Visual Question Answering On Vqa V1 Test Std
評価指標
Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| NMN+LSTM+FT | 58.7 | Neural Module Networks | |
| DMN+ | 60.4 | Dynamic Memory Networks for Visual and Textual Question Answering | |
| HieCoAtt (ResNet) | 62.1 | Hierarchical Question-Image Co-Attention for Visual Question Answering | |
| SAAA (ResNet) | 64.6 | Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering | |
| RAU (ResNet) | 63.2 | Training Recurrent Answering Units with Joint Loss Minimization for VQA | - |
| SAN (VGG) | 58.9 | Stacked Attention Networks for Image Question Answering |
0 of 6 row(s) selected.