Vision And Language Navigation On Touchdown
Metrics
Task Completion (TC)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Task Completion (TC) |
|---|---|
| touchdown-natural-language-navigation-and | 5.5 |
| flame-learning-to-navigate-with-multimodal | 40.20 |
| multimodal-text-style-transfer-for-outdoor | 14.9 |
| analyzing-generalization-of-vision-and | 29.1 |
| multimodal-text-style-transfer-for-outdoor | 11.9 |
| retouchdown-adding-touchdown-to-streetlearn | 12.8 |
| multimodal-text-style-transfer-for-outdoor | 11.8 |
| learning-to-stop-a-simple-yet-effective | 14.13 |
| analyzing-generalization-of-vision-and | 24.2 |
| multimodal-text-style-transfer-for-outdoor | 16.2 |
| touchdown-natural-language-navigation-and | 10.7 |
| learning-to-stop-a-simple-yet-effective | 16.68 |