Spatio-Temporal Video Grounding 벤치마크
Spatio-Temporal Video Grounding on VidSTG
Declarative m_vIoU
- 2022-03-30 — TubeDETR: Declarative m_vIoU 30.4
- 2024-01-03 — CG-STVG: Declarative m_vIoU 34.0
- 2025-02-16 — TA-STVG: Declarative m_vIoU 34.4
| Rank | Model | Declarative m_vIoU | Declarative vIoU@0.3 | Declarative vIoU@0.5 | Interrogative m_vIoU | Interrogative vIoU@0.3 | Interrogative vIoU@0.5 | Paper | Code | Year |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | 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 | HengLan/TA-STVG | 2025 |
| 2 | CG-STVG | 34.0 | 47.7 | 33.1 | 29.0 | 40.5 | 27.5 | Context-Guided Spatio-Temporal Video Grounding | henglan/cgstvg · shaohuadong2021/dplnet | 2024 |
| 3 | TubeDETR | 30.4 | 42.5 | 28.2 | 25.7 | 35.7 | 23.2 | TubeDETR: Spatio-Temporal Video Grounding with Transformers | antoyang/TubeDETR | 2022 |