2020/01/10 by Harsh Mehta, Mehta, Harsh, Yoav Artzi +7 · 3 citations
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Geographic Information Systems Studies #Human Mobility and Location-Based Analysis #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.2001.03671
openalex publication_date 2020/01/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The Touchdown dataset (Chen et al., 2019) provides instructions by human\nannotators for navigation through New York City streets and for resolving\nspatial descriptions at a given location. To enable the wider research\ncommunity to work effectively with the Touchdown tasks, we are publicly\nreleasing the 29k raw Street View panoramas needed for Touchdown. We follow the\nprocess used for the StreetLearn data release (Mirowski et al., 2019) to check\npanoramas for personally identifiable information and blur them as necessary.\nThese have been added to the StreetLearn dataset and can be obtained via the\nsame process as used previously for StreetLearn. We also provide a reference\nimplementation for both of the Touchdown tasks: vision and language navigation\n(VLN) and spatial description resolution (SDR). We compare our model results to\nthose given in Chen et al. (2019) and show that the panoramas we have added to\nStreetLearn fully support both Touchdown tasks and can be used effectively for\nfurther research and comparison.\n