arjunmajum/vln-bert
Code for the paper "Improving Vision-and-Language Navigation with Image-Text Pairs from the Web" (ECCV 2020)
Python
Issues
- 0
- 0
Could you add a license file?
#17 opened by lavenderrz - 0
How to perform the data preprocessing
#16 opened by IMNearth - 1
Reproducing resources requirement
#15 opened by g-jing - 4
Access to trained model
#14 opened by g-jing - 5
Executing Training Script
#13 opened by ManaalAhi - 1
- 3
Reproducing full model's weights
#10 opened by guhur - 3
Speaker + follower + VLNBERT baseline
#9 opened by guhur - 2
Generating metrics for testing
#8 opened by guhur - 3
Sharing precomputed dataset
#4 opened by guhur - 2
Converting results file into sucess rate
#7 opened by guhur - 2
Model differs from weights
#6 opened by guhur - 1
Distances file
#5 opened by guhur - 1
- 2
Adding config file
#2 opened by guhur - 1