Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View
This work provides a shareable resource for the research community working on language grounding tasks in street view, but it is incremental as it primarily involves data release and validation.
The authors released 29k raw Street View panoramas needed for the Touchdown dataset, making it shareable via StreetLearn, and provided a reference implementation for vision and language navigation and spatial description resolution tasks, showing that the panoramas fully support these tasks.
The Touchdown dataset (Chen et al., 2019) provides instructions by human annotators for navigation through New York City streets and for resolving spatial descriptions at a given location. To enable the wider research community to work effectively with the Touchdown tasks, we are publicly releasing the 29k raw Street View panoramas needed for Touchdown. We follow the process used for the StreetLearn data release (Mirowski et al., 2019) to check panoramas for personally identifiable information and blur them as necessary. These have been added to the StreetLearn dataset and can be obtained via the same process as used previously for StreetLearn. We also provide a reference implementation for both of the Touchdown tasks: vision and language navigation (VLN) and spatial description resolution (SDR). We compare our model results to those given in Chen et al. (2019) and show that the panoramas we have added to StreetLearn fully support both Touchdown tasks and can be used effectively for further research and comparison.