Touchdown Dataset
Introduced by Chen et al. in Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
Touchdown is a corpus for executing navigation instructions and resolving spatial descriptions in visual real-world environments. The task is to follow instruction to a goal position and there find a hidden object, Touchdown the bear.
Source: https://github.com/lil-lab/touchdownBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Touchdown Dataset
|
ORAR + junction type + heading delta
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
