Visual Commonsense Reasoning On Vcr Q Ar Dev
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||
|---|---|---|---|
| PEVL | 57.8 | PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models |
0 of 1 row(s) selected.
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||
|---|---|---|---|
| PEVL | 57.8 | PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models |