Spatio Temporal Video Grounding On Hc Stvg2
평가 지표
Val m_vIoU
Val vIoU@0.3
Val vIoU@0.5
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Val m_vIoU | Val vIoU@0.3 | Val vIoU@0.5 | Paper Title | Repository |
|---|---|---|---|---|---|
| CG-STVG | 39.5 | 64.5 | 36.3 | Context-Guided Spatio-Temporal Video Grounding | |
| TA-STVG | 40.2 | 65.8 | 36.7 | Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding | - |
| STVGFormer | 38.7 | 65.5 | 33.8 | STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding | - |
| TubeDETR | 36.4 | 58.8 | 30.6 | TubeDETR: Spatio-Temporal Video Grounding with Transformers |
0 of 4 row(s) selected.