Spatio-Temporal Video Grounding on VidSTG Interrogative Sentence
29.5m_vIoUTA-STVG
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| TA-STVGSetting=Fully Sup2025.12 | 29.5 | 50.2 | 41.5 | 28 | |
| CG-STVGSetting=Fully Sup2025.12 | 29 | 49.9 | 40.5 | 27.5 | |
| STVGFormerSetting=Fully Sup2025.12 | 28.5 | — | 39.9 | 26.2 | |
| STCATSetting=Fully Sup2025.12 | 28.2 | 49.7 | 39.2 | 26.6 | |
| DEViLSetting=LLM2025.12 | 27.7 | 47.3 | 37.5 | 25.5 | |
| TubeDETRSetting=Fully Sup2025.12 | 25.7 | 46.9 | 35.7 | 23.2 | |
| STVGBertSetting=Fully Sup2025.12 | 22.5 | — | 26 | 16 | |
| LLaVA-STSetting=LLM2025.12 | 6.8 | 27.5 | 8.3 | 3.9 |