Paragraph-to-video retrieval on QuerYD (test)
84.2R@1TESTA w/o agg.
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| TESTA w/o agg.#PT Data=5M, #Frame=96, GFLOPS=2383, token_aggregation=disabled2023.10 | 84.2 | 93.8 | 95.1 | |
| TESTA#PT Data=5M, #Frame=96, GFLOPS=13812023.10 | 83.4 | 93.8 | 95.3 | |
| TESTA w/o agg.#PT Data=5M, #Frame=32, GFLOPS=786, token_aggregation=disabled2023.10 | 79.7 | 92.6 | 95.5 | |
| TESTA#PT Data=5M, #Frame=32, GFLOPS=4202023.10 | 77 | 91.3 | 94.6 | |
| LF-VILA#PT Data=8M, #Frame=32, GFLOPS=2982023.10 | 69.7 | 85.7 | 90.3 | |
| VINDLU#PT Data=25M, #Frame=32, GFLOPS=745, implementation=re-implementation2023.10 | 67.8 | 86.3 | 81.8 | |
| TESTAPre-training Data=5M, GFLOPS=786, Evaluation Protocol=Zero-shot, Frames=322023.10 | 64.4 | 82.9 | 86.9 | |
| Frozen#PT Data=5M, #Frame=32, GFLOPS=14242023.10 | 53.8 | 75.7 | 82.7 | |
| BLIPPre-training Data=129M, GFLOPS=707, Evaluation Protocol=Zero-shot, Frames=322023.10 | 50.7 | 67.6 | 73.5 | |
| Clip4ClipPre-training Data=400M, GFLOPS=282, Evaluation Protocol=Zero-shot, Frames=322023.10 | 50 | 74.5 | 83.3 | |
| TeachText2023.10 | 14.4 | 37.7 | 50.9 | |
| MoEE2023.10 | 11.6 | 30.2 | 43.2 |