Video Retrieval On Tgif
評価指標
text-to-video R@1
text-to-video R@10
text-to-video R@5
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | text-to-video R@1 | text-to-video R@10 | text-to-video R@5 | Paper Title | Repository |
|---|---|---|---|---|---|
| LAFF | 24.5 | 54.5 | 45.0 | Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval | |
| MDMMT-2 | 25.5 | 55.7 | 46.1 | MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization | - |
0 of 2 row(s) selected.