Spatial-Temporal Video Grounding on ST-Align
44.6tIoU@0.5LLaVA-ST
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| LLaVA-STLLM Scale=7B2025.01 | 44.6 | 43.8 | 21.1 | 22.8 | |
| Grounded-VideoLLMLLM Scale=4B2025.01 | 30 | 33 | — | — | |
| GroundingGPTLLM Scale=7B2025.01 | 7.1 | 12.2 | 2.9 | 9.2 | |
| VTimeLLMLLM Scale=7B2025.01 | 7.1 | 15.5 | — | — |