Vision And Language Navigation On Map2Seq
Metrics
Task Completion (TC)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Task Completion (TC) |
|---|---|
| flame-learning-to-navigate-with-multimodal | 52.44 |
| analyzing-generalization-of-vision-and | 45.1 |
| analyzing-generalization-of-vision-and | 46.7 |
| analyzing-generalization-of-vision-and | 14.7 |
| analyzing-generalization-of-vision-and | 17 |