Visual Question Answering On Coco Visual 3
Metrics
Percentage correct
Results
Performance results of various models on this benchmark
Model Name | Percentage correct | Paper Title | Repository |
|---|---|---|---|
| Dualnet ensemble | 71.18 | VQA: Visual Question Answering | |
| LSTM + global features | 69.21 | VQA: Visual Question Answering | |
| LSTM blind | 61.41 | VQA: Visual Question Answering | |
| Graph VQA | 74.37 | Graph-Structured Representations for Visual Question Answering | - |
0 of 4 row(s) selected.