Visual Question Answering On Vizwiz 2018 1
Metrics
overall
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| LXR955, No Ensemble | 55.4 | LXMERT: Learning Cross-Modality Encoder Representations from Transformers |
| fw_vqa_ | 54.93 | - |
| Pythia v0.3 | 54.72 | Towards VQA Models That Can Read |
| B-Ultra | 53.68 | Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering |
| DVW | 52.23 | - |
| DVizWiz | 51.71 | - |
| BAN | 51.61 | - |
| ss | 47.6 | - |
| hdhs | 47.32 | - |
| Colin | 45.53 | - |
0 of 10 row(s) selected.