Text-to-Video Retrieval on DiDeMo 12 (test)
45.3R@1InternVideo2-1B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| InternVideo2-1BParams=1412M, Search Pool Size=1,0032026.01 | 45.3 | 71.6 | 79.6 | 257 | |
| CLIP4CLIPParams=151M, Search Pool Size=1,0032026.01 | 43.4 | 70.2 | 80.6 | 245 | |
| X-PoolParams=153M, Search Pool Size=1,0032026.01 | 41.4 | 70.6 | 79.9 | 394 | |
| GRDRParams=63M, Search Pool Size=1,0032026.01 | 39.9 | 65.8 | 74.2 | 118 | |
| T2VIndexerParams=144M, Search Pool Size=1,0032026.01 | 34.8 | 53.4 | 60.4 | 179 | |
| EERCFParams=164M, Search Pool Size=1,0032026.01 | 27.1 | 54.5 | 63.8 | 2,292 | |
| AVGParams=69M, Search Pool Size=1,0032026.01 | 24.9 | 40.5 | 45.3 | 235 | |
| TIGERParams=69M, Search Pool Size=1,0032026.01 | 17.4 | 28.9 | 32.8 | 242 |