Visual Grounding on Multi-Concept Personalized VLM Benchmark
72.3VGMC-LLaVA
Evaluation results
| Method | Links | |
|---|---|---|
| MC-LLaVA2024.11 | 72.3 | |
| GPT-4V + PromptPrompting=true2024.11 | 68.1 | |
| Qwen2.5-VL-7B + PromptPrompting=true2024.11 | 60.6 |
| Method | Links | |
|---|---|---|
| MC-LLaVA2024.11 | 72.3 | |
| GPT-4V + PromptPrompting=true2024.11 | 68.1 | |
| Qwen2.5-VL-7B + PromptPrompting=true2024.11 | 60.6 |