Visual Question Answering (VQA) on GQA
Metric: Accuracy (higher is better)
LeaderboardDataset
Loading chart...
Results
Submit a result| # | Model↕ | Accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | PEVL+ | 77 | No | PEVL: Position-enhanced Pre-training and Prompt ... | 2022-05-23 | Code |
| 2 | RelViT | 65.54 | No | RelViT: Concept-guided Vision Transformer for Vi... | 2022-04-24 | Code |
| 3 | LocVLM-L | 50.2 | No | Learning to Localize Objects Improves Spatial Re... | 2024-04-11 | Code |