Explanatory Visual Question Answering On Gqa
Metriken
BLEU-4
CIDEr
GQA-test
GQA-val
Grounding
METEOR
ROUGE-L
SPICE
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | BLEU-4 | CIDEr | GQA-test | GQA-val | Grounding | METEOR | ROUGE-L | SPICE | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|---|---|
| VCIN | 58.65 | 519.23 | 60.61 | 81.80 | 77.33 | 41.57 | 81.45 | 54.63 | Variational Causal Inference Network for Explanatory Visual Question Answering | |
| REX-LXMERT | 54.79 | 466.01 | 58.15 | 78.19 | 70.79 | 39.51 | 79.41 | 49.98 | REX: Reasoning-aware and Grounded Explanation | |
| EXP | 42.45 | 357.10 | 56.92 | 65.17 | 33.52 | 34.46 | 73.51 | 40.35 | Faithful Multimodal Explanation for Visual Question Answering | |
| VQAE | 42.56 | 358.20 | 57.24 | 65.19 | 31.29 | 34.51 | 73.59 | 40.39 | VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions | - |
| REX-VisualBert | 54.59 | 464.20 | 57.77 | 66.16 | 67.95 | 39.22 | 78.56 | 46.80 | REX: Reasoning-aware and Grounded Explanation |
0 of 5 row(s) selected.