📊 Showing 4 results | 📏 Metric: Val m_vIoU
| Rank | Model | Paper | Val m_vIoU | Date | Code |
|---|---|---|---|---|---|
| 1 | TA-STVG | Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding | 40.20 | 2025-02-16 | 📦 HengLan/TA-STVG |
| 2 | CG-STVG | Context-Guided Spatio-Temporal Video Grounding | 39.50 | 2024-01-03 | 📦 henglan/cgstvg 📦 shaohuadong2021/dplnet |
| 3 | STVGFormer | STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding | 38.70 | 2022-07-06 | - |
| 4 | TubeDETR | TubeDETR: Spatio-Temporal Video Grounding with Transformers | 36.40 | 2022-03-30 | 📦 antoyang/TubeDETR |