Room-across-Room
Room-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.
Source: Room-Across-Room (RxR) Dataset
Variants: RxR
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Vision and Language Navigation | MARVAL | A New Path: Scaling Vision-and-Language … | 2022-10-06 |
| Vision and Language Navigation | EnvEdit-PT | EnvEdit: Environment Editing for Vision-and-Language … | 2022-03-29 |
| Vision and Language Navigation | HAMT | History Aware Multimodal Transformer for … | 2021-10-25 |
| Vision and Language Navigation | CLEAR-CLIP | How Much Can CLIP Benefit … | 2021-07-13 |
| Vision and Language Navigation | Monolingual Baseline | Room-Across-Room: Multilingual Vision-and-Language Navigation with … | 2020-10-15 |
| Vision and Language Navigation | Multilingual Baseline | Room-Across-Room: Multilingual Vision-and-Language Navigation with … | 2020-10-15 |
Recent papers with results on this dataset: