Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation
Open paper
Benchmark
Model
Rank
Results
visual-navigation-on-room-to-room-1
DUET
#5
spl: 0.58
visual-navigation-on-soon-test
DUET
#4
Nav-SPL: 21.42
SR: 33.44
Rank counts only results with a code link.