- P
RxR Dataset
- paperswithcode.com
Updated Jul 8, 2024
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCiteAlexander Ku; Peter Anderson; Roma Patel; Eugene Ie; Jason Baldridge (2024). RxR Dataset [Dataset]. https://paperswithcode.com/dataset/rxrDataset updatedJul 8, 2024AuthorsAlexander Ku; Peter Anderson; Roma Patel; Eugene Ie; Jason BaldridgeDescriptionRoom-Across-Room (RxR) is a multilingual dataset for Vision-and-Language Navigation (VLN) for Matterport3D environments. In contrast to related datasets such as Room-to-Room (R2R), RxR is 10x larger, multilingual (English, Hindi and Telugu), with longer and more variable paths, and it includes and fine-grained visual groundings that relate each word to pixels/surfaces in the environment.
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailRoom-Across-Room (RxR) is a multilingual dataset for Vision-and-Language Navigation (VLN) for Matterport3D environments. In contrast to related datasets such as Room-to-Room (R2R), RxR is 10x larger, multilingual (English, Hindi and Telugu), with longer and more variable paths, and it includes and fine-grained visual groundings that relate each word to pixels/surfaces in the environment.