CLIP (ViT-B/16), # Params (M)=0.832025.06 | 45.7 | 74 | 82.9 | 202.6 | 10.9 | |
| TempMeBackbone=CLIP (ViT-B/32), # Params (M)=0.502025.06 | 45.6 | 72.4 | 81.2 | 199.2 | 10.2 | |
| MV-AdapterBackbone=CLIP (ViT-B/16), # Params (M)=3.62025.06 | 45.6 | 74 | 83.8 | 203.4 | — | |
| RAPBackbone=CLIP (ViT-B/16), # Params (M)=1.062025.06 | 45.3 | 76.4 | 84.8 | 206.5 | 9.1 | |
| DRL2026.01 | 45.1 | 72.9 | 83.5 | — | — | |
| DGLBackbone=CLIP (ViT-B/32), # Params (M)=0.832025.06 | 44.5 | 70.7 | 80.6 | 195.8 | 11.5 | |
| RAPBackbone=CLIP (ViT-B/32), # Params (M)=1.062025.06 | 44 | 71.9 | 82.4 | 198.3 | 10.1 | |
| AdapterBackbone=CLIP (ViT-B/32), # Params (M)=0.262025.06 | 43.6 | 69.9 | 80.1 | 193.6 | 11.5 | |
| VoP F+PBackbone=CLIP (ViT-B/32), # Params (M)=0.42025.06 | 43.6 | 71.2 | 81.2 | 196 | 11 | |
| CLIP2Video2026.01 | 43.5 | 72.3 | 82.1 | — | — | |
| Full fine-tuningBackbone=CLIP (ViT-B/32), # Params (M)=123.542025.06 | 43.1 | 70.5 | 81.2 | 194.8 | 12.4 | |
| CLIP4Clip2026.01 | 43.1 | 70.5 | 81.2 | — | — | |
| LORABackbone=CLIP (ViT-B/32), # Params (M)=0.492025.06 | 43 | 70.2 | 82.2 | 195.4 | 12 | |
| PromptBackbone=CLIP (ViT-B/32), # Params (M)=0.082025.06 | 42.2 | 69.7 | 79.2 | 191.1 | 12.4 | |
| VoP F+CBackbone=CLIP (ViT-B/32), # Params (M)=14.102025.06 | 42.1 | 70 | 80.6 | 192.7 | 13.4 | |
| VIOLET2026.01 | 36.6 | 64.1 | 75.1 | — | — |