google-research-datasets/RxR
Room-across-Room (RxR) is a large-scale, multilingual dataset for Vision-and-Language Navigation (VLN) in Matterport3D environments. It contains 126k navigation instructions in English, Hindi and Telugu, and 126k navigation following demonstrations. Both annotation types include dense spatiotemporal alignments between the text and the visual perceptions of the annotators
PythonCC-BY-4.0
Issues
- 1
RxR leaderboard
#13 opened by ashutoshpndy - 0
Question regarding pose traces
#12 opened by SaumyaSaxena - 0
- 0
I can't download the dataset
#10 opened by jdiazram - 1
Visualization not working
#9 opened by Yihao21 - 0
Access to the jpg images from an instruction
#8 opened by agelosk - 2
- 2
- 2
Saving Visualizations as GIFs?
#5 opened by FelixLabelle - 3
Exact size of the dataset
#3 opened by shurjobanerjee - 1
- 1