📊 Showing 4 results | 📏 Metric: Percentage correct
| Rank | Model | Paper | Percentage correct | Date | Code |
|---|---|---|---|---|---|
| 1 | CMN | Modeling Relationships in Referential Expressions with Compositional Modular Networks | 72.53 | 2016-11-30 | 📦 hengyuan-hu/bottom-up-attention-vqa 📦 thilinicooray/Bottom-up-vqa |
| 2 | CTI (with Boxes) | Compact Trilinear Interaction for Visual Question Answering | 72.30 | 2019-09-26 | 📦 aioz-ai/ICCV19_VQA-CTI |
| 3 | CFR | Coarse-to-Fine Reasoning for Visual Question Answering | 71.90 | 2021-10-06 | 📦 aioz-ai/cfr_vqa 📦 aioz-ai/crf_vqa |
| 4 | MCB+Att. | Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding | 62.20 | 2016-06-06 | 📦 Cadene/vqa.pytorch 📦 MarcBS/keras 📦 akirafukui/vqa-mcb |