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
Stargazers
- AbecidUC Berkeley
- airsplayUNC
- cacosandonperhaps
- d-behl
- daoyuan98Tencent
- dpjaneswww.davidjanes.com
- DzienBakanae
- eric-xwUniversity of California, Santa Cruz
- FangliangBai
- fly51flyPRIS
- francescomilano172Zürich, Switzerland
- ggsonic
- gmrukwa@Clari
- hartzelljkh
- hbb1ShanghaiTech
- hongweizengXi'an Jiaotong University
- Huangying-ZhanOPPO US Research Center
- jianjieluoSun Yat-sen University & JD AI Research
- kthejokerDatabricks
- ma7devMalaa Technologies
- MaciejMacko
- MohitShridharUniversity of Washington
- narayanacharya6New York
- purug2000@microsoft
- rajaboja
- rajnathaniSan Francisco
- rhee
- rmantSantiago de Chile
- shurjobanerjeeThe University of Michigan
- StOnEGiggity
- TheShadow29Meta
- vincentlux
- VincentqywTHU
- yestinl
- zedavidSemasio
- zkytonyBoston Dynamics AI Institute