Seq2Seq Baseline

Reported on 7 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Robots7 results

Visual NavigationonCooperative Vision-and-Dialogue Navigation
dist_to_end_reduction· 2019-07-10
2.35
best: 7.9 (NaviLLM)
SOTA
Vision-and-Dialog Navigation arXiv:1907.04957
Visual NavigationonCooperative Vision-and-Dialogue Navigation
spl· 2019-07-10
0.16
best: 0.25 (Best SPL)
SOTA
Vision-and-Dialog Navigation arXiv:1907.04957
Vision and Language NavigationonVLN Challenge
error
7.85
best: 1.61 (human)
Vision and Language NavigationonVLN Challenge
length
8.13
best: 1257.38 (Speaker-Follower)
Vision and Language NavigationonVLN Challenge
oracle success
0.27
best: 1 (FOAM-Beam Search)
Vision and Language NavigationonVLN Challenge
spl
0.18
best: 0.76 (human)
Vision and Language NavigationonVLN Challenge
success
0.2
best: 0.86 (human)