Spatio Temporal Video Grounding On Vidstg
評価指標
Declarative m_vIoU
Declarative vIoU@0.3
Declarative vIoU@0.5
Interrogative m_vIoU
Interrogative vIoU@0.3
Interrogative vIoU@0.5
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 | Declarative m_vIoU | Declarative vIoU@0.3 | Declarative vIoU@0.5 | Interrogative m_vIoU | Interrogative vIoU@0.3 | Interrogative vIoU@0.5 | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|
| TubeDETR | 30.4 | 42.5 | 28.2 | 25.7 | 35.7 | 23.2 | TubeDETR: Spatio-Temporal Video Grounding with Transformers | |
| TA-STVG | 34.4 | 48.2 | 33.5 | 29.5 | 41.5 | 28.0 | Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding | - |
| CG-STVG | 34.0 | 47.7 | 33.1 | 29.0 | 40.5 | 27.5 | Context-Guided Spatio-Temporal Video Grounding |
0 of 3 row(s) selected.