Text-to-Video Retrieval on ActivityNet 11 (test)
47.4R@1InternVideo2-1B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| InternVideo2-1BParams=1412M, Search Pool Size=4,9172026.01 | 47.4 | 76 | 85.2 | 1,214 | |
| EERCFParams=164M, Search Pool Size=4,9172026.01 | 43.1 | 74.5 | 86 | 5,179 | |
| CLIP4CLIPParams=151M, Search Pool Size=4,9172026.01 | 40.5 | 72.4 | — | 1,211 | |
| X-PoolParams=153M, Search Pool Size=4,9172026.01 | 35 | 65.9 | 78.5 | 1,899 | |
| GRDRParams=63M, Search Pool Size=4,9172026.01 | 33.7 | 63.7 | 76.6 | 125 | |
| T2VIndexerParams=144M, Search Pool Size=4,9172026.01 | 26 | 46.4 | 53.9 | 183 | |
| AVGParams=69M, Search Pool Size=4,9172026.01 | 14.3 | 26.4 | 30.5 | 237 | |
| TIGERParams=69M, Search Pool Size=4,9172026.01 | 8.9 | 15.9 | 18.3 | 243 |