Text-to-Video Retrieval on ActivityNet 11 (full-corpus)
33.9R@1InternVideo2-1B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| InternVideo2-1BParams=1412M, Search Pool Size=14,9262026.01 | 33.9 | 59.5 | 70.9 | 3,661 | |
| X-PoolParams=153M, Search Pool Size=14,9262026.01 | 21.5 | 45.7 | 57.9 | 5,641 | |
| CLIP4CLIPParams=151M, Search Pool Size=14,9262026.01 | 20.5 | 43.4 | 55.6 | 3,658 | |
| GRDRParams=63M, Search Pool Size=14,9262026.01 | 19.2 | 41.1 | 51.8 | 116 | |
| EERCFParams=164M, Search Pool Size=14,9262026.01 | 18.9 | 41.3 | 53.4 | 7,628 | |
| T2VIndexerParams=144M, Search Pool Size=14,9262026.01 | 17.5 | 37.9 | 49 | 207 | |
| AVGParams=69M, Search Pool Size=14,9262026.01 | 4.9 | 9.9 | 12.4 | 219 | |
| TIGERParams=69M, Search Pool Size=14,9262026.01 | 3.7 | 6.6 | 8.1 | 248 |