VLN-Bert

Reported on 5 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots5 results

Vision and Language NavigationonVLN Challenge
error· 2020-04-30
3.09
best: 1.61 (human)
SOTA
Improving Vision-and-Language Navigation with Image-Text Pairs from the Web arXiv:2004.14973
Vision and Language NavigationonVLN Challenge
success· 2020-04-30
0.73
best: 0.86 (human)
SOTA
Improving Vision-and-Language Navigation with Image-Text Pairs from the Web arXiv:2004.14973
Vision and Language NavigationonVLN Challenge
length· 2020-04-30
686.62
best: 1257.38 (Speaker-Follower)
Improving Vision-and-Language Navigation with Image-Text Pairs from the Web arXiv:2004.14973
Vision and Language NavigationonVLN Challenge
oracle success· 2020-04-30
0.99
best: 1 (FOAM-Beam Search)
Improving Vision-and-Language Navigation with Image-Text Pairs from the Web arXiv:2004.14973
Vision and Language NavigationonVLN Challenge
spl· 2020-04-30
0.01
best: 0.76 (human)
Improving Vision-and-Language Navigation with Image-Text Pairs from the Web arXiv:2004.14973