Command Palette
Search for a command to run...
Visual Commonsense Reasoning On Vcr Q A Dev
Metrics
Accuracy
Results
Performance results of various models on this benchmark
| Paper Title | Repository | ||
|---|---|---|---|
| PEVL | 75.1 | PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models |
0 of 1 row(s) selected.