Spatio-Temporal Video Grounding on VidSTG Declarative Sentences
34.4m_vIoUTA-STVG
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| TA-STVG2025.02 | 34.4 | 51.7 | 48.2 | 33.5 | |
| TA-STVGSetting=Fully Sup2025.12 | 34.4 | 51.7 | 48.2 | 33.5 | |
| CG-STVG2025.02 | 34 | 51.4 | 47.7 | 33.1 | |
| CG-STVGSetting=Fully Sup2025.12 | 34 | 51.4 | 47.7 | 33.1 | |
| STVGFormer2025.02 | 33.7 | — | 47.2 | 32.8 | |
| STVGFormerSetting=Fully Sup2025.12 | 33.7 | — | 47.2 | 32.8 | |
| STCAT2025.02 | 33.1 | 50.8 | 46.2 | 32.6 | |
| STCATSetting=Fully Sup2025.12 | 33.1 | 50.8 | 46.2 | 32.6 | |
| Baseline2025.02 | 32.3 | 49.5 | 44.9 | 31.6 | |
| DEViLSetting=LLM2025.12 | 32 | 49 | 43.7 | 30.7 | |
| TubeDETR2025.02 | 30.4 | 48.1 | 42.5 | 28.2 | |
| TubeDETRSetting=Fully Sup2025.12 | 30.4 | 48.1 | 42.5 | 28.2 | |
| SGFDN2025.02 | 28.3 | 45.1 | 41.7 | 29.1 | |
| STVGBert2025.02 | 24 | — | 30.9 | 18.4 | |
| STVGBertSetting=Fully Sup2025.12 | 24 | — | 30.9 | 18.4 | |
| OMRN2025.02 | 23.1 | 50.7 | 32.6 | 16.4 | |
| STGVT2025.02 | 21.6 | — | 29.8 | 18.9 | |
| STGVTSetting=Fully Sup2025.12 | 21.6 | — | 29.8 | 18.9 | |
| STGRN2025.02 | 19.8 | 48.5 | 25.8 | 14.6 | |
| LLaVA-STSetting=LLM2025.12 | 8.2 | 28.7 | 10.6 | 5 |