Explanatory Visual Question Answering
Explanatory Visual Question Answering (EVQA) requires answering visual questions and generating multimodal explanations for the reasoning processes.
Papers
Showing 1–5 of 5 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | VCIN | BLEU-4 | 58.65 | — | Unverified |
| 2 | REX-LXMERT | BLEU-4 | 54.79 | — | Unverified |
| 3 | REX-VisualBert | BLEU-4 | 54.59 | — | Unverified |
| 4 | VQAE | BLEU-4 | 42.56 | — | Unverified |
| 5 | EXP | BLEU-4 | 42.45 | — | Unverified |