MVV-IN

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

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

Robots4 results

Visual NavigationonAI2-THOR
SPL (All)· 2020-09-01
17.27
SOTA
Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning arXiv:2009.00402
Visual NavigationonAI2-THOR
Success Rate (All)· 2020-09-01
48.7
SOTA
Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning arXiv:2009.00402
Visual NavigationonAI2-THOR
Success Rate (L≥5)· 2020-09-01
30.9
SOTA
Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning arXiv:2009.00402
Visual NavigationonAI2-THOR
SPL (L≥5)· 2020-09-01
13.63
best: 13.91 (SAVN)
Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning arXiv:2009.00402