Multimodal Deep Learning on VALSE actant swap
Metric: Accuracy (%) (higher is better)
Metric: Accuracy (%) (higher is better)
| # | Model↕ | Accuracy (%)▼ | Augmentations | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ViLBERT 12-in-1 | 52.2 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 2 | ViLBERT | 50.4 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 3 | VisualBERT | 49.7 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |
| 4 | LXMERT | 48.5 | No | VALSE: A Task-Independent Benchmark for Vision a... | 2021-12-14 | Code |